[
  {
    "path": ".gitignore",
    "content": "/.idea/\n"
  },
  {
    "path": "LICENSE",
    "content": "Creative Commons Legal Code\n\nCC0 1.0 Universal\n\n    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE\n    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN\n    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS\n    INFORMATION ON AN \"AS-IS\" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES\n    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS\n    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM\n    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED\n    HEREUNDER.\n\nStatement of Purpose\n\nThe laws of most jurisdictions throughout the world automatically confer\nexclusive Copyright and Related Rights (defined below) upon the creator\nand subsequent owner(s) (each and all, an \"owner\") of an original work of\nauthorship and/or a database (each, a \"Work\").\n\nCertain owners wish to permanently relinquish those rights to a Work for\nthe purpose of contributing to a commons of creative, cultural and\nscientific works (\"Commons\") that the public can reliably and without fear\nof later claims of infringement build upon, modify, incorporate in other\nworks, reuse and redistribute as freely as possible in any form whatsoever\nand for any purposes, including without limitation commercial purposes.\nThese owners may contribute to the Commons to promote the ideal of a free\nculture and the further production of creative, cultural and scientific\nworks, or to gain reputation or greater distribution for their Work in\npart through the use and efforts of others.\n\nFor these and/or other purposes and motivations, and without any\nexpectation of additional consideration or compensation, the person\nassociating CC0 with a Work (the \"Affirmer\"), to the extent that he or she\nis an owner of Copyright and Related Rights in the Work, voluntarily\nelects to apply CC0 to the Work and publicly distribute the Work under its\nterms, with knowledge of his or her Copyright and Related Rights in the\nWork and the meaning and intended legal effect of CC0 on those rights.\n\n1. Copyright and Related Rights. A Work made available under CC0 may be\nprotected by copyright and related or neighboring rights (\"Copyright and\nRelated Rights\"). Copyright and Related Rights include, but are not\nlimited to, the following:\n\n  i. the right to reproduce, adapt, distribute, perform, display,\n     communicate, and translate a Work;\n ii. moral rights retained by the original author(s) and/or performer(s);\niii. publicity and privacy rights pertaining to a person's image or\n     likeness depicted in a Work;\n iv. rights protecting against unfair competition in regards to a Work,\n     subject to the limitations in paragraph 4(a), below;\n  v. rights protecting the extraction, dissemination, use and reuse of data\n     in a Work;\n vi. database rights (such as those arising under Directive 96/9/EC of the\n     European Parliament and of the Council of 11 March 1996 on the legal\n     protection of databases, and under any national implementation\n     thereof, including any amended or successor version of such\n     directive); and\nvii. other similar, equivalent or corresponding rights throughout the\n     world based on applicable law or treaty, and any national\n     implementations thereof.\n\n2. Waiver. To the greatest extent permitted by, but not in contravention\nof, applicable law, Affirmer hereby overtly, fully, permanently,\nirrevocably and unconditionally waives, abandons, and surrenders all of\nAffirmer's Copyright and Related Rights and associated claims and causes\nof action, whether now known or unknown (including existing as well as\nfuture claims and causes of action), in the Work (i) in all territories\nworldwide, (ii) for the maximum duration provided by applicable law or\ntreaty (including future time extensions), (iii) in any current or future\nmedium and for any number of copies, and (iv) for any purpose whatsoever,\nincluding without limitation commercial, advertising or promotional\npurposes (the \"Waiver\"). Affirmer makes the Waiver for the benefit of each\nmember of the public at large and to the detriment of Affirmer's heirs and\nsuccessors, fully intending that such Waiver shall not be subject to\nrevocation, rescission, cancellation, termination, or any other legal or\nequitable action to disrupt the quiet enjoyment of the Work by the public\nas contemplated by Affirmer's express Statement of Purpose.\n\n3. Public License Fallback. Should any part of the Waiver for any reason\nbe judged legally invalid or ineffective under applicable law, then the\nWaiver shall be preserved to the maximum extent permitted taking into\naccount Affirmer's express Statement of Purpose. In addition, to the\nextent the Waiver is so judged Affirmer hereby grants to each affected\nperson a royalty-free, non transferable, non sublicensable, non exclusive,\nirrevocable and unconditional license to exercise Affirmer's Copyright and\nRelated Rights in the Work (i) in all territories worldwide, (ii) for the\nmaximum duration provided by applicable law or treaty (including future\ntime extensions), (iii) in any current or future medium and for any number\nof copies, and (iv) for any purpose whatsoever, including without\nlimitation commercial, advertising or promotional purposes (the\n\"License\"). The License shall be deemed effective as of the date CC0 was\napplied by Affirmer to the Work. Should any part of the License for any\nreason be judged legally invalid or ineffective under applicable law, such\npartial invalidity or ineffectiveness shall not invalidate the remainder\nof the License, and in such case Affirmer hereby affirms that he or she\nwill not (i) exercise any of his or her remaining Copyright and Related\nRights in the Work or (ii) assert any associated claims and causes of\naction with respect to the Work, in either case contrary to Affirmer's\nexpress Statement of Purpose.\n\n4. Limitations and Disclaimers.\n\n a. No trademark or patent rights held by Affirmer are waived, abandoned,\n    surrendered, licensed or otherwise affected by this document.\n b. Affirmer offers the Work as-is and makes no representations or\n    warranties of any kind concerning the Work, express, implied,\n    statutory or otherwise, including without limitation warranties of\n    title, merchantability, fitness for a particular purpose, non\n    infringement, or the absence of latent or other defects, accuracy, or\n    the present or absence of errors, whether or not discoverable, all to\n    the greatest extent permissible under applicable law.\n c. Affirmer disclaims responsibility for clearing rights of other persons\n    that may apply to the Work or any use thereof, including without\n    limitation any person's Copyright and Related Rights in the Work.\n    Further, Affirmer disclaims responsibility for obtaining any necessary\n    consents, permissions or other rights required for any use of the\n    Work.\n d. Affirmer understands and acknowledges that Creative Commons is not a\n    party to this document and has no duty or obligation with respect to\n    this CC0 or use of the Work.\n"
  },
  {
    "path": "README.md",
    "content": "<div align=\"center\">\n\n<p align=\"center\">\n<img width=\"1000px\" alt=\"Awesome DeepSeek Integrations\" src=\"docs/Awesome DeepSeek Integrations.png\">\n</p>\n\n# Awesome DeepSeek Integrations ![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)\n\nIntegrate the DeepSeek API into popular softwares. Access [DeepSeek Open Platform](https://platform.deepseek.com/) to get an API key.\n\nEnglish / [简体中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_cn.md) / [繁體中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_zh_tw.md) / [日本語](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_ja.md) / [Español](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_es.md)\n\n<a href=\"https://trendshift.io/repositories/12798\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/12798\" alt=\"deepseek-ai%2Fawesome-deepseek-integration | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/></a>\n</div>\n\n## Table of Contents\n\n- [Awesome DeepSeek Integrations ](#awesome-deepseek-integrations-)\n  - [Table of Contents](#table-of-contents)\n  - [Project List](#project-list)\n    - [Applications](#applications)\n    - [AI Agent frameworks](#ai-agent-frameworks)\n    - [Data AI Applications frameworks](#data-ai-applications-frameworks)\n    - [RAG frameworks](#rag-frameworks)\n    - [FHE (Fully Homomorphic Encryption) frameworks](#fhe-fully-homomorphic-encryption-frameworks)\n    - [Solana frameworks](#solana-frameworks)\n    - [Synthetic data curation](#synthetic-data-curation)\n    - [IM Application Plugins](#im-application-plugins)\n    - [Office Addin](#office-addin)\n    - [Browser Extensions](#browser-extensions)\n    - [VS Code Extensions](#vs-code-extensions)\n    - [Visual Studio Extensions](#visual-studio-extensions)\n    - [neovim Extensions](#neovim-extensions)\n    - [JetBrains Extensions](#jetbrains-extensions)\n    - [Discord Bots](#discord-bots)\n    - [Native AI Code Editor](#native-ai-code-editor)\n    - [Emacs](#emacs)\n    - [Security](#security)\n    - [Providers](#providers)\n    - [Others](#others)\n    - [Star History](#star-history)\n\n## Project List\n\n###  <span id=\"applications\">Applications</span>\n\n<table>\n    <tr>\n        <td><img src=\"docs/ETOS-LLM-Studio/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"docs/ETOS-LLM-Studio/README.md\">ETOS LLM Studio</a></td>\n        <td>ETOS LLM Studio (ELS) is a flagship AI client explicitly tailored for watchOS and iOS. It features a watch-first design, aesthetic UI, seamless sync between devices, and deep system integration. Supports multiple models including DeepSeek, redefining AI interaction on your wrist.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/operit/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/AAswordman/Operit\">Operit AI</a></td>\n        <td>An open-source system integration AI assistant for the Android platform, supporting almost complete mcp usage and highly compatible with the Android system. The software features both high customization and a low learning threshold, with built-in tools for file operations, searches, automatic clicks, format conversions, and an integrated DeepSeek API webpage.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/openEuler Intelligence/intelligence_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.openeuler.org/en/projects/intelligence/\">openEuler Intelligence</a></td>\n        <td>The intelligent large model platform, built on openEuler, deeply integrates mainstream large language models, including DeepSeek, and features local knowledge base construction capabilities. The platform offers core functionalities such as semantic interface registration, MCP service management, intelligent agent (Agent) development, and automated workflow orchestration. It supports both web and desktop client access, significantly enhancing development efficiency and enterprise-level application experience!</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/hh-wserver/wserver.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/hzmosi/ai-wechat\">WeChat RPA Intelligent Customer Service</a></td>\n        <td>Built-in DeepSeek Official API and Ali Bailian DeepSeek API, with seamless automatic switching when AI services are unavailable, ensuring 24/7 stable operation! This tool is implemented via RPA automation, does not access private interfaces.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/OpenXLab/migo/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://migo.intern-ai.org.cn/\">Migo</a></td>\n        <td>A free AI innovation accelerator offering intelligent Q&A, in-depth paper comprehension, cutting-edge AI tools, and a personal academic knowledge base. As your exploration partner, Migo helps you discover and realize outstanding ideas!</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/eechat/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Lucassssss/eechat\">eechat</a></td>\n        <td>A simple and user-friendly tool for local deployment of large language models, supporting local private deployment of open-source models such as DeepSeek-R1, DLlama 3, Phi-4, Mistral, Gemma 3, etc., while also supporting remote LLM API calls.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://openrouter.ai/brand/logo-grey.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://openrouter.ai/\">OpenRouter</a></td>\n        <td>OpenRouter provides a unified API that gives you access to hundreds of AI models through a single endpoint, while automatically handling fallbacks and selecting the most cost-effective options. Get started with just a few lines of code using your preferred SDK or framework.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/aingdesk/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/aingdesk/AingDesk\">AingDesk</a></td>\n        <td>One-click deployment of AI models on your computer with a visual interface, featuring an elegant chat UI. It allows online sharing for collaborative use, supports various models like DeepSeek, and enables web search and third-party API integration.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/dingtalk/assets/dingtalk_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.dingtalk.com/\">DingTalk</a></td>\n        <td>DingTalk AI Assistant integrates multiple AI product features from the DingTalk platform to intelligently support enterprises in their daily workflows. It possesses various intelligent capabilities, including but not limited to smart communication, smart collaboration, and smart management.\nWith these functionalities, the AI assistant can summarize key points within an organization, generate meeting minutes, and provide users with relevant task notifications and schedule reminders. Additionally, DingTalk AI Assistant leverages its knowledge base to intelligently answer common employee inquiries regarding company administrative processes, HR policies, and other related topics.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://chatdoc.com/chatdoc/chatdoc.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://chatdoc.com\">ChatDOC</a></td>\n        <td>ChatDOC is an AI-powered document reading tool equipped with robust traceability features, ensuring that the source of every piece of information is clear and verifiable, helping you efficiently and accurately grasp the core of your documents.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/SwiftChat/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/SwiftChat/README.md\">SwiftChat</a></td>\n        <td> <a href=\"https://github.com/aws-samples/swift-chat\">SwiftChat</a> is a lightning-fast, cross-platform AI chat application built with React Native. It delivers native performance on Android, iOS, and macOS. Features include real-time streaming chat, rich Markdown support, AI image generation, customizable system prompts, quick model selection and multimodal capabilities. Supports multiple AI providers including DeepSeek, Amazon Bedrock, Ollama and OpenAI Compatible Modles with clean UI and high performance.</td>\n    </tr>\n    </tr>\n    <tr>\n        <td><img src=\"https://4everlogo.4everland.store/logo/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/4EVERChat/README.md\">4EVERChat</a></td>\n        <td><a href=\"https://chat.4everland.org/\">4EVERChat</a> is an intelligent model selection platform integrating hundreds of LLMs, enabling real-time comparison of model performance. Leveraging <a href=\"https://www.4everland.org/\">4EVERLAND</a> AI RPC's unified API endpoint, it achieves cost-free model switching and automatically selects combinations with fast responses and low costs.</td>\n    </tr>\n    <tr>\n        <td><img src=\"./docs/xhai_browser/assets/logo_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"./docs/xhai_browser/README.md\">xhai Browser</a></td>\n        <td>xhai Browser is an Android desktop management & AI browser, DeepSeek is the default AI dialog engine.It has the ultimate performance (0.2 seconds to start), slim size (apk 3M), no ads, ultra-fast ad blocking, multi-screen classification, screen navigation, multi-search box, a box multiple search!</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://i.imgur.com/FkbmMVG.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://intellibar.app/\">IntelliBar</a></td>\n        <td>IntelliBar is a beautiful assistant for the Mac that lets you use advanced models like DeepSeek R1 with any app on your Mac — ex: edit emails in your mail app or summarize articles in your browser.</td>\n    </tr>\n    <tr>\n        <td><img src=\"./docs/gptbots/gptbots.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td><a href=\"https://www.gptbots.ai/docs\">GPTBots</a></td>\n        <td><a href=\"https://www.gptbots.ai/\">GPTBots</a> is a no-code AI agent building platform that integrates major international LLMs, including Deepseek. It offers modules for RAG-based knowledge storage/retrieval, tool customization/calling, and workflow orchestration. Additionally, it allows agents to be integrated into multiple mainstream platforms (such as WhatsApp, Telegram, etc.), providing end-to-end AI solutions for businesses and helping them stand out in the AI era.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/build/icon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/README.md\">DeepChat</a></td>\n        <td>DeepChat is a fully free desktop smart assistant, with a powerful DeepSeek large model, supporting multi-round conversations, internet search, file uploads, knowledge bases, and more.</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"https://avatars.githubusercontent.com/u/171659527?s=400&u=39906ab3b6e2066f83046096a66a77fb3f8bb836&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/quantalogic/quantalogic\">Quantalogic</a> </td>\n        <td> QuantaLogic is a ReAct (Reasoning & Action) framework for building advanced AI agents. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/224d547a-6fbc-47c8-859f-aa14813e2b0f\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatbox/README.md\">Chatbox</a> </td>\n        <td> Chatbox is a desktop client for multiple cutting-edge LLM models, available on Windows, Mac and Linux. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/bb65404c-f867-42d8-ae2b-281fe953ab54\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_next_web/README.md\"> ChatGPT-Next-Web </a> </td>\n        <td> ChatGPT Next Web is a cross-platform ChatGPT web UI, with GPT3, GPT4 & Gemini Pro support. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/Casibase/assets/casibase.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://casibase.org/docs/category/beginner-guide/\">Casibase</a></td>\n        <td> <a href=\"https://casibase.org\">Casibase</a> is an open source AI knowledge base and dialogue system that combines the latest RAG technology, SSO functionality, and support for a wide range of mainstream AI models. Casibase is designed to provide enterprises and developers with a powerful, flexible, and easy-to-use knowledge management and intelligent dialogue platform. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Coco AI/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Coco AI/README.md\">Coco AI</a></td>\n        <td> <a href=\"https://coco.rs\">Coco AI</a> is a fully open-source, cross-platform unified search and productivity tool that connects and searches across various data sources, including applications, files, Google Drive, Notion, Yuque, Hugo, and more, both local and cloud-based. By integrating with large models like DeepSeek, Coco AI enables intelligent personal knowledge management, emphasizing privacy and supporting private deployment, helping users quickly and intelligently access their information. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/liubai/assets/liubai-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/liubai/README.md\">Liubai</a> </td>\n        <td> Liubai allows DeepSeek to have arms and legs to manipulate your notes, tasks, calendars, and to-do lists just on WeChat! </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1ac9791b-87f7-41d9-9282-a70698344e1d\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/pal/README.md\"> Pal - AI Chat Client<br/>(iOS, ipadOS) </a> </td>\n        <td> Pal is a customized chat playground on iOS. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.librechat.ai/librechat.svg\" alt=\"LibreChat\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/deepseek\">LibreChat</a> </td>\n        <td> LibreChat is a customizable open-source app that seamlessly integrates DeepSeek for enhanced AI interactions. </td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/longevity-genie/chat-ui/11c6647c83f9d2de21180b552474ac5ffcf53980/static/geneticsgenie/icon-128x128.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/longevity-genie/just-chat\">Just-Chat</a> </td>\n        <td> Make your LLM agent and chat with it simple and fast!</td>\n     </tr>\n    <tr>\n        <td> <img src=\"https://www.papersgpt.com/images/logo/favicon.ico\" alt=\"PapersGPT\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/papersgpt/papersgpt-for-zotero\">PapersGPT</a> </td>\n        <td> PapersGPT is a Zotero plugin that seamlessly with DeepSeek and other multiple AI models for quickly reading papers in Zotero. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/rss-translator/RSS-Translator/main/core/static/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/rss_translator/README.md\"> RSS Translator </a> </td>\n        <td> Translate RSS feeds into your language! </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://relingo.net/assets/images/relingo-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://relingo.net\"> Relingo </a> </td>\n        <td> Build and master vocabulary while you browse website and watch youtube! </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/enconvo/README.md\"> Enconvo </a> </td>\n        <td> Enconvo is the Launcher of the AI era, the entry point for all AI functions, and a thoughtful intelligent assistant.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/kangfenmao/cherry-studio/blob/main/src/renderer/src/assets/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cherrystudio/README.md\">Cherry Studio</a></td>\n        <td>A powerful desktop AI assistant for producer</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://tomemo.top/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/tomemo/README.md\"> ToMemo (iOS, ipadOS) </a> </td>\n        <td> A phrasebook + clipboard history + keyboard iOS app with integrated AI macromodeling for quick output use in the keyboard.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/buxuku/video-subtitle-master/refs/heads/main/resources/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/buxuku/video-subtitle-master\">Video Subtitle Master</a></td>\n        <td> Batch generate subtitles for videos, with the ability to translate subtitles into other languages. This is a client-side tool that supports both Mac and Windows platforms and integrates with multiple translation services such as Baidu, Volcengine, DeepLx, OpenAI, DeepSeek, and Ollama.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/dist/assets/chatworm-72x72.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/README.md\">Chatworm</a> </td>\n        <td> Chatworm is a webapp for multiple cutting-edge LLM models, open-source and also available on Android. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/tisfeng/ImageBed/main/uPic/icon_512x512@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tisfeng/Easydict\">Easydict</a></td>\n        <td> Easydict is a concise and easy-to-use translation dictionary macOS App that allows you to easily and elegantly look up words or translate text. Supports calling large language model APIs for translation.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.raycast.com/favicon-production.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/raycast/README.md\">Raycast</a></td>\n        <td> <a href=\"https://raycast.com/?via=ViGeng\">Raycast</a> is a productivity tool for macOS that lets you control your tools with a few keystrokes. It supports various extensions including DeepSeek AI.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/chatpdflocal/assets/chatpdflocal-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatpdflocal.com\">ChatPDFLocal</a> </td>\n        <td> ChatPDFLocal is an AI powered Mac OS App for helping to chat PDF, it works seamlessly with DeepSeek and other multiple AI models to improve your reading efficiency. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://niceprompt.app/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td> <td> <a href=\"https://niceprompt.app\">Nice Prompt</a></td> <td> <a href=\"https://niceprompt.app\">Nice Prompt</a> Organize, share and use your prompts in your code editor, with Cursor and VSCode。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/193405629?s=200&v=4\" alt=\"PHP Client\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-php-client/blob/master/README.md\">PHP Client</a> </td>\n        <td> Deepseek PHP Client is a robust and community-driven PHP client library for seamless integration with the Deepseek API. </td>\n    </tr>\n        <tr>\n  <td>\n    <img\n      src=\"https://github.com/tornikegomareli/DeepSwiftSeek/blob/main/logo.webp\"\n      alt=\"DeepSwiftSeek Logo\"\n      width=\"64\"\n      height=\"auto\"\n    />\n  </td>\n  <td>\n    <a href=\"https://github.com/tornikegomareli/DeepSwiftSeek/blob/main/README.md\">DeepSwiftSeek</a>\n  </td>\n  <td>\n    DeepSwiftSeek is a lightweight yet powerful Swift client library, pretty good integration with the DeepSeek API.\n    It provides easy-to-use Swift concurrency for chat, streaming, FIM (Fill-in-the-Middle) completions, and more.\n  </td>\n</tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/958072?s=200&v=4\" alt=\"Laravel Integration\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-laravel/blob/master/README.md\">Laravel Integration</a> </td>\n        <td> Laravel wrapper for Deepseek PHP client, to seamless deepseek API integration with laravel applications.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/cohesion-org/deepseek-go/refs/heads/main/internal/images/deepseek-go.png\" alt=\"Go Client\" width=\"64\" height=\"auto\"> </td>\n        <td> <a href=\"https://github.com/cohesion-org/deepseek-go/blob/main/README.md\">Deepseek Go</a> </td>\n        <td>  A Deepseek client written for Go supporting Chat and Reasoning Models. Also supports external providers like Azure, OpenRouter and others. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/zotero/assets/zotero-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/zotero/README_cn.md\">Zotero</a></td>\n        <td> <a href=\"https://www.zotero.org\">Zotero</a> is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share research. It can use deepseek as translation service.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://b3log.org/images/brand/siyuan-128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/SiYuan/README.md\">SiYuan</a> </td>\n        <td> SiYuan is a privacy-first personal knowledge management system that supports complete offline usage, as well as end-to-end encrypted data sync.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/ArvinLovegood/go-stock/raw/master/build/appicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/ArvinLovegood/go-stock/blob/master/README.md\">go-stock</a> </td>\n        <td>go-stock is a Chinese stock data viewer built by Wails with NativeUI and powered by LLM.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/102771702?s=200&v=4\" alt=\"Wordware\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wordware/README.md\">Wordware</a> </td>\n        <td><a href=\"https://www.wordware.ai/\">Wordware</a> is a toolkit that enables anyone to build, iterate, and deploy their AI stack with just natural language.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/xRJ6vNo9mUYeVNxt0KITXCXEuSk.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/langgenius/dify/\">Dify</a> </td>\n        <td> <a href=\"https://dify.ai/\">Dify</a> is an LLM application development platform that supports DeepSeek models for creating assistants, workflows, text generators, and more. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/enricoros/big-AGI/refs/heads/v2-dev/public/favicon.ico\" alt=\"Big-AGI\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/enricoros/big-AGI/blob/v2-dev/README.md\">Big-AGI</a> </td>\n        <td><a href=\"https://big-agi.com/\">Big-AGI</a> is a groundbreaking AI suite designed to democratize access to advanced artificial intelligence for everyone.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/LiberSonora/LiberSonora/blob/main/assets/avatar.jpeg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/LiberSonora/LiberSonora/blob/main/README_en.md\">LiberSonora</a> </td>\n        <td> LiberSonora, meaning \"Voice of Freedom\", is an AI-powered, robust, open-source audiobook toolkit that includes features like intelligent subtitle extraction, AI title generation, multilingual translation, with support for GPU acceleration and batch offline processing.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ripperhe/Bob/master/docs/_media/icon_128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a></td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a> is a macOS translation & OCR tool ready to use in any app — right out of the box!</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://agenticflow.ai/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a> is a no-code platform where marketers build agentic AI workflows for go-to-market automation, powered by hundreds of everyday apps as tools for your AI agents.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://agentomat.com/static/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://agentomat.com/\">AGENTOMAT</a> </td>\n        <td> <a href=\"https://agentomat.com/\">AGENTOMAT</a> AI Agents for Everyone - the platform to create, share and monitor AI Agents.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/obot-platform/obot/refs/heads/main/docs/static/img/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/obot-platform/obot\">Obot</a> </td>\n        <td> Obot is an agent platform for building and deploying AI assistants with built-in RAG, workflow automation, and seamless integration with popular tools and services, powered by LLMs like DeepSeek. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/STranslate/STranslate/refs/heads/main/images/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a></td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a>（Windows） is a ready-to-go translation ocr tool developed by WPF </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://devinci.onicai.com/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://devinci.onicai.com/\">DeVinci</a></td>\n        <td> <a href=\"https://devinci.onicai.com/\">DeVinci</a> is the end-to-end decentralized AI chat app to privately chat with open-source LLMs.</td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/5e16beb0-993e-47bf-807e-7c8804b313a2\" alt=\"Asp Client\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Anwar-alhitar/Deepseek.Asp.Client/blob/master/README.md\">ASP Client</a> </td>\n        <td><a href=\"https://github.com/Anwar-alhitar/Deepseek.Asp.Client/blob/master/README.md\">Deepseek.ASPClient</a>  is a lightweight ASP.NET wrapper for the Deepseek AI API, designed to simplify AI-driven text processing in .NET applications.. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.gptaiflow.tech/logo.png\" alt=\"gpt-ai-flow-logo\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.gptaiflow.tech/docs/product/api-keys-setup#setup-deepseek-api-keys\">GPT AI Flow</a></td>\n        <td>\n            The ultimate productivity weapon built by engineers for efficiency enthusiasts (themselves): <a href=\"https://www.gptaiflow.tech/\">GPT AI Flow</a>\n            <ul>\n                <li>`Shift+Alt+Space` Wake up desktop intelligent hub</li>\n                <li>Local encrypted storage</li>\n                <li>Custom instruction engine</li>\n                <li>On-demand calling without subscription bundling</li>\n            </ul>\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/b09f17a8-936d-4dac-8b24-1682d52c9a3c\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/alecm20/story-flicks\">Story-Flicks</a></td>\n        <td>With just one sentence, you can quickly generate high-definition story short videos, supporting models such as DeepSeek.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://prompt.16x.engineer/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/16x_prompt/README.md\">16x Prompt</a> </td>\n        <td> <a href=\"https://prompt.16x.engineer/\">16x Prompt</a> is an AI coding tool with context management. It helps developers manage source code context and craft prompts for complex coding tasks on existing codebases.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/assets/favicon1.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/README.md\"> Alpha Pai </a> </td>\n        <td> AI Research Assistant / The Next-Generation Financial Information Portal Driven by AI.<br>Proxy for investors to attend meetings and take notes, as well as providing search and Q&A services for financial information and quantitative analysis for investment research.</td>\n    </tr>\n        <td> <img src=\"https://docs.xark-argo.com/img/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.xark-argo.com\">argo</a> </td>\n        <td>Locally download and run Ollama and Huggingface models with RAG on Mac/Windows/Linux. Support LLM API too.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.petercat.ai/images/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.petercat.ai\">PeterCat</a> </td>\n        <td> A conversational Q&A agent configuration system, self-hosted deployment solutions, and a convenient all-in-one application SDK, allowing you to create intelligent Q&A bots for your GitHub repositories.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/labring/FastGPT/refs/heads/main/.github/imgs/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fastgpt.cn/en\">FastGPT</a> </td>\n        <td>\n            FastGPT is an open-source AI knowledge base platform built on large language models (LLMs), supporting various models including DeepSeek and OpenAI. We provide out-of-the-box capabilities for data processing, model invocation, RAG retrieval, and visual AI workflow orchestration, enabling you to effortlessly build sophisticated AI applications.\n        </td>\n   </tr>\n   <tr>\n        <td> <img src=\"./docs/ruzhiai_note/assets/play_store_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/ruzhiai_note/README.md\">RuZhi AI Notes</a> </td>\n        <td>RuZhi AI Notes is an intelligent knowledge management tool powered by AI, providing one-stop knowledge management and application services including AI search & exploration, AI results to notes conversion, note management & organization, knowledge presentation & sharing. Integrated with DeepSeek model to provide more stable and higher quality outputs.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cdn.link-ai.tech/doc/CoW%20logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zhayujie/chatgpt-on-wechat\">Chatgpt-on-Wechat</a> </td>\n        <td> Chatgpt-on-Wechat(CoW) is a flexible chatbot framework that supports seamless integration of multiple LLMs, including DeepSeek, OpenAI, Claude, Qwen, and others, into commonly used platforms or office software such as WeChat Official Accounts, WeCom, Feishu, DingTalk, and websites. It also supports a wide range of custom plugins. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://athenalab.ai/assets/favicon/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://athenalab.ai/\">Athena</a> </td>\n        <td>The world's first autonomous general AI with advanced cognitive architecture and human-like reasoning capabilities, designed to tackle complex real-world challenges.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://maxkb.cn/images/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/1Panel-dev/MaxKB\">MaxKB</a> </td>\n        <td> <a href=\"https://maxkb.cn/\">MaxKB</a> is a ready-to-use, flexible RAG Chatbot. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/TigerGPT/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ttm.financial/gpt\">TigerGPT</a> </td>\n        <td>TigerGPT is the first financial AI investment assistant of its kind based on OpenAI, developed by Tiger Group. TigerGPT aims to provide intelligent investment decision-making support for investors. On February 18, 2025, TigerGPT officially integrated the DeepSeek-R1 model to provide users with online Q&A services that support deep reasoning. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/HIX.AI/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://hix.ai\">HIX.AI</a> </td>\n        <td>Try DeepSeek for free and enjoy unlimited AI chat on HIX.AI. Use DeepSeek R1 for AI chat, writing, coding & more. Experience next-gen AI chat now!</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/sharmt1411/askanywhere/blob/main/icon/Depth_8,_Frame_0explore-%E8%A7%92%E6%A0%87.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sharmt1411/askanywhere\">Askanywhere</a> </td>\n        <td>Select text anywhere and start a conversation with Deepseek</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/OJZen/1chat/raw/refs/heads/main/doc/assets/icon.ico?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/OJZen/1chat\">1chat</a> </td>\n        <td>An iOS app that lets you chat with the DeepSeek-R1 model locally.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://chatlabsai.com/assets/logo/logo.png\" alt=\"iOS AI Chatbot\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chatlabsai.com\">Access 250+ text, image LLMs in one app</a> </td>\n        <td> 1AI iOS Chatbot integrates with 250+ text, image, voice models allowing users chat with any model in the world including Deepseek R1 and Deepseek V3 models.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/PopAi/assets/logo.svg\" alt=\"PopAi\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://popai.pro\">PopAi</a> </td>\n        <td>PopAi launches DeepSeek R1!  Enjoy lag-free, lightning-fast performance with PopAi. Seamlessly toggle online search on/off.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pot-app.com/logo/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a></td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a> 🌈 A cross-platform software for text translation and recognition. </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Byaidu/PDFMathTranslate/raw/main/docs/images/banner.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Byaidu/PDFMathTranslate\">PDFMathTranslate</a></td>\n        <td>PDF Math Translate is an AI-based full-text bilingual translation tool that fully preserves the layout of PDF documents.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Richasy/Bili.Copilot/raw/master/assets/StoreLogo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Richasy/Bili.Copilot\">Bili.Copilot</a></td>\n        <td>Bilibili third-party Windows desktop client, a native application built with the Windows App SDK.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://www.tensorbounce.com/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.tensorbounce.com/\">LawAgent</a></td>\n        <td>LawAgent is a legal AI product developed by the Tensorbounce team, integrating a knowledge base with AI Agent capabilities. It boasts a vast repository of tens of millions of official legal-related data points and also allows for custom knowledge base configurations. The professional mode leverages the reasoning abilities of DeepSeek-R1 to assist users in legal analysis, contract review, document generation, file translation, and other legal scenarios.</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/AlphaBot/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://alphabot.x-pai.com/\">AlphaBot</a> </td>\n        <td> AlphaBot is an intelligent stock analysis assistant that integrates multi-source data with AI analysis technology to provide technical analysis, predictions, and risk assessment, helping investors make data-driven trading decisions. It supports one-click deployment, easy operation，Support Windows/Linux/MacOS and other platforms</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://h1.appinn.me/file/1741929316827_21.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/jiqi136/DS-AI\">Real-time Web-Access AI Assistant</a></td>\n        <td>The AI assistant supports direct API access to the strongest Claude Code model via the DeepSeek-V3.1 interface, enabling usage without network relay (costs slashed by 90%). It supports image and PDF file parsing with free image generation capabilities, allows custom integration of other AI models, and enables real-time web searches by connecting to local browsers for vast online content retrieval. Alternatively, free models online content retrieval. Alternatively, free models like R1 are also available.\n</td>\n    </tr>\n    <tr>\n    <td><img src=\"docs/remio/assets/remio_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n    <td><a href=\"https://www.remio.ai/\">remio</a></td>\n    <td>remio is an AI-powered personal knowledge hub that builds personalized knowledge bases by automatically capturing browsed web content, parsing local files, and integrating personal notes. It enables search and natural language Q&A within your personal knowledge base for instant insights while offering smart writing assistance—adapting to your style to streamline drafting, refining, and completing content with ease. Designed with local-first storage, remio prioritizes data privacy while centralizing fragmented information for maximum productivity.</td>\n    </tr> \n    <tr>\n    <td><img src=\"docs/DocKit/assets/dockit.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n    <td><a href=\"https://dockit.geekfun.club/\">DocKit</a></td>\n    <td>DocKit is an AI powered desktop GUI client designed for NoSQL database, support Elasticsearch and OpenSearch across Mac, windows and Linux. By integrating with large models like DeepSeek, DocKit can help developers to write complex DSL queries, and provide a better experience for data management and analysis. </td>\n    </tr> \n    <tr>\n        <td> <img src=\"docs/zenfeed/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/glidea/zenfeed\">zenfeed</a> </td>\n        <td> Empower RSS with AI, automatically filter, summarize, and push important information to overcome information overload. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/NoteGen/NoteGen.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/codexu/note-gen\">NoteGen</a> </td>\n        <td> NoteGen is a cross-platform Markdown note-taking application dedicated to using AI to bridge recording and writing, organizing fragmented knowledge into a readable note. </td>\n    </tr>\n    <tr>\n        <td> </td>\n        <td> <a href=\"https://github.com/SamYuan1990/i18n-agent-action\">i18n-agent-action</a> </td>\n        <td> The i18n Agent is an AI-powered tool designed to streamline and automate internationalization (i18n) and localization (l10n) workflows. By leveraging advanced natural language processing (NLP) and machine learning, it helps developers, translators, and product teams efficiently manage multilingual content—eliminating manual errors and accelerating global deployments. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://mindpal.space/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://mindpal.io\">MindPal</a> </td>\n        <td> <a href=\"https://mindpal.io\">MindPal</a> is a platform to build AI Agents and Multi-agent Systems to automate any business processes </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://3min.top/imgs/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://3min.top/en\">3mintop</a> </td>\n        <td> A powerful AI-powered tool that helps you quickly summarize and understand any content in just 3 minutes, supporting DeepSeek models for enhanced comprehension. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://5ire.app/favicon.ico\" alt=\"5ire-logo\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/nanbingxyz/5ire\">5ire</a> </td>\n        <td> <a href=\"https://github.com/nanbingxyz/5ire\">5ire</a> is a user-friendly, cross-platform open-source desktop AI assistant, compatible with mainstream LLMs, supporting MCP Servers, local RAG, prompt libraries, and various practical functions.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://prompt.16x.engineer/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/16x_prompt/README.md\">16x Prompt</a> </td>\n        <td> <a href=\"https://prompt.16x.engineer/\">16x Prompt</a> is an AI coding tool with context management. It helps developers manage source code context and craft prompts for complex coding tasks on existing codebases.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cantian.ai/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://cantian.ai/\">Cantian AI</a></td>\n        <td>An exclusive AI-native Bazi fortune-telling service with a deep, structured knowledge base of traditional eastern culture.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://obsidian.md/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/TarsLab/obsidian-tars\">Obsidian Tars</a></td>\n        <td> Integrate LLM conversations into Obsidian's note editing, with deepseek-reasoner's CoT output in callout format. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.chatbotbuilder.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bobbylkchao/chatbotBuilder\">AI Chatbot Builder</a> </td>\n        <td> <a href=\"www.chatbotbuilder.dev/\">Chatbot Builder</a> is an open-source chatbot platform powered by DeepSeek and OpenAI, enabling intelligent conversations across various scenarios.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://bibigpt.co/icons/lucid/icon_32x32@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"http://bibigpt.co\">BibiGPT</a> </td>\n        <td> <a href=\"http://bibigpt.co\">BibiGPT</a> is an AI audio/video assistant that supports content analysis and summarization from major platforms like Bilibili, YouTube, Xiaohongshu, and podcast platforms, making audio/video content faster to consume, easier to find, and better to use. Features include content summarization, interactive Q&A, and article generation. Supports video file uploads, note-taking app integration, and DeepSeek R1 and V3 models. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lobehub.com/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://lobehub.com/docs/usage/providers/deepseek\">LobeChat</a> </td>\n        <td> <a href=\"https://lobehub.com\">LobeChat</a> - an open-source, modern-design AI chat framework. Supports DeepSeek R1, Knowledge Base (file upload / knowledge management / RAG ), Multi-Modals (Vision/TTS/Plugins/Artifacts). One-click FREE deployment of your private DeepSeek application </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/ruzhiai_note/assets/play_store_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/ruzhiai_note/README.md\">RuZhi AI Notes</a> </td>\n        <td>RuZhi AI Notes is an intelligent knowledge management tool powered by AI, providing one-stop knowledge management and application services including AI search & exploration, AI results to notes conversion, note management & organization, knowledge presentation & sharing. Integrated with DeepSeek model to provide more stable and higher quality outputs.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cdn.link-ai.tech/doc/CoW%20logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zhayujie/chatgpt-on-wechat\">Chatgpt-on-Wechat</a> </td>\n        <td> Chatgpt-on-Wechat(CoW) is a flexible chatbot framework that supports seamless integration of multiple LLMs, including DeepSeek, OpenAI, Claude, Qwen, and others, into commonly used platforms or office software such as WeChat Official Accounts, WeCom, Feishu, DingTalk, and websites. It also supports a wide range of custom plugins. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.weiyuai.cn/logo.png\" alt=\"AI Customer Service\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Bytedesk/bytedesk\">Bytedesk</a> </td>\n        <td> Enterprise IM Solution with AI powered live chat, email support, omni-channel customer service & team im，alternative to slack + zendesk/intercom.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://raw.githubusercontent.com/rockbenben/subtitle-translator/main/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/rockbenben/subtitle-translator\">Subtitle Translator</a></td>\n        <td>A batch subtitle translator supporting SRT/ASS/VTT/LRC formats, compatible with DeepSeek and various other LLMs and machine translation interfaces.</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/turtlenoir/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://turtlenoir.com/\"> Turtle Noir </a> </td>\n        <td> <a href=\"https://turtlenoir.com/\"> Turtle Noir </a> An AI-hosted lateral thinking puzzle game (Situation Puzzles / \"Turtle Soup\") powered by DeepSeek, supporting both single-player and multiplayer modes. The AI moderator manages the game flow and provides witty commentary, guiding the deduction process through standard \"Yes / No / Irrelevant\" Q&A. Features include an immersive gameplay mode, smart hints, puzzle deduplication, and content moderation. Perfect for casual brain training and online social gaming. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/songquanpeng/one-api/main/web/default/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/songquanpeng/one-api\">One API</a> </td>\n        <td> One API is a LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"agent\">AI Agent frameworks</span>\n\n<table>\n    <tr>\n        <td width=80> <img src=\"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolagents/mascot_smol.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/huggingface/smolagents/tree/main\"> smolagents </a> </td>\n        <td> The simplest way to build great agents. Agents write python code to call tools and orchestrate other agents. Priority support for open models like DeepSeek-R1!  </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/user-attachments/assets/865634cb-1383-4317-a895-dfcb15f11375\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/yomo/README.md\">YoMo</a></td>\n        <td>Stateful Serverless LLM Function Calling Framework with Strongly-typed Language Support</td>\n     </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/182288589?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/DMontgomery40/deepseek-mcp-server/blob/main/README.md\">DeepSeek MCP Server</a> </td>\n        <td> Model Context Protocol server for DeepSeek's advanced language models.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/superagentxai/superagentX/refs/heads/master/docs/logo/icononly_transparent_nobuffer.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/superagentx/README.md\">SuperAgentX</a> </td>\n        <td>SuperAgentX: A Lightweight Open Source AI Framework Built for Autonomous Multi-Agent Applications with Artificial General Intelligence (AGI) Capabilities.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://panda.fans/_assets/favicons/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/anda/README.md\">Anda</a> </td>\n        <td>A Rust framework for AI agent development, designed to build a highly composable, autonomous, and perpetually memorizing network of AI agents.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.dreams.fun/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/daydreamsai/daydreams\">Daydreams</a> </td>\n        <td>Daydreams is a generative crosschain agent framework for executing anything onchain. Autonomous and easy to build on enabling the next generation of agents.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://rig.rs/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" alt=\"Rig (Rust)\" /> </td>\n        <td> <a href=\"https://rig.rs\">RIG</a> </td>\n        <td>Build modular and scalable LLM Applications in Rust.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/longevity-genie/chat-ui/11c6647c83f9d2de21180b552474ac5ffcf53980/static/geneticsgenie/icon-128x128.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/longevity-genie/just-agents\">Just-Agents</a> </td>\n        <td>A lightweight, straightforward library for LLM agents - no over-engineering, just simplicity!</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://alice.fun/alice-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bob-robert-ai/bob/blob/main/alice/readme.md\">Alice</a> </td>\n        <td>An autonomous AI agent on ICP, leveraging LLMs like DeepSeek for on-chain decision-making. Alice combines real-time data analysis with a playful personality to manage tokens, mine BOB, and govern ecosystems.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Upsonic/Upsonic/blob/9d2e6d43b44defc6744817330625661ca3a2184e/Upsonic%20pp.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Upsonic/Upsonic\">Upsonic</a> </td>\n        <td>Upsonic offers a cutting-edge enterprise-ready agent framework where you can orchestrate LLM calls, agents, and computer use to complete tasks cost-effectively.</td>\n    </tr>\n\n<tr>\n        <td> <img src=\"https://github.com/guyoung/AIMatrices/raw/main/docs/assets/logo/ai-matrices1.png\" alt=\"AIMatrices 图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/guyoung/AIMatrices/blob/main/README.md\">AIMatrices</a> </td>\n        <td>AIMatrices is a lightweight, high-performance, scalable, and open source AI application rapid building platform designed to provide developers with an efficient and convenient AI application development experience. It integrates multiple advanced technologies and tools to help users quickly build, deploy, and maintain AI applications without having to write complex code from scratch.</td>\n    </tr>\n</table>\n\n### RAG frameworks\n\n<table>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/173022229\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/APRO-com\">ATTPs</a> </td>\n        <td>A foundational protocol framework for trusted communication between agents. Any agents based on DeepSeek, By integrating with the <a href=\"https://docs.apro.com/attps\">ATTPs</a> SDK, can access features such as agent registration, sending verifiable data, and retrieving verifiable data. So that it can make trusted communication with agents from other platforms. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/translate.js/assets/icon.png\" alt=\"图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/translate.js/README.md\">translate.js</a> </td>\n        <td> AI i18n for front-end developers. It can achieve fully automatic HTML translation with just two lines of JavaScript. You can switch among dozens of languages with a single click. There is no need to modify the page, no language configuration files are required, and it supports dozens of fine-tuning extension instructions. It is SEO-friendly. Moreover, it opens up a standard text translation API interface.  </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/agentUniverse/assets/agentUniverse_logo_s.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/antgroup/agentUniverse\"> agentUniverse </a> </td>\n        <td> agentUniverse is a multi-agent collaboration framework designed for complex business scenarios. It offers rapid and user-friendly development capabilities for LLM agent applications, with a focus on mechanisms such as agent collaborative scheduling, autonomous decision-making, and dynamic feedback. The framework originates from Ant Group's real-world business practices in the financial industry. In June 2024, agentUniverse achieved full integration support for the DeepSeek series of models.  </td>\n    </tr>\n        <tr>\n            <td width=80> <img src=\"docs/BotSharp/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n            <td> <a href=\"https://github.com/SciSharp/BotSharp\"> BotSharp </a> </td>\n            <td> BotSharp is an open-source multi-agent application development framework. From simple chatbots to multi-agent collaboration and complex tasks like the Text To SQL framework, it provides out-of-the-box solutions to quickly integrate large model capabilities into existing business systems. It also includes built-in knowledge base and session management features. The framework has been thoroughly tested with DeepSeek V3 models, and thanks to the performance of DeepSeek V3, the framework's performance is on par with other proprietary models. </td>\n        </tr>\n           <tr>\n            <td width=80> <img src=\"docs/eino/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n            <td> <a href=\"https://github.com/cloudwego/eino\"> Eino </a> </td>\n            <td> Eino (pronounced like \"I know\") aims to be the best LLM application development framework in the Go language. It draws on the design concept of excellent LLM frameworks in open source communities such as LangChain and LlamaIndex, while absorbing cutting-edge research results and practical application experience, providing a LLM application development framework that is more in line with Go programming conventions, emphasizing simplicity, scalability, reliability and efficiency. </td>\n        </tr>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"https://raw.githubusercontent.com/Tencent/Youtu-agent/924aeeb6c49ee524b8bb4de2642a3dc84b7b86b9/docs/assets/mascot.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> is a flexible, high-performance framework for building, running, and evaluating autonomous agents. Beyond topping the benchmarks, this framework delivers powerful agent capabilities, e.g. data analysis, file processing, and deep research, all with open-source models. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"data\">Data AI Applications frameworks</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/user-attachments/assets/a327d72f-755f-4256-8a37-32a518a55df3\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td width=\"120\"> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/dbgpt/README.md\"> DB-GPT </a> </td>\n        <td> 🤖 DB-GPT is an open source AI native data app development framework with AWEL(Agentic Workflow Expression Language) and agents.\nThe purpose is to build infrastructure in the field of large models, through the development of multiple technical capabilities such as multi-model management (SMMF), Text2SQL effect optimization, RAG framework and optimization, Multi-Agents framework collaboration, AWEL (agent workflow orchestration), etc. Which makes large model applications with data simpler and more convenient.\n\n </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"rag\">RAG frameworks</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/ragflow/README.md\"> RAGFlow </a> </td>\n        <td> An open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data. </td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/pingcap/autoflow/refs/heads/main/docs/public/icon-dark.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/autoflow/README.md\"> Autoflow </a> </td>\n        <td> <a href=\"https://github.com/pingcap/autoflow\">AutoFlow</a> is an open-source knowledge base tool based on GraphRAG (Graph-based Retrieval-Augmented Generation), built on <a href=\"https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community\">TiDB</a> Vector, LlamaIndex, and DSPy. It provides a Perplexity-like search interface and allows easy integration of AutoFlow's conversational search window into your website by embedding a simple JavaScript snippet. </td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://assets.zilliz.com/Zilliz_Logo_Mark_White_20230223_041013_86057436cc.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zilliztech/deep-searcher\"> DeepSearcher </a> </td>\n        <td> DeepSearcher combines powerful LLMs (DeepSeek, OpenAI, etc.) and Vector Databases (Milvus, etc.) to perform search, evaluation, and reasoning based on private data, providing highly accurate answer and comprehensive report.  </td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/OpenSPG/openspg/089188f3e7b0392221f5a8e8f1a3629b6352a6f9/LOGO.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/OpenSPG/KAG/blob/master/README.md\"> KAG </a> </td>\n        <td> KAG is a logical reasoning and Q&A framework based on the <a href=\"https://github.com/OpenSPG/openspg\">OpenSPG</a> engine and large language models, which is used to build logical reasoning and Q&A solutions for vertical domain knowledge bases. KAG can effectively overcome the ambiguity of traditional RAG vector similarity calculation and the noise problem of GraphRAG introduced by OpenIE. KAG supports logical reasoning and multi-hop fact Q&A, etc.</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/TencentCloudADP/youtu-graphrag/refs/heads/main/assets/logo.png\" alt=\"Youtu-GraphRAG icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/TencentCloudADP/Youtu-GraphRAG\"> Youtu-GraphRAG </a> </td>\n        <td>Youtu-GraphRAG proposes a new graph retrieval-augmented generation paradigm which vertically unifies graph construction, indexing and retrieval through schema. It advances GraphRAG towards enterprise-level applications, allowing seamless cross-domain adaptation with minimum human intervention, with (i) a dynamic schema-bounded extraction; (ii) a comprehensive community detection algorithm and (iii) a schema-guided query decomposition for iterative reflection and reasoning.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"fhe\">FHE (Fully Homomorphic Encryption) frameworks</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/fhe.mind-network/mind-network-log.png\" alt=\"Icon\" width=\"200\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\"> Mind FHE Rust SDK </a> </td>\n        <td> <p>An open-source SDK for encrypting AI with Fully Homomorphic Encryption (FHE) and integrating with Mind Network for agent consensus. FHE is considered the <b>holy grail of cryptography</b>, enabling computations directly on encrypted data without the need for decryption. With FHE, agents can safeguard their privacy while using Deepseek, ensuring both model integrity and result consensus -<b> all without exposing their data </b>- by connecting to Mind Network. The SDK <a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\"> source code </a> is implemented in pure <b>Rust</b>> and the package also available on <a href=\"https://crates.io/crates/mind_sdk_deepseek\"> crates.io </a>. </p> </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"solana\">Solana frameworks</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/solana-agent-kit/assets/sendai-logo.png\" alt=\"Icon\" width=\"128\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sendaifun/solana-agent-kit\"> Solana Agent Kit </a> </td>\n        <td>An open-source toolkit for connecting AI agents to Solana protocols. Now, any agent, using any Deepseek LLM, can autonomously perform 60+ Solana actions: </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"sythetic\">Synthetic data curation</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/bespokelabsai/curator/main/docs/Bespoke-Labs-Logomark-Red-crop.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/curator/README.md\"> Curator </a> </td>\n        <td> An open-source tool to curate large scale datasets for post-training LLMs. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/8455694b-c52e-40ec-847e-adf6a5ac064f\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Kiln-AI/Kiln\"> Kiln </a> </td>\n        <td>Generate synthetic datasets and distill R1 models into custom fine-tunes. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/192579850?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/DataEval/dingo\"> Dingo </a> </td>\n        <td>Dingo: A Comprehensive Data Quality Evaluation Tool. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"im\">IM Application Plugins</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/huixiangdou.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/huixiangdou/README_cn.md\">HuixiangDou<br/>(wechat,lark)</a> </td>\n        <td>Domain knowledge assistant in personal WeChat and Feishu, focusing on answering questions.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/RockChinQ/LangBot/blob/master/res/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/RockChinQ/LangBot\">LangBot<br/>（QQ, Lark, WeCom）</a> </td>\n        <td> LLM-based IM bots framework, supports QQ, Lark, WeCom, and more platforms.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://nonebot.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/KomoriDev/nonebot-plugin-deepseek\">NoneBot<br/>（QQ, Lark, Discord, TG, etc.）</a> </td>\n        <td> Based on NoneBot framework, provide intelligent chat and deep thinking functions, supports QQ, Lark, Discord, TG, and more platforms.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/197911947?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/AstrBotDevs/AstrBot/\">AstrBot<br/>（QQ, WeChat, WeCom, Lark, TG, etc.）</a> </td>\n        <td> User-friendly LLM-based multi-platform chatbot with a WebUI, supporting long-term-memory, RAG, LLM agents, and plugins integration.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://oss.nekro.ai/nekro_agent_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/KroMiose/nekro-agent\">NekroAgent<br/>(QQ, Discord, BiliBiliLive, Minecraft etc.)</a> </td>\n        <td> Nekro Agent is a smart and elegant AI agent execution framework. At its core, it leverages a powerful and flexible prompt engineering system to guide AI in generating code and executing it within a secure sandbox. It delivers robust cross-platform event stream processing through a native multi-platform adapter architecture, seamlessly supporting major platforms like OneBot v11 (QQ), Discord, Minecraft, and Bilibili Live (powering V-Tuber performances). The project also boasts a highly extensible plugin system, a shared ecosystem for personas and plugins, and supports efficient interactions in complex, multi-user group chats. Its goal is to offer both users and developers a developer-friendly intelligent hub that is extremely efficient, highly flexible, and easy to use. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.lanyingim.com/img/header/dock_lanying.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.lanyingim.com\">蓝莺IM<br/></a> </td>\n        <td> <b>AI Chatbot SDK with IM cloud service</b>, <br/> Cross-platform (iOS, Android, Web, PC, Linux) <a href=\"https://github.com/maxim-top/maxim-bistro\">chat SDK</a> and AI Agent platform. <br/> Easily integrates into apps, and supports WeChat and official accounts. <br/> Native DeepSeek support, no API-Key needed.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"office\">Office Addin</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://www.44886.com/view/img/bukeng.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.bukenghezi.com/\">BKOffice</a> </td>\n        <td>An Office plugin that supports the Word, Excel, and PPT suite (also supports the WPS suite), adding more than 300 functions to Office.</td>\n    </tr>\n      <tr>\n        <td> <img src=\"https://www.aippt.cn/_nuxt/logo_cn.eYEokZzA.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.aippt.cn/\">AiPPT</a> </td>\n        <td>AiPPT.com，chosen by over 20 million users，One sentence, one minute, one click to generate PPT。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/office-sec/OfficeAI/blob/main/logo/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/office-sec/OfficeAI\">OfficeAI Assistant</a> </td>\n        <td>OfficeAI Assistant is a free office plugin that provides functions such as AI Q&A, AI proofreading, AI typesetting, AI creation, and AI data processing within Office. It can improve office efficiency and is compatible with both Microsoft Office and WPS Office.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"browser\">Browser Extensions</span>\n\n<table>\n    <tr>\n        <td><img src=\"./docs/SelectTranslate/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://selecttranslate.com/\">SelectTranslate</a></td>\n        <td>A free and open AI translation extension, with innovative and practical translation functions such as bilingual webpage translation, AI-selected translation (copy translation), input translation, and PDF translation.\n        </td>\n    </tr>\n    <tr>\n        <td><img src=\"./docs/deepshare/assets/logo_200.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"./docs/deepshare/README.md\">Tiny AI Bee</a></td>\n        <td> Tiny AI Bee is a free login-free one-click grease monkey plugin for sharing AI chats,\n            Specialized in solving the problem of sending thousands of words of AI Q&A to friends, causing their phones to be brushed, or long screenshots to be compressed and opened blurred, not easy to read.\n            Satisfy users' need to share their crystallized wisdom with AI to others\n        </td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/OpenXLab/migo/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://chromewebstore.google.com/detail/cjapgnecnkblehipjghhegiccobeloka?utm_source=item-share-cb\">Migo</a></td>\n        <td> Migo offers comprehensive text processing, information search, and knowledge Q&A functions, adapting to various online work and research scenarios (such as Feishu, arXiv, Overleaf, etc.).</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9d3f42b8-fcd0-47ab-8b06-1dd0554dd80e\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_translate/README.md\"> Immersive Translate </a> </td>\n        <td> Immersive Translate is a bilingual webpage translation plugin. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lh3.googleusercontent.com/K9i0qJb8phasC5wWf5tU68rhnfvX4swsE0hrhJP-WB3WV7MwE5KpMUIJvHKNHHRE6GKNIvIdTNSWoDMl_NggrmUsaw=s120\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_reading_guide/README.md\"> Immersive Reading Guide </a> </td>\n        <td> NO Sidebar!!! Immersive AI web summarization, ask questions... </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/8a301619-a3de-489b-81fd-69aaa7c1c561\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_box/README.md\"> ChatGPT Box </a> </td>\n        <td> ChatGPT Box is a ChatGPT integration in browser, completely for free. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c3d9d100-247a-41cc-97c1-10b01ed25e70\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/hcfy/README.md\"> hcfy (划词翻译) </a> </td>\n        <td> hcfy (划词翻译) is a web browser extension to integrate multiple translation services. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.eudic.net/web/trans/en_trans.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Lulu Translate/README.md\"> Lulu Translate </a> </td>\n        <td> The plugin provides mouse selection translation, paragraph-by-paragraph comparison translation, and PDF document translation functionalities. It can utilize various translation engines, such as DeepSeek AI, Bing, GPT, Google, etc. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Bistutu/FluentRead/blob/main/public/icon/128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fluent.thinkstu.com/\"> FluentRead </a> </td>\n        <td> A revolutionary open-source browser translation plugin that enables everyone to have a native-like reading experience </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.ncurator.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.ncurator.com/\"> Ncurator </a> </td>\n        <td> Knowledge Base AI Q&A Assistant - Let AI help you organize and analyze knowledge</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/oinzen/RSSFlow-doc/blob/main/docs/images/en/icon64.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://rssflow.oinchain.com\"> RssFlow </a> </td>\n        <td>An intelligent RSS reader browser extension with AI-powered RSS summarization and multi-dimensional feed views. Supports DeepSeek model configuration for enhanced content understanding. </td>\n    </tr>\n    <tr>\n<td> <img src=\"./docs/refinereader/assets/refinereader-128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://refinereader.cuihuaer.com\"> Refine Reader </a> </td>\n        <td> A Chrome extension that uses AI (DeepSeek, OpenAI, etc.) to help you quickly understand and summarize articles. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Hedwi/deepchat/refs/heads/main/images/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chromewebstore.google.com/detail/deepchat-power-of-deepsee/femhcibnncinlabdboehojdhfcihpkpl?hl=en\"> DeepChat </a> </td>\n        <td>A Chrome extension that enables users to chat with DeepSeek by opening a sidebar on any website. In addition, it provides a floating menu underneath any selected text on any website that allows users to generate text summaries, check grammar issues, and translate content.</td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://www.typral.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.typral.com/\"> Typral </a> </td>\n        <td> Fast AI writer assistant - Let AI help you quickly improve article, paper, text...</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.trancy.org/assets/trancy_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.trancy.org/\"> Trancy </a> </td>\n        <td>Immersive bilingual translation, video bilingual subtitles, sentence/word selection translation extension</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://ziziyi.com/svg/anything_copilot.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/baotlake/anything-copilot\"> Anything Copilot </a> </td>\n        <td> Anything Copilot is a browser extension that enables seamless access to mainstream AI tools directly from your sidebar. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cliprun.com/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://cliprun.com/\"> Cliprun </a> </td>\n        <td> Python code runner & playground. Right-click Python code on DeepSeek to run it instantly in your browser. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"http://cdn.docky.ai/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/docky-ai/README.md\"> Docky AI </a> </td>\n        <td>Docky AI is a powerful browser extension that allows you to have real-time conversations with multiple AI models through a sidebar. It supports simultaneous communication with multiple models and can assist you in reading web pages, writing, translating, and creating images</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://readfrog.mengxi.work/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://readfrog.mengxi.work\"> 🐸 Read Frog </a> </td>\n        <td> Translate and understand any webpage in depth with AI assistance. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://chathub.gg/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chathub.gg\"> ChatHub </a> </td>\n        <td> All-in-one AI client </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Rearview/assets/favicon.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"./docs/Rearview/README.md\"> RearView </a> </td>\n        <td>Rearview is a browser history management extension that supports full-text search of historical browsing content and converts browsing history into a conversationable knowledge base.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.chatgot.io/chat/assets/imgs/logo@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatgot.io/\"> ChatGOT </a> </td>\n        <td> A free AI chatbot assistant for enhancing productivity </td>\n    </tr>\n</table>\n\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"vscode\">VS Code Extensions</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://mintlify.s3.us-west-1.amazonaws.com/continue-docs/logo/light.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continue is an open-source autopilot in IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/assets/favicon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/README.md\"> Cline </a> </td>\n        <td> Meet Cline, an AI assistant that can use your CLI aNd Editor. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Sitoi/ai-commit/refs/heads/main/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Sitoi/ai-commit/blob/main/README.md\"> AI Commit </a> </td>\n        <td> Use AI to generate git commit messages in VS Code. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/titusTong/seekCodeCopilot/blob/main/assets/SeekCodeCopilotLogo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/titusTong/seekCodeCopilot/blob/main/README.md\"> SeekCode Copilot </a> </td>\n        <td> vscode intelligent coding assistant supports configuring locally deployed DeepSeek models </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/intellism/vscode-comment-translate/blob/master/doc/image/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/intellism/vscode-comment-translate/blob/master/README.md\"> Comment Translation </a> </td>\n        <td> This extension helps developers translate comments, strings, code hints, error messages, and variable names in their code. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/AITK/assets/AIToolkit.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://code.visualstudio.com/docs/intelligentapps/overview\"> AI Toolkit </a> </td>\n        <td> AI Toolkit for Visual Studio Code is a comprehensive extension that empowers developers and AI engineers to build, test, and deploy intelligent applications using generative AI models. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/joygqz/commit-genie/refs/heads/main/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=joygqz.commit-genie\"> Commit Genie </a> </td>\n        <td> AI-powered code review and commit message generator for VS Code. Automatically reviews your code changes and generates meaningful, standard commit messages. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/JohnnyZ93/oai-compatible-copilot/blob/main/assets/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/oai-compatible-copilot/README.md\"> OAI Compatible Provider for Copilot </a> </td>\n        <td> An open-source VS Code extension to use openai compatible inference providers in GitHub Copilot. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://littlecareless.gallerycdn.vsassets.io/extensions/littlecareless/dish-ai-commit/0.56.1/1766035023782/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/littleCareless/dish-ai-commit\"> Dish AI Commit </a> </td>\n        <td> An AI-powered VS Code extension that automatically generates standardized Git/SVN commit messages, PR summaries, and weekly reports using DeepSeek and other AI providers. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"vs\">Visual Studio Extensions</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/comment2gpt/2.0.5/1739475434185/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.Comment2GPT\"> Comment2GPT </a> </td>\n        <td> Use OpenAI ChatGPT, Google Gemini, Anthropic Claude, DeepSeek and Ollama through your comments </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/codelens2gpt/2.0.5/1739475875714/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.CodeLens2GPT\"> CodeLens2GPT </a> </td>\n        <td> Use OpenAI ChatGPT, Google Gemini, Anthropic Claude, DeepSeek and Ollama through the CodeLens </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/uca-lite/1.4.2/1739392928984/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.UCA-Lite\"> Unity Code Assist Lite </a> </td>\n        <td> Code assistance for Unity scripts </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"neovim\">neovim Extensions</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/c316f70a-0a3c-4a32-b148-4df15e609acc\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/avante.nvim/README.md\"> avante.nvim </a> </td>\n        <td> avante.nvim is an open-source autopilot in IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/llm.nvim/README.md\"> llm.nvim </a> </td>\n        <td> A free large language model (LLM) plugin that allows you to interact with LLM in Neovim. Supports any LLM, such as Deepseek, GPT, GLM, Kimi or local LLMs (such as ollama). </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/codecompanion.nvim/README.md\"> codecompanion.nvim </a> </td>\n        <td> AI-powered coding, seamlessly in Neovim. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/minuet-ai.nvim/README.md\"> minuet-ai.nvim </a> </td>\n        <td> Minuet offers code completion as-you-type from popular LLMs including Deepseek, OpenAI, Gemini, Claude, Ollama, Codestral, and more. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"jetbrains\">JetBrains Extensions</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://ide.unitmesh.cc/img/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ide.unitmesh.cc/quick-start\"> AutoDev </a> </td>\n        <td>‍AutoDev is an open-source AI coding assistant in JetBrain's IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/84a0175f-39a6-41b0-83e5-2ea15a4ac771\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/21410-onegai-copilot\"> Onegai Copilot </a> </td>\n        <td>Onegai Copilot is an AI coding assistant in JetBrain's IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://mintlify.s3.us-west-1.amazonaws.com/continue-docs/logo/light.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continue is an open-source autopilot in IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/a18792721831/studyplugin/535b9cab69da0f97b42dcaebb00bb0d4ed15c8a6/translate/src/main/resources/META-INF/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/18336-chinese-english-translate\">Chinese-English Translate</a> </td>\n        <td> Chinese-English Translate is a multiple translation services in JetBrain's IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://ai-commit.com/git-commit-logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/24851-ai-git-commit\">AI Git Commit</a> </td>\n        <td> This plugin uses AI to automatically generate commit messages based on the changes in your code. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/YiiGuxing/TranslationPlugin/blob/master/pluginIcon.svg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://intellij-translation.yiiguxing.top/#/en/\">IntelliJ Translation Plugin</a> </td>\n        <td> A translation plugin for IntelliJ-based IDEs that integrates multiple translation services, including OpenAI Translator (compatible with DeepSeek, Doubao, Ollama, etc.), allowing direct translation of code texts like comments and documentation within the IDE at any time. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"discord\">Discord Bots</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://geneplore.com/img/geneplore_color_logo_circular.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Geneplore AI/README.md\"> Geneplore AI </a> </td>\n        <td> Geneplore AI runs one of the largest AI Discord bots, now with Deepseek v3 and R1. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"codeeditor\">Native AI Code Editor</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/126759922?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.cursor.com/\"> Cursor </a> </td>\n        <td>‍The AI Code Editor based on VS Code</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://exafunction.github.io/public/images/windsurf/windsurf-app-icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://codeium.com/windsurf\"> WindSurf </a> </td>\n        <td>Another AI Code Editor based on VS Code by Codeium</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/wusigram/assets/logo-512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wusigram/README.md\"> 无思微程序 </a> </td>\n        <td>A mobile AI code writing and running tool. DeepSeek Programming Companion</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"emacs\">Emacs</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/karthink/gptel\"> gptel </a> </td>\n        <td>A simple LLM client for Emacs</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/milanglacier/minuet-ai.el\"> Minuet AI </a> </td>\n        <td>Dance with Intelligence in Your Code 💃</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"security\">Security</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/lukehinds/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/codegate.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/stacklok/codegate/\"> CodeGate </a> </td>\n        <td> CodeGate: secure AI code generation</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/tencent/hunyuan.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tencent/AI-Infra-Guard\"> AI-Infra-Guard </a> </td>\n        <td> Tencent's Hunyuan Security Team - AI infrastructure security assessment tool designed to discover and detect potential security risks in AI systems.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"providers\">Providers</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/aimlapi/aimlapi_logo.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://docs.aimlapi.com/api-references/text-models-llm?utm_source=awesome-deepseek-integrations&utm_medium=github&utm_campaign=integration\"> AI/ML API </a> </td>\n        <td> AI/ML API gives users enterprise-grade access to 200+ models with just one API. This includes Deepseek R1 and V3, alongside closed and open-source models. All at 99% uptime and with 24/7 human support.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n###  <span id=\"others\">Others</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/mlflow/mlflow/refs/heads/master/assets/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://mlflow.org/docs/latest/tracing/integrations/deepseek\"> MLflow </a></td>\n        <td> Open-source MLOps / LLMOps platform for build, test, deploy, and monitor AI applications with DeepSeek. </td>\n    </tr>\n    <tr>\n        <td style=\"font-size: 64px\">🤖</td>\n        <td> <a href=\"https://github.com/wangrongding/wechat-bot/blob/main/README.md\"> Wechat-Bot </a></td>\n        <td> A wechat robot based on WeChaty combined with DeepSeek and other Ai services. </td>\n    </tr>\n    <tr>\n        <td style=\"font-size: 64px\">&#128032;</td>\n        <td> <a href=\"https://github.com/lunary-ai/abso/blob/main/README.md\"> Abso </a></td>\n        <td> TypeScript SDK to interact with any LLM provider using the OpenAI format. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.imgur.com/IsQYInJ.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/djcopley/ShellOracle/\"> ShellOracle </a> </td>\n        <td> A terminal utility for intelligent shell command generation. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/178783630?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bolna-ai/bolna/\"> Bolna </a> </td>\n        <td> Use DeepSeek as the LLM for conversational voice AI agents</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/fatwang2/siri-ultra\"> Siri Ultra </a> </td>\n        <td> A GitHub project with 1000 stars, supporting internet connectivity, multi-turn conversations, and DeepSeek series models </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c1e47b01-1766-4f7e-bfe6-ab3cb3991c30\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/tree/main/docs/siri_deepseek_shortcut\"> siri_deepseek_shortcut </a> </td>\n        <td> Siri equiped with the DeepSeek API </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/n8n-io/n8n/blob/master/assets/n8n-logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/rubickecho/n8n-deepseek\"> n8n-nodes-deepseek </a> </td>\n        <td> An N8N community node that supports direct integration with the DeepSeek API into workflows. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/TSKshn2UFdTyvUi85EDMIXrXgs.png?scale-down-to=512\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Portkey-AI/gateway\"> Portkey AI </a> </td>\n        <td> Portkey is a unified API for interacting with over 1600+ LLM models, offering advanced tools for control, visibility, and security in your DeepSeek apps. Python & Node SDK available. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/8rF2JOaZ8l9AvM4H6ezliw44aI.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/BerriAI/litellm\"> LiteLLM </a> </td>\n        <td> Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format. Supports DeepSeek AI with cost tracking as well. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.postimg.cc/k5Z4YWjt/Screenshot-2025-01-23-at-6-08-01-PM.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mem0ai/mem0\"> Mem0 </a> </td>\n        <td> Mem0 enhances AI assistants with an intelligent memory layer, enabling personalized interactions and continuous learning over time. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://simplismart-public-assets.s3.ap-south-1.amazonaws.com/logos/Logo+Icon+Light.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://simplismart.ai/\"> Simplismart AI </a> </td>\n        <td> Simplismart enables seamless GenAI deployments with the fastest inference for LLMs, Diffusion, and Speech models. Deploy Deepseek effortlessly on the Simplismart Cloud or with your own Cloud. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.promptfoo.dev/img/logo-panda.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/promptfoo/README.md\"> promptfoo </a> </td>\n        <td> Test and evaluate LLM prompts, including DeepSeek models. Compare different LLM providers, catch regressions, and evaluate responses. </td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/AndersonBY/deepseek-tokenizer\"> deepseek-tokenizer </a> </td>\n        <td> An efficient and lightweight tokenization library for DeepSeek models, relying solely on the `tokenizers` library without heavy dependencies like `transformers`. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://langfuse.com/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://langfuse.com/docs/integrations/deepseek\"> Langfuse </a> </td>\n        <td> Open-source LLM observability platform that helps teams collaboratively debug, analyze, and iterate on their DeepSeek applications. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/8226202?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/comet-ml/opik\"> Opik </a> </td>\n        <td> Open-source platform for LLM observability, evaluations, and prompt optimization for DeepSeek applications. </td>\n    </tr>\n    <tr>\n        <td> CR </td>\n        <td> <a href=\"https://github.com/hustcer/deepseek-review\"> deepseek-review </a> </td>\n        <td> 🚀 Sharpen Your Code, Ship with Confidence – Elevate Your Workflow with Deepseek Code Review 🚀 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"http://gptlocalhost.com/wp-content/uploads/2025/01/icon_1024.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://youtu.be/T1my2gqi-7Q\"> GPTLocalost </a> </td>\n        <td> Use DeepSeek-R1 in Microsoft Word Locally. No inference costs. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/suqicloud/wp-ai-chat/raw/main/ic_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/suqicloud/wp-ai-chat\"> WordPress ai助手 </a> </td>\n        <td> Docking Deepseek api for WordPress site ai conversation assistant, post generation, post summary plugin. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/ComfyUI-Copilot/assets/logo 2.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/AIDC-AI/ComfyUI-Copilot\"> ComfyUI-Copilot </a> </td>\n        <td> An intelligent assistant built on the Comfy-UI framework that simplifies and enhances the AI algorithm debugging and deployment process through natural language interactions. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Optima-CityU/llm4ad/blob/main/assets/figs/logo_short.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> is a unified open-source Python-based Platform using Large Language Models (LLMs) for Automatic Algorithm Design (AD).</td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/JiauZhang/chatchat\"> chatchat </a> </td>\n        <td> Large Language Models Python API. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.imgur.com/zDgW8wB.png\" width=\"64\" alt=\"Icon\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/skypilot-org/skypilot\">SkyPilot</a> </td>\n        <td> <a href=\"https://github.com/skypilot-org/skypilot/tree/master/llm/deepseek-r1\">Serve DeepSeek models</a> in any cloud infrastructure (Kubernetes, AWS, Azure, GCP, or GPU clouds). Autoscale to multi-region, multi-cluster, and multi-cloud.</td>\n    </tr>\n    <tr>\n        <td></td>\n        <td> <a href=\"https://serpapi.com/blog/connect-deepseek-api-with-the-internet-google-search-and-more/#connect-deepseek-with-google-search-result\"> SerpApi </a> </td>\n        <td> Connect DeepSeek API with search results like Google. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/yincongcyincong/telegram-deepseek-bot/blob/main/static/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> is a Telegram bot integrated with DeepSeek AI capabilities. </td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> is an AI-powered CLI tool to generate context-aware shell commands with multi-backend LLM support. Supports shell-specific syntax, read-only system tools, and custom inference endpoints.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.godtierprompts.com/logo.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a> </td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a> is a community driven leaderboard where the best prompts rise to the top.</td>\n    </tr>\n    <tr>\n<td> <img src=\"https://avatars.githubusercontent.com/u/89342560?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Jeff2Ma/AlfredWorkflow-DeepSeek\">DeepSeek Alfred WorkFlow</a> </td>\n        <td> DeekSeek integrations in Alfred. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/cbf6193b-fd66-4b88-bcf7-98699becf046\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sally-suite/open-office-copilot\">Open Office Copilot</a> </td>\n        <td> Open Office Copilot is an open-source Office copilot that supports Microsoft Office and Google Workspace, based on AI-Agent. It can help you with writing in Word, generating slides in PowerPoint, analyzing data in Excel, and generating emails in Outlook, among other tasks. It has now integrated with DeepSeek. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/LSTM-Kirigaya/openmcp-client/raw/main/icons/openmcp.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/LSTM-Kirigaya/openmcp-client\"> OpenMCP </a> </td>\n        <td> An all-in-one VS Code/Trae/Cursor plugin for MCP server development and debugging. Uses DeepSeek as the default LLM for testing MCP servers. </td>\n    </tr>\n    <tr>\n<td></td>\n        <td> <a href=\"https://github.com/informatico-madrid/blackwell-linux-infra-optimizer\"> Blackwell Linux Infra Optimizer </a> </td>\n        <td> Optimized vLLM stack for NVIDIA Blackwell (SM_120) and Linux Kernel 6.14. Achieving 59.0 t/s on DeepSeek-R1-32B using native FlashInfer backend. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#table-of-contents\">^ Back to Contents ^</a></p>\n\n### Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=deepseek-ai/awesome-deepseek-integration&type=Date)](https://star-history.com/#deepseek-ai/awesome-deepseek-integration&Date)\n"
  },
  {
    "path": "README_cn.md",
    "content": "<div align=\"center\">\n\n<p align=\"center\">\n<img width=\"1280\" alt=\"Awesome DeepSeek Integrations\" src=\"docs/Awesome DeepSeek Integrations.png\">\n</p>\n\n# DeepSeek 实用集成 ![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)\n\n将 DeepSeek 大模型能力轻松接入各类软件。访问 [DeepSeek 开放平台](https://platform.deepseek.com/) 来获取您的 API key。\n\n[English](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README.md) / 简体中文 / [繁体中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_zh_tw.md) / [日本語](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_ja.md) / [Español](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_es.md)\n\n</div>\n\n<br></br>\n\n## 目录\n\n- [DeepSeek 实用集成 ](#deepseek-实用集成-)\n  - [目录](#目录)\n  - [项目列表](#项目列表)\n    - [应用程序](#应用程序)\n    - [AI Agent 框架](#ai-agent-框架)\n    - [AI数据应用框架](#ai数据应用框架)\n    - [RAG 框架](#rag-框架)\n    - [FHE (全同态加密) frameworks](#fhe-全同态加密-frameworks)\n    - [Solana 框架](#solana-框架)\n    - [综合数据管理](#综合数据管理)\n    - [即时通讯插件](#即时通讯插件)\n    - [Office插件](#office插件)\n    - [浏览器插件](#浏览器插件)\n    - [VS Code 插件](#vs-code-插件)\n    - [neovim 插件](#neovim-插件)\n    - [JetBrains 插件](#jetbrains-插件)\n    - [AI Code编辑器](#ai-code编辑器)\n    - [安全](#安全)\n    - [其它](#其它)\n\n## 项目列表\n\n###  <span id=\"applications\">应用程序</span>\n\n<table>\n    <tr>\n        <td><img src=\"docs/ETOS-LLM-Studio/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"docs/ETOS-LLM-Studio/README.md\">ETOS LLM Studio</a></td>\n        <td>ETOS LLM Studio (ELS) 是一款专为 watchOS 与 iOS 深度定制的旗舰级 AI 客户端。它拥有“腕上智核”的独立交互体验、极简的律动美学设计以及全端联动的无缝体验。支持 DeepSeek 等多种模型，重塑你手腕上的 AI 交互维度。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/operit/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/AAswordman/Operit\">Operit AI</a></td>\n        <td>面向安卓平台的开源系统集成化ai助手，支持几乎完整的mcp使用，高度兼容安卓系统。软件同时具备高度自定义和上手低门槛，内置文件操作/搜索/自动点击/格式转换等工具调用，并内置deepseek api网页。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/openEuler Intelligence/intelligence_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.openeuler.org/zh/projects/intelligence/\">openEuler Intelligence</a></td>\n        <td>基于 openEuler 的大模型智能平台，深度整合了包括 DeepSeek 在内的主流大语言模型，并具备本地知识库构建能力。平台提供语义接口注册、MCP 服务管理、智能体（Agent）开发及自动化工作流编排等核心功能，同时支持 Web 端和桌面客户端双模式访问，显著提升开发效率与企业级应用体验！</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/hh-wserver/wserver.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/hzmosi/ai-wechat\">微信RPA智能客服</a></td>\n        <td>AI双擎-微信智能客服。内置Deepseek官方API及阿里百炼Deepseek API，AI服务不可用时无缝自动切换，全天持续稳定运行！本工具通过RPA自动化实现，不访问私有接口。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/OpenXLab/migo/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://migo.intern-ai.org.cn/\">觅果</a></td>\n        <td>免费的 AI 创新加速工具，提供智能问答、论文深度理解、前沿 AI 工具以及个人学术知识库。作为探索的伙伴，觅果助你发现并实现卓越创意！</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/eechat/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Lucassssss/eechat\">eechat</a></td>\n        <td>简洁易用的大模型本地部署工具，支持开源模型 DeepSeek-R1， DLlama 3, Phi-4, Mistral, Gemma 3 等模型的本地化隐私部署，同时支持远程大模型API调用。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/aingdesk/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/aingdesk/AingDesk\">AingDesk</a></td>\n        <td>一键把AI模型部署在你电脑，操作可视化，内置精美聊天界面，可在线分享他人共用，支持 DeepSeek 等其他模型，支持联网搜索和第三方API</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/dingtalk/assets/dingtalk_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.dingtalk.com/\">钉钉</a></td>\n        <td>钉钉 AI 助理，它融合了钉钉平台的多项 AI 产品功能，以智能化的方式辅助企业日常的工作流程。钉钉 AI 助理具备多种智能能力，包括但不限于智能沟通、智能协同、智能管理等。通过这些功能，AI 助理能够在企业内部中归纳要点、生成会议纪要，并且能够为用户推送相关工作任务和日程提醒。此外，钉钉 AI 助理还能够通过知识库的能力智能地回答员工企业的行政流程、人力资源政策等多个方面的常见问题。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/mrzhang1013/CodingSee/blob/main/codingseeicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.codingsee.com\">CodingSee-AI伴学</a></td>\n        <td>CodingSee是一款专为中国少儿编程设计的软件，内容包含社区，项目协作，站内实时消息，AI问答，Scratch/Python/C++编译环境，代码精准纠错的集成平台，UI设计友好，目前支持Windows和mac系统。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://chatdoc.com/chatdoc/chatdoc.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://chatdoc.com\">ChatDOC</a></td>\n        <td>ChatDOC是一款AI文档阅读工具，具备强大的溯源功能，确保每一条信息的来源清晰可查，助您高效、精准地掌握文档核心。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/SwiftChat/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/SwiftChat/README_cn.md\">SwiftChat</a></td>\n        <td> <a href=\"https://github.com/aws-samples/swift-chat\">SwiftChat</a> 是一款使用 React Native 构建的闪电般快速的跨平台 AI 聊天应用。它在 Android、iOS 和 macOS 上提供原生性能。功能包括实时流式聊天、丰富的 Markdown 支持、AI 图像生成、可自定义系统提示、快速切换模型和多模态能力。支持 DeepSeek、Amazon Bedrock、Ollama 和 OpenAI API 兼容的模型，并具有简洁的用户界面和高性能表现。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://4everlogo.4everland.store/logo/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/4EVERChat/README_cn.md\">4EVERChat</a></td>\n        <td><a href=\"https://chat.4everland.org/\">4EVERChat</a> 是集成数百款LLM的智能模型选型平台，支持直接对比不同模型的实时响应差异，基于<a href=\"https://www.4everland.org/\">4EVERLAND</a> AI RPC 统一API端点实现零成本模型切换，自动选择响应快、成本低的模型组合。</td>\n    </tr>\n    <tr>\n        <td><img src=\"./docs/xhai_browser/assets/logo_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"./docs/xhai_browser/README_cn.md\">小海浏览器</a></td>\n        <td>小海浏览器是安卓桌面管理&AI浏览器,DeepSeek是默认AI对话引擎.他有极致的性能(0.2秒启动),苗条的体型(apk 3M大),无广告,超高速广告拦截,多屏分类,屏幕导航,多搜索框,一框多搜</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/gptbots/gptbots.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.gptbots.ai/zh_CN/docs\">GPTBots</a> </td>\n        <td> <a href=\"https://www.gptbots.ai/zh_CN\">GPTBots</a> 是一个无代码的 AI Agent 构建平台，集成了包括 Deepseek 在内的国际主流 LLM，并提供了基于 RAG 的知识存储/检索，工具自定义/调用，工作流编排等模块，并可将 Agent 集成至多个主流平台（WhatsApp、Telegram 等），为企业提供端到端的 AI 解决方案，助力企业在 AI 时代脱颖而出。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/build/icon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/README.md\">DeepChat</a></td>\n        <td>DeepChat 是一款完全免费的桌面端智能助手，内置强大的 DeepSeek 大模型，支持多轮对话、联网搜索、文件上传、知识库等多种功能。</td>\n    </tr>\n    <tr>\n        <td></td>\n        <td> <a href=\"https://github.com/wangrongding/wechat-bot/blob/main/README.md\"> Wechat-Bot </a></td>\n        <td> 基于 wechaty 实现的微信机器人，结合了 DeepSeek 和其他 Ai 服务。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/171659527?s=400&u=39906ab3b6e2066f83046096a66a77fb3f8bb836&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/quantalogic/quantalogic\">Quantalogic</a> </td>\n        <td> QuantaLogic 是一个 ReAct（推理和行动）框架，用于构建高级 AI 代理。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/224d547a-6fbc-47c8-859f-aa14813e2b0f\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatbox/README_cn.md\">Chatbox</a> </td>\n        <td> 一个支持多种流行LLM模型的桌面客户端，可在 Windows、Mac 和 Linux 上使用 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/bb65404c-f867-42d8-ae2b-281fe953ab54\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_next_web/README_cn.md\"> ChatGPT-Next-Web </a> </td>\n        <td> 一键获取跨平台ChatGPT网页用户界面，支持流行的LLM </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/Casibase/assets/casibase.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://casibase.org/zh/docs/category/beginner-guide/\">Casibase</a></td>\n        <td> <a href=\"https://casibase.org\">Casibase</a> 是一个开源的 AI 知识库和对话系统，它结合了最新的 RAG 技术、SSO 功能，并支持各种主流 AI 模型。旨在为企业和开发者提供一个功能强大、灵活易用的知识管理和智能对话平台。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/Coco AI/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Coco AI/README_cn.md\">Coco AI</a></td>\n        <td> <a href=\"https://coco.rs\">Coco AI</a> 是一个完全开源、跨平台的统一搜索与效率工具，能够连接并搜索多种数据源，包括应用程序、文件、谷歌网盘、Notion、语雀、Hugo 等本地与云端数据。通过接入 DeepSeek 等大模型，Coco AI 实现了智能化的个人知识库管理，注重隐私，支持私有部署，帮助用户快速、智能地访问信息。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/liubai/assets/liubai-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/liubai/README_cn.md\">留白记事</a> </td>\n        <td> 留白让你直接在微信上使用 DeepSeek 管理你的笔记、任务、日程和待办清单！ </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1ac9791b-87f7-41d9-9282-a70698344e1d\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/pal/README_cn.md\"> Pal - AI Chat Client<br/>(iOS, ipadOS) </a> </td>\n        <td> 一款可以在 iPhone 或 iPad 上使用的 AI 助手 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.librechat.ai/librechat.svg\" alt=\"LibreChat\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/deepseek\">LibreChat</a> </td>\n        <td> LibreChat 是一个可定制的开源应用程序，无缝集成了 DeepSeek，以增强人工智能交互体验 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.papersgpt.com/images/logo/favicon.ico\" alt=\"PapersGPT\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/papersgpt/papersgpt-for-zotero\">PapersGPT</a> </td>\n        <td> PapersGPT是一款集成了DeepSeek及其他多种AI模型的辅助论文阅读的Zotero插件。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/rss-translator/RSS-Translator/main/core/static/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/rss_translator/README_cn.md\"> RSS翻译器 </a> </td>\n        <td> 开源、简洁、可自部署的RSS翻译器 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://relingo.net/assets/images/relingo-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://relingo.net\"> Relingo </a> </td>\n        <td> 在浏览网站和观看 YouTube 视频时，轻松构建和掌握词汇！ </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/enconvo/README_cn.md\"> Enconvo </a> </td>\n        <td> Enconvo是AI时代的启动器,是所有AI功能的入口,也是一位体贴的智能助理。 </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/kangfenmao/cherry-studio/blob/main/src/renderer/src/assets/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cherrystudio/README_cn.md\">Cherry Studio</a></td>\n        <td> 一款为创造者而生的桌面版 AI 助手 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://tomemo.top/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/tomemo/README_cn.md\"> ToMemo (iOS, ipadOS) </a> </td>\n        <td> 一款短语合集 + 剪切板历史 + 键盘输出的iOS应用，集成了AI大模型，可以在键盘中快速输出使用。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/buxuku/video-subtitle-master/refs/heads/main/resources/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/buxuku/video-subtitle-master\">Video Subtitle Master</a></td>\n        <td> 批量为视频生成字幕，并可将字幕翻译成其它语言。这是一个客户端工具, 跨平台支持 mac 和 windows 系统, 支持百度，火山，deeplx, openai, deepseek, ollama 等多个翻译服务 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/tisfeng/ImageBed/main/uPic/icon_512x512@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tisfeng/Easydict\">Easydict</a></td>\n        <td> Easydict 是一个简洁易用的词典翻译 macOS App，能够轻松优雅地查找单词或翻译文本，支持调用大语言模型 API 翻译。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.raycast.com/favicon-production.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/raycast/README_cn.md\">Raycast</a></td>\n        <td> <a href=\"https://raycast.com/?via=ViGeng\">Raycast</a> 是一款 macOS 生产力工具，它允许你用几个按键来控制你的工具。它支持各种扩展，包括 DeepSeek AI。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/chatpdflocal/assets/chatpdflocal-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatpdflocal.com\">ChatPDFLocal</a> </td>\n        <td> ChatPDFLocal 是一款基于AI的Mac OS App，可以帮助您与PDF互动，可以帮助您快速地理解PDF，它集成了DeepSeek及其他多种AI模型旨在提高您的阅读效率。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/zotero/assets/zotero-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/zotero/README_cn.md\">Zotero</a></td>\n        <td> <a href=\"https://www.zotero.org\">Zotero</a> 是一款免费且易于使用的文献管理工具，旨在帮助您收集、整理、注释、引用和分享研究成果。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://b3log.org/images/brand/siyuan-128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/SiYuan/README_cn.md\">思源笔记</a> </td>\n        <td> 思源笔记是一款隐私优先的个人知识管理系统，支持完全离线使用，并提供端到端加密的数据同步功能。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/ArvinLovegood/go-stock/raw/master/build/appicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/ArvinLovegood/go-stock/blob/master/README.md\">go-stock</a> </td>\n        <td> go-stock 是一个由 Wails 使用 NativeUI 构建并由 LLM 提供支持的股票数据查看分析器。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/102771702?s=200&v=4\" alt=\"Wordware\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-wordware/blob/master/README.md\">Wordware </a> </td>\n        <td><a href=\"https://www.wordware.ai/\">Wordware</a> 这是一个工具包，使任何人都可以仅通过自然语言构建、迭代和部署他们的AI堆栈 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/xRJ6vNo9mUYeVNxt0KITXCXEuSk.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/langgenius/dify/\">Dify</a> </td>\n        <td> <a href=\"https://dify.ai/\">Dify</a> 是一个支持 DeepSeek 模型的 LLM 应用开发平台，可用于创建 AI 助手、工作流、文本生成器等应用。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/LiberSonora/LiberSonora/blob/main/assets/avatar.jpeg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/LiberSonora/LiberSonora\">LiberSonora</a> </td>\n        <td> LiberSonora，寓意\"自由的声音\"，是一个 AI 赋能的、强大的、开源有声书工具集，包含智能字幕提取、AI标题生成、多语言翻译等功能，支持 GPU 加速、批量离线处理 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ripperhe/Bob/master/docs/_media/icon_128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a></td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a> 是一款 macOS 平台的翻译和 OCR 软件，您可以在任何应用程序中使用 Bob 进行翻译和 OCR，即用即走！ </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/STranslate/STranslate/refs/heads/main/images/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a></td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a>（Windows） 是 WPF 开发的一款即用即走的翻译、OCR工具 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.gptaiflow.tech/logo.png\" alt=\"gpt-ai-flow-logo\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.gptaiflow.tech/zh/docs/product/api-keys-setup#setup-deepseek-api-keys\">GPT AI Flow</a></td>\n        <td>\n            工程师为效率狂人（他们自己）打造的终极生产力武器: <a href=\"https://www.gptaiflow.tech/zh/\">GPT AI Flow</a>\n            <ul>\n                <li>`Shift+Alt+空格` 唤醒桌面智能中枢</li>\n                <li>本地加密存储</li>\n                <li>自定义指令引擎</li>\n                <li>按需调用拒绝订阅捆绑</li>\n            </ul>\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/b09f17a8-936d-4dac-8b24-1682d52c9a3c\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/alecm20/story-flicks\">Story-Flicks</a></td>\n        <td> 通过一句话即可快速生成高清故事短视频，支持 DeepSeek 等模型。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/assets/favicon1.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/README_cn.md\"> Alpha派 </a> </td>\n        <td> AI投研助理/AI驱动的新一代金融信息入口。代理投资者听会/记纪要，金融投资信息的搜索问答/定量分析等投资研究工作。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://docs.xark-argo.com/img/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.xark-argo.com\">argo</a> </td>\n        <td> 本地下载并运行Huggingface及Ollama模型，支持RAG、LLM API、工具接入等，支持Mac/Windows/Linux。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://5ire.app/favicon.ico\" alt=\"5ire-logo\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/nanbingxyz/5ire\">5ire</a> </td>\n        <td> <a href=\"https://github.com/nanbingxyz/5ire\">5ire</a>是一款设计友好的跨平台开源桌面智能助手，兼容市面主流的大模型，支持 MCP Servers，本地知识库、提示词库及众多实用功能。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.petercat.ai/images/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.petercat.ai\">PeterCat</a> </td>\n        <td> 我们提供对话式答疑 Agent 配置系统、自托管部署方案和便捷的一体化应用 SDK，让您能够为自己的 GitHub 仓库一键创建智能答疑机器人，并快速集成到各类官网或项目中， 为社区提供更高效的技术支持生态。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/labring/FastGPT/refs/heads/main/.github/imgs/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fastgpt.cn/zh\">FastGPT</a> </td>\n        <td>\n            FastGPT 基于 LLM 大模型的开源 AI 知识库构建平台，支持 DeepSeek、OpenAI 等多种模型。我们提供了开箱即用的数据处理、模型调用、RAG 检索、可视化 AI 工作流编排等能力，帮助您轻松构建复杂的 AI 应用。\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cdn.link-ai.tech/doc/CoW%20logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zhayujie/chatgpt-on-wechat\">Chatgpt-on-Wechat</a> </td>\n        <td> Chatgpt-on-Wechat（CoW）项目是一个灵活的聊天机器人框架，支持将DeepSeek、OpenAI、Claude、Qwen等多种LLM 一键接入到微信公众号、企业微信、飞书、钉钉、网站等常用平台或办公软件，并支持丰富的自定义插件。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/ruzhiai_note/assets/play_store_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/ruzhiai_note/README_cn.md\">如知AI笔记</a> </td>\n        <td>如知AI笔记是一款智能化的AI知识管理工具，致力于为用户提供一站式的知识管理和应用服务，包括AI搜索探索、AI结果转笔记、笔记管理与整理、知识演示与分享等。集成了DeepSeek深度思考模型，提供更稳定、更高质量的输出。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://athenalab.ai/assets/favicon/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://athenalab.ai/\">Athena</a> </td>\n        <td>世界上首个具有先进认知架构和类人推理能力的自主通用人工智能，旨在解决复杂的现实世界挑战。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/TigerGPT/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.laohu8.com/gpt\">TigerGPT</a> </td>\n        <td>TigerGPT 是老虎集团开发的，业内首个基于 OpenAI 的金融 AI 投资助理。TigerGPT 旨在为投资者提供智能化的投资决策支持。2025年2月18日，TigerGPT 正式接入 DeepSeek-R1 模型，为用户提供支持深度推理的在线问答服务。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/HIX.AI/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://hix.ai\">HIX.AI</a> </td>\n        <td>免费试用 DeepSeek，在 HIX.AI 上享受无限量的 AI 聊天。使用 DeepSeek R1 进行 AI 聊天、写作、编码等。立即体验下一代 AI 聊天！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/sharmt1411/askanywhere/blob/main/icon/Depth_8,_Frame_0explore-%E8%A7%92%E6%A0%87.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sharmt1411/askanywhere\">划词AI助手</a> </td>\n        <td>一个划词ai助手，在任何地方划词，快速打开与Deepseek的对话！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/OJZen/1chat/raw/refs/heads/main/doc/assets/icon.ico?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/OJZen/1chat\">1查</a> </td>\n        <td>一款能让你在本地运行 DeepSeek 的 iOS 应用</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://chatlabsai.com/assets/logo/logo.png\" alt=\"iOS AI 聊天机器人\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chatlabsai.com\">在一个应用中访问250多个文本、图像大模型</a> </td>\n        <td> 1AI iOS聊天机器人集成了250多个文本、图像、语音模型，让用户可以与OpenRouter、Replicate上的任何模型对话，包括Deepseek推理和Deepseek V3模型。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/PopAi/assets/logo.svg\" alt=\"PopAi\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://popai.pro\">PopAi</a> </td>\n        <td>PopAi推出DeepSeek R1！享受无延迟、闪电般快速的性能，尽在PopAi。轻松切换在线搜索开/关。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pot-app.com/logo/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a></td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a> 🌈一个跨平台的划词翻译和OCR软件 </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Byaidu/PDFMathTranslate/raw/main/docs/images/banner.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Byaidu/PDFMathTranslate\">PDFMathTranslate</a></td>\n        <td>PDFMathTranslate是一款基于 AI 完整保留排版的 PDF 文档全文双语翻译工具。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Richasy/Bili.Copilot/raw/master/assets/StoreLogo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Richasy/Bili.Copilot\">哔哩助理</a></td>\n        <td>B站第三方 Windows 桌面客户端，使用 Windows App SDK 构建的原生应用。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://www.tensorbounce.com/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.tensorbounce.com/\">LawAgent</a></td>\n        <td>LawAgent是tensorbounce团队出品的知识库结合AI Agent的法律AI产品,拥有上千万官方法律相关知识库数据，用户可自定义知识库，专业模式结合DeepSeek-R1的推理能力应用在用户的法律分析、合同审查、文书生成、文件翻译等法律场景。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://h1.appinn.me/file/1741929316827_21.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/jiqi136/DS-AI\">实时联网AI助手</a></td>\n        <td>AI助手支持DeepSeek-V3.1接口直连最强Claude Code代码模型，无需网络中转即可使用（成本直降90%）。 支持图片、PDF文件读取及免费生成图片；可自定义接入其他AI模型；支持调用本地浏览器实时联网检索海量网页内容。另提供R1等免费模型选择。</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/AlphaBot/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://alphabot.x-pai.com/\">AlphaBot</a> </td>\n        <td> AlphaBot是一款智能股票分析助手，整合多源数据与AI分析技术，提供技术分析、预测和风险评估功能，帮助投资者做出数据驱动的交易决策。支持一键部署，操作简便，支持Windows/Linux/MacOS等平台</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/remio/assets/remio_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.remio.ai/\">remio</a></td>\n        <td>remio 是一个 AI 驱动的个人知识中心，通过自动捕获浏览的网页内容、解析本地文件并整合个人笔记，构建个性化的知识库。它支持在个人知识库中进行搜索和自然语言问答，以提供即时洞察，同时提供智能写作辅助——适应您的写作风格，轻松简化起草、润色和完成内容的过程。remio 采用本地优先存储设计，优先保护数据隐私，同时集中管理零散信息，以实现最大化的生产力。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/DocKit/assets/dockit.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://dockit.geekfun.club/\">DocKit</a></td>\n        <td>DocKit是一款由AI驱动的桌面GUI客户端，专为NoSQL数据库设计，支持Mac、Windows和Linux操作系统上的Elasticsearch和OpenSearch。通过集成DeepSeek等大型模型，DocKit可以帮助开发者编写复杂的DSL查询，并提升数据管理和分析的用户体验。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/zenfeed/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/glidea/zenfeed\">zenfeed</a> </td>\n        <td> 用 AI 赋能 RSS，自动筛选、总结、推送重要信息，告别信息过载。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/NoteGen/NoteGen.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/codexu/note-gen\">NoteGen</a> </td>\n        <td> NoteGen 是一款的跨端的 Markdown 笔记应用，致力于使用 AI 建立记录和写作的桥梁，将碎片化知识整理成一篇可读的笔记。 </td>\n    </tr>\n    <tr>\n        <td></td>\n        <td> <a href=\"https://github.com/SamYuan1990/i18n-agent-action\">i18n-agent-action</a> </td>\n        <td> i18n Agent是一款人工智能驱动的工具，旨在简化和自动化国际化（i18n）与本地化（l10n）工作流程。它通过先进的自然语言处理（NLP）和机器学习技术，帮助开发者、翻译人员和产品团队高效管理多语言内容——既能消除人工错误，又能加速全球部署进程。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/obot-platform/obot/refs/heads/main/docs/static/img/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/obot-platform/obot\">Obot</a> </td>\n        <td> Obot 是一个用于构建和部署 AI 助手的智能体平台，内置 RAG、工作流自动化，并可与流行工具和服务无缝集成，支持 DeepSeek 等大语言模型。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://3min.top/imgs/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://3min.top/zh\">3mintop</a> </td>\n        <td> 一个强大的AI驱动工具，帮助您在3分钟内快速总结和理解任何内容，支持DeepSeek模型以增强理解能力。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cantian.ai/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://cantian.ai/\">参天AI</a></td>\n        <td>基于高质量数据集打造的八字命理AI</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://obsidian.md/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/TarsLab/obsidian-tars\">Obsidian Tars</a></td>\n        <td> 把大模型对话融入到 Obsidian 的笔记编辑, deepseek-reasoner 的思维链以 callout 格式输出。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.chatbotbuilder.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bobbylkchao/chatbotBuilder\">AI Chatbot Builder</a> </td>\n        <td> <a href=\"www.chatbotbuilder.dev/\">Chatbot Builder</a> 是一个开源平台，集成了 DeepSeek 和 OpenAI模型，允许用户为不同的对话场景创建定制化的聊天机器人。通过低代码和可配置的方式，轻松构建智能对话体验。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://bibigpt.co/icons/lucid/icon_32x32@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"http://bibigpt.co\">BibiGPT</a> </td>\n        <td> <a href=\"http://bibigpt.co\">BibiGPT</a> 是一款AI音视频助理，支持B站、油管、小红书、小宇宙播客等主流平台的内容分析和总结，让音视频看得快、搜得到、用得好。提供内容摘要、智能问答和文章生成等功能。支持视频文件上传、笔记应用集成和DeepSeek R1及V3模型。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lobehub.com/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://lobehub.com/zh/docs/usage/providers/deepseek\">LobeChat</a> </td>\n        <td> <a href=\"https://lobehub.com\">LobeChat</a> - 一款开源的现代化 AI 对话框架。支持 DeepSeek R1、知识库（文件上传/知识管理/RAG）、多模态能力（视觉/语音合成/插件/创作）。一键免费部署专属 DeepSeek 应用，打造您的私人 AI 助手。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/ruzhiai_note/assets/play_store_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/ruzhiai_note/README_cn.md\">如知AI笔记</a> </td>\n        <td>如知AI笔记是一款智能化的AI知识管理工具，致力于为用户提供一站式的知识管理和应用服务，包括AI搜索探索、AI结果转笔记、笔记管理与整理、知识演示与分享等。集成了DeepSeek深度思考模型，提供更稳定、更高质量的输出。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cdn.link-ai.tech/doc/CoW%20logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zhayujie/chatgpt-on-wechat\">Chatgpt-on-Wechat</a> </td>\n        <td> Chatgpt-on-Wechat（CoW）项目是一个灵活的聊天机器人框架，支持将DeepSeek、OpenAI、Claude、Qwen等多种LLM 一键接入到微信公众号、企业微信、飞书、钉钉、网站等常用平台或办公软件，并支持丰富的自定义插件。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.weiyuai.cn/logo.png\" alt=\"AI Customer Service\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Bytedesk/bytedesk\">微语</a> </td>\n        <td> 企业级多租户即时通讯解决方案，免费开源8件套：企业IM、在线客服、企业知识库、帮助文档、工单系统、AI对话、项目管理、工作流。.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://raw.githubusercontent.com/rockbenben/subtitle-translator/main/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/rockbenben/subtitle-translator\">Subtitle Translator</a></td>\n        <td>支持 SRT/ASS/VTT/LRC 格式的批量字幕翻译工具，兼容 DeepSeek 等多种大模型接口和机器翻译接口。</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/turtlenoir/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://haiguitang.net/\"> 出前一汤 </a> </td>\n        <td> <a href=\"https://haiguitang.net/\"> 出前一汤 </a> 基于 DeepSeek 的 AI 主持人海龟汤 / 侧向思维解谜产品，可单人或者多人游玩。AI 进行控场与吐槽，围绕“是 / 否 / 无关”的问答推进推理；提供沉浸式玩法（更强剧情氛围与节奏引导）、引导提示与防卡关机制，同时结合向量检索 + DeepSeek 进行题目去重，并提供内容审核能力。适合轻量脑洞训练与在线陪玩。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/songquanpeng/one-api/main/web/default/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/songquanpeng/one-api\">One API</a> </td>\n        <td> LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/guyoung/AIMatrices/raw/main/docs/assets/logo/ai-matrices1.png\" alt=\"AIMatrices 图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/guyoung/AIMatrices/blob/main/README.md\">AIMatrices</a> </td>\n        <td>AIMatrices 是一款轻量级、高性能、可扩展、开源的AI应用快速构建平台，旨在为开发者提供高效、便捷的 AI 应用开发体验。它通过集成多种先进的技术和工具，帮助用户快速搭建、部署和维护 AI 应用，无需从零开始编写复杂的代码。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/AIspire/assets/AIspire_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.aispire.info\">AIspire</a> </td>\n        <td> AIspire是一个辅助AI学术写作的全能助手，从学术问题解答、学术灵感发现、文献管理、辅助阅读到全自动化AI辅助写作，让你的科研更精准、更高效。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"agent\">AI Agent 框架</span>\n\n<table>\n        <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/182288589?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/DMontgomery40/deepseek-mcp-server/blob/main/README.md\">DeepSeek MCP Server</a> </td>\n        <td> 用于 DeepSeek 高级语言模型的 Model Context Protocol 服务器</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://panda.fans/_assets/favicons/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/anda/README_cn.md\">Anda</a> </td>\n        <td> 一个专为 AI 智能体开发设计的 Rust 语言框架，致力于构建高度可组合、自主运行且具备永久记忆能力的 AI 智能体网络。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://yomo.run/yomo-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/yomo/README.md\">YoMo</a> </td>\n        <td> Stateful Serverless LLM Function Calling Framework with Strongly-typed Language Support </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://alice.fun/alice-logo.png\" alt=\"图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bob-robert-ai/bob/blob/main/alice/readme.md\">Alice</a> </td>\n        <td> 一个基于 ICP 的自主 AI 代理，利用 DeepSeek 等大型语言模型进行链上决策。Alice 结合实时数据分析和独特的个性，管理代币、挖掘 BOB 并参与生态系统治理。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/173022229\" alt=\"图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/APRO-com\">ATTPs</a> </td>\n        <td> 一个用于Agent之间可信通信的基础协议框架，基于DeepSeek的Agent，可以接入<a href=\"https://docs.apro.com/attps\">ATTPs</a>的SDK，获得注册Agent，发送可验证数据，获取可验证数据等功能，从而与其他平台的Agent进行可信通信。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/translate.js/assets/icon.png\" alt=\"图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/translate.js/README_cn.md\">translate.js</a> </td>\n        <td> 面向前端开发者的 AI i18n, 两行js实现html全自动翻译，几十语种一键切换，无需改动页面、无语言配置文件、支持几十个微调扩展指令、对SEO友好。并且开放标准文本翻译API接口</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/agentUniverse/assets/agentUniverse_logo_s.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/antgroup/agentUniverse\"> agentUniverse </a> </td>\n        <td> agentUniverse 是一个面向复杂业务场景设计的多智能体协作框架。其提供了快速易用的大模型智能体应用搭建能力，并着重于提供智能体协同调度、自主决策与动态反馈等机制，其源自蚂蚁集团在金融领域的真实业务实践沉淀。agentUniverse于2024年6月全面接入支持deepseek系列模型。  </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/BotSharp/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/SciSharp/BotSharp\"> BotSharp </a> </td>\n        <td> BotSharp 是一个开源的多智能体应用开发框架，从简单的聊天机器人，再到多智能体协作，以及复杂的任务如【Text To Sql】框架都提供了开箱即用的使用方法，可以快速的将大模型的能力接入到现有的业务系统中，并且内置知识库和会话管理功能等，框架使用DeepSeek V3的模型进行了详细的测试，得益于DeepSeek V3的性能，框架的表现不输其他的闭源的模型。 </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/eino/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/cloudwego/eino\"> Eino </a> </td>\n        <td> Eino（发音类似\"I know\"）旨在成为Go语言中最优秀的LLM应用开发框架。它借鉴了LangChain、LlamaIndex等开源社区优秀LLM框架的设计理念，同时吸收了前沿研究成果和实际应用经验，提供了一个更符合Go语言编程惯例的LLM应用开发框架，强调简洁性、可扩展性、可靠性和高效性。\n        </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"https://raw.githubusercontent.com/Tencent/Youtu-agent/924aeeb6c49ee524b8bb4de2642a3dc84b7b86b9/docs/assets/mascot.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> 是一个灵活、高性能的框架，用于构建、运行和评估自主智能体。除了在基准测试中名列前茅，该框架还提供了强大的智能体能力，采用开源模型即可实现例如数据分析、文件处理、深度研究等功能。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"data\">AI数据应用框架</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/user-attachments/assets/a327d72f-755f-4256-8a37-32a518a55df3\" alt=\"Icon\" width=\"96\" height=\"auto\" /> </td>\n        <td width=\"120\"> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/dbgpt/README_cn.md\"> DB-GPT </a> </td>\n        <td> DB-GPT是一个开源的AI原生数据应用开发框架(AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents)。\n目的是构建大模型领域的基础设施，通过开发多模型管理(SMMF)、Text2SQL效果优化、RAG框架以及优化、Multi-Agents框架协作、AWEL(智能体工作流编排)等多种技术能力，让围绕数据库构建大模型应用更简单，更方便。\n </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"rag\">RAG 框架</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/ragflow/README_cn.md\"> RAGFlow </a> </td>\n        <td> 一款基于深度文档理解构建的开源 RAG（Retrieval-Augmented Generation）引擎。RAGFlow 可以为各种规模的企业及个人提供一套精简的 RAG 工作流程，结合大语言模型（LLM）针对用户各类不同的复杂格式数据提供可靠的问答以及有理有据的引用。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/pingcap/tidb.ai/main/frontend/app/public/nextra/icon-dark.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/autoflow/README_cn.md\"> Autoflow </a> </td>\n        <td> <a href=\"https://github.com/pingcap/autoflow\">AutoFlow</a> 是一个开源的基于 GraphRAG 的知识库工具，构建于 <a href=\"https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community\">TiDB</a> Vector、LlamaIndex 和 DSPy 之上。提供类 Perplexity 的搜索页面，并可以嵌入简单的 JavaScript 代码片段，轻松将 Autoflow 的对话式搜索窗口集成到您的网站。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://assets.zilliz.com/Zilliz_Logo_Mark_White_20230223_041013_86057436cc.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zilliztech/deep-searcher\"> DeepSearcher </a> </td>\n        <td> DeepSearcher 结合强大的 LLM（DeepSeek、OpenAI 等）和向量数据库（Milvus 等），根据私有数据进行搜索、评估和推理，提供高度准确的答案和全面的报告。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/OpenSPG/openspg/089188f3e7b0392221f5a8e8f1a3629b6352a6f9/LOGO.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/OpenSPG/KAG/blob/master/README_cn.md\"> KAG </a> </td>\n        <td> KAG 是基于 <a href=\"https://github.com/OpenSPG/openspg\">OpenSPG</a> 引擎和大型语言模型的逻辑推理问答框架，用于构建垂直领域知识库的逻辑推理问答解决方案。KAG 可以有效克服传统 RAG 向量相似度计算的歧义性和 OpenIE 引入的 GraphRAG 的噪声问题。KAG 支持逻辑推理、多跳事实问答等。 </td>\n    </tr>\n   <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/TencentCloudADP/youtu-graphrag/refs/heads/main/assets/logo.png\" alt=\"Youtu-GraphRAG icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/TencentCloudADP/Youtu-GraphRAG\"> Youtu-GraphRAG </a> </td>\n        <td>Youtu-GraphRAG是腾讯优图实验室开源的图检索增强生成新范式，通过Schema连接两个智能体，在图构建、索引和检索上实现垂直统一和认知闭环，以领先的落地级图构建与推理能力推动GraphRAG进入新的阶段。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"fhe\">FHE (全同态加密) frameworks</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/fhe.mind-network/mind-network-log.png\" alt=\"Icon\" width=\"200\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\"> Mind FHE Rust SDK </a> </td>\n        <td> <p>一个开源 SDK，可使用**全同态加密（FHE）**对 AI 进行加密，实现代理共识。FHE被誉为密码学的圣杯，能够在无需解密的情况下直接对加密数据进行计算。借助FHE，代理在使用Deepseek时可以保护隐私，同时确保模型的完整性和计算结果的一致性，无需暴露任何数据。该SDK的<a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\">源代码</a>采用纯Rust实现，并可在<a href=\"https://crates.io/crates/mind_sdk_deepseek\">crates.io</a>获取</p> </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"solana\">Solana 框架</span>\n\n<table>\n    <tr>\n        <td style=\"background-color: black\"> <img src=\"docs/solana-agent-kit/assets/sendai-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sendaifun/solana-agent-kit\"> Solana Agent Kit </a> </td>\n        <td> 一个用于连接 AI 智能体到 Solana 协议的开源工具包。现在，任何使用 DeepSeek LLM 的智能体都可以自主执行 60+ 种 Solana 操作。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"sythetic\">综合数据管理</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/192579850?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/DataEval/dingo\"> Dingo </a> </td>\n        <td> 一个综合性的数据质量评估工具。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"im\">即时通讯插件</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/huixiangdou.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/huixiangdou/README_cn.md\">茴香豆<br/>（个人微信/飞书）</a> </td>\n        <td> 一个集成到个人微信群/飞书群的领域知识助手，专注解答问题不闲聊</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/RockChinQ/LangBot/blob/master/res/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/RockChinQ/LangBot\">LangBot<br/>（QQ, 企微, 飞书）</a> </td>\n        <td> 大模型原生即时通信机器人平台，适配 QQ / QQ频道 / 飞书 / OneBot / 企业微信（wecom） 等多种消息平台 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://nonebot.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/KomoriDev/nonebot-plugin-deepseek\">NoneBot<br/>（QQ, 飞书, Discord, TG, etc.）</a> </td>\n        <td> 基于 NoneBot 框架，支持智能对话与深度思考功能。适配 QQ / 飞书 / Discord, TG 等多种消息平台 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/197911947?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/AstrBotDevs/AstrBot/\">AstrBot<br/>（QQ, 微信, 企微, 飞书, TG, etc.）</a> </td>\n        <td> 支持大模型的多平台聊天机器人及开发框架。支持 RAG、长期记忆以及网页搜索等各种 LLM Agent 功能, 支持插件开发。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://oss.nekro.ai/nekro_agent_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/KroMiose/nekro-agent\">NekroAgent<br/>（QQ, Discord, BiliBiliLive, Minecraft etc.）</a> </td>\n        <td> Nekro Agent 是一个智能优雅的 AI 代理执行框架，其核心是通过强大灵活的提示词构建系统，引导 AI 生成代码并在安全的沙盒环境中执行。它通过原生的多平台适配器架构实现了强大的跨平台事件流处理能力，能够无缝支持 OneBot v11 (QQ)、Discord、Minecraft 和 B站直播(驱动VTB进行演出) 等多种主流平台。项目还拥有高度可扩展的插件系统、人设与插件共享生态，并支持在复杂的群聊多人交互场景中进行高效互动。目标是为用户和开发者提供极致高效、高自由度与易用性的开发友好型智能中枢。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.lanyingim.com/img/header/dock_lanying.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.lanyingim.com\">蓝莺IM<br/></a> </td>\n        <td> <b>AI Chatbot SDK 和云服务</b>，<br>包括一个跨平台（iOS、安卓、网页、PC、Linux等）的<a href=\"https://github.com/maxim-top/maxim-bistro\">聊天SDK</a>和一个AI Agent平台。<br/> 可嵌入应用APP，支持对接微信、公众号。<br/> 原生支持DeepSeek，无需单独配置API-Key。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"office\">Office插件</span>\n\n<table>\n     <tr>\n        <td> <img src=\"https://image.yoojober.com/users/2025-05/6836d9fdc8508.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatppt.cn/\">ChatPPT</a> </td>\n        <td>对话式AI创作PPT产品，国内最早（2023年3月4日上线）首款基于Chat对话式创作的AI PPT产品，目前支持web网页版、Office插件版（微软+WPS）、PC应用端（windows、mac、linux）、微信小程序等多版本，已经实现超过1800+指令服务，目前注册使用超过1500+万，且支持用户基于DeepSeek进行自由对话与文档对话两种模式，也满足用户配置自己的DeepSeek模型。</td>\n    </tr> \n  <tr>\n        <td> <img src=\"https://www.44886.com/view/img/bukeng.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.bukenghezi.com/\">不坑盒子</a> </td>\n        <td>一款支持Word、Excel、PPT三件套的Office插件（WPS三件套也支持），给Office增加300多功能</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.aippt.cn/_nuxt/logo_cn.eYEokZzA.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.aippt.cn/\">AiPPT</a> </td>\n        <td>AiPPT.com 超2000万用户选择的正版AiPPT。一句话，一分钟，一键生成 PPT。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.office-ai.cn/static/images/officeai/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.office-ai.cn/\">OfficeAI助手</a> </td>\n        <td>OfficeAI助手是一款免费的办公插件，在Office中提供AI问答、AI校对、AI排版、AI创作、AI数据处理等功能，可提高办公效率。兼容Microsoft Office和WPS Office。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"browser\">浏览器插件</span>\n\n<table>\n    <tr>\n        <td><img src=\"./docs/SelectTranslate/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://selecttranslate.com/\">精挑翻译</a></td>\n        <td>一款免费开放的 AI 翻译插件，拥有双语网页翻译、择优翻译（文案翻译）、输入翻译、PDF 翻译等创新实用的翻译功能。</td>\n    </tr>\n    <tr>\n        <td><img src=\"./docs/deepshare/assets/logo_200.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"./docs/deepshare/README_cn.md\">小智蜂</a></td>\n        <td> 小智蜂是免费免登录一键分享AI聊天的油猴插件,专门解决数千字AI问答发给朋友,导致其手机被刷屏,或长截图被压缩,打开模糊不清,不方便阅读的问题,满足用户将自己与AI智慧的结晶分享给他人的需求\n        </td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/OpenXLab/migo/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://chromewebstore.google.com/detail/cjapgnecnkblehipjghhegiccobeloka?utm_source=item-share-cb\">觅果</a></td>\n        <td> 提供全面的文本处理、信息检索与知识问答功能，灵活适配多种在线办公与科研场景（如飞书、arXiv、Overleaf 等），助力高效智能化工作流</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9d3f42b8-fcd0-47ab-8b06-1dd0554dd80e\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_translate/README_cn.md\"> 沉浸式翻译 </a> </td>\n        <td> 一款双语对照网页翻译插件，简洁，高效 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lh3.googleusercontent.com/K9i0qJb8phasC5wWf5tU68rhnfvX4swsE0hrhJP-WB3WV7MwE5KpMUIJvHKNHHRE6GKNIvIdTNSWoDMl_NggrmUsaw=s120\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_reading_guide/README_cn.md\"> 沉浸式导读 </a> </td>\n        <td> NO Sidebar!!! 沉浸式的 AI 网页摘要，提问... </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/8a301619-a3de-489b-81fd-69aaa7c1c561\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_box/README_cn.md\"> ChatGPT Box </a> </td>\n        <td> 将 LLM 作为私人助手，整合到你的浏览器中 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c3d9d100-247a-41cc-97c1-10b01ed25e70\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/hcfy/README_cn.md\"> 划词翻译 </a> </td>\n        <td> 整合了多家翻译 API 以及 LLM API 的浏览器翻译插件 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.eudic.net/web/trans/en_trans.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Lulu Translate/README_cn.md\"> 欧路翻译 </a> </td>\n        <td> 提供鼠标划词搜索、逐段对照翻译、PDF文献翻译功能。可以使用支持 DeepSeek AI、Bing、GPT、Google 等多种翻译引擎。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Bistutu/FluentRead/raw/refs/heads/main/public/icon/192.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fluent.thinkstu.com/\"> 流畅阅读 </a> </td>\n        <td> 一款革新性的浏览器开源翻译插件，让所有人都能够拥有基于母语般的阅读体验 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.ncurator.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.ncurator.com/\"> 馆长 </a> </td>\n        <td> 知识库AI问答助手 - 让AI帮助你整理与分析知识</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/oinzen/RSSFlow-doc/blob/main/docs/images/en/icon64.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://rssflow.oinchain.com\"> RssFlow </a> </td>\n        <td> 一款智能的RSS阅读器浏览器扩展，具有AI驱动的RSS摘要和多维度订阅视图功能。支持配置DeepSeek模型以增强内容理解能力。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.typral.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.typral.com/\"> Typral </a> </td>\n        <td> 超快的AI写作助手 - 让AI帮你快速优化日报，文章，文本等等... </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.trancy.org/assets/trancy_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.trancy.org/\"> Trancy </a> </td>\n        <td> 沉浸双语对照翻译、视频双语字幕、划句/划词翻译插件 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://ziziyi.com/svg/anything_copilot.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/baotlake/anything-copilot\"> Anything Copilot </a> </td>\n        <td> Anything Copilot 是一款可以让你在侧边栏无缝使用任意主流AI工具的浏览器插件 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Hedwi/deepchat/refs/heads/main/images/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chromewebstore.google.com/detail/deepchat-power-of-deepsee/femhcibnncinlabdboehojdhfcihpkpl?hl=en\"> DeepChat </a> </td>\n        <td>一款Chrome扩展程序，允许用户在任何网站上通过打开侧边栏与DeepSeek聊天。此外，它还在任何网站上选中的文本下方提供一个浮动菜单，使用户能够生成文本摘要、检查语法问题和翻译内容。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"http://cdn.docky.ai/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/docky-ai/README_cn.md\"> Docky AI </a> </td>\n        <td>Docky AI 是一款功能强大的浏览器插件，允许您通过侧边栏与多个 AI 模型进行实时对话。它支持多模型同时交流，并能协助您阅读网页、写作、翻译和创作图片</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/refinereader/assets/refinereader-128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://refinereader.cuihuaer.com\"> Refine Reader </a> </td>\n        <td> 一款基于 AI （DeepSeek、OpenAI等） 的智能阅读助手，致力于帮助用户快速理解和提炼文章精华，支持阅读互动。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://readfrog.mengxi.work/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://readfrog.mengxi.work\"> 🐸 陪读蛙 </a></td>\n        <td>借助 AI 深度翻译并理解任何网页。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Rearview/assets/favicon.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"./docs/Rearview/README_cn.md\"> RearView </a> </td>\n        <td>Rearview 是一款浏览器历史管理扩展，支持对历史浏览内容的全文搜索，并将浏览历史转换为可对话的知识库。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.chatgot.io/chat/assets/imgs/logo@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatgot.io/\"> ChatGOT </a> </td>\n        <td> 一个免费的AI聊天机器人助手，用于提高生产力 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"vscode\">VS Code 插件</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/continuedev/continue/blob/main/docs/static/img/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README_cn.md\"> Continue </a> </td>\n        <td> 开源 IDE 插件，使用 LLM 做你的编程助手 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/assets/favicon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/README.md\"> Cline </a> </td>\n        <td> Cline 是一款能够使用您的 CLI 和编辑器的 AI 助手 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Sitoi/ai-commit/refs/heads/main/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Sitoi/ai-commit/blob/main/README.md\"> AI Commit </a> </td>\n        <td> 使用 AI 生成 git commit message 的 VS Code 插件 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/titusTong/seekCodeCopilot/blob/main/assets/SeekCodeCopilotLogo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/titusTong/seekCodeCopilot/blob/main/README.md\"> SeekCode Copilot </a> </td>\n        <td> vscode智能编码助手，支持配置本地部署的DeepSeek模型 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/intellism/vscode-comment-translate/blob/master/doc/image/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/intellism/vscode-comment-translate/blob/master/doc/README_ZH.md\"> Comment Translation </a> </td>\n        <td> 这款扩展程序能够帮助开发者翻译代码中的注释、字符串、代码提示、错误信息以及变量名。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/AITK/assets/AIToolkit.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://code.visualstudio.com/docs/intelligentapps/overview\"> AI Toolkit </a> </td>\n        <td> Visual Studio Code 的 AI Toolkit 是一个综合性扩展，为开发人员和 AI 工程师提供使用生成式 AI 模型构建、测试和部署智能应用程序的能力。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/joygqz/commit-genie/refs/heads/main/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=joygqz.commit-genie\"> Commit Genie </a> </td>\n        <td> 适用于 VS Code 的 AI 代码审查和提交消息生成器。自动审查您的代码更改并生成有意义的标准提交消息。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/JohnnyZ93/oai-compatible-copilot/blob/main/assets/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/oai-compatible-copilot/README_cn.md\"> OAI Compatible Provider for Copilot </a> </td>\n        <td> 开源的 VS Code 扩展，可在 GitHub Copilot 中使用 OpenAI 兼容的推理提供商。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"neovim\">neovim 插件</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/c316f70a-0a3c-4a32-b148-4df15e609acc\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/avante.nvim/README_cn.md\"> avante.nvim </a> </td>\n        <td> 开源 IDE 插件，使用 LLM 做你的编程助手 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/llm.nvim/README.md\"> llm.nvim </a> </td>\n        <td> 免费的大语言模型插件，让你在Neovim中与大模型交互，支持任意一款大模型，比如DeepSeek，GPT，GLM，kimi或者本地运行的大模型(比如ollama) </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/minuet-ai.nvim/README_cn.md\"> minuet-ai.nvim </a> </td>\n        <td> Minuet 提供实时代码补全功能，支持多个主流大语言模型，包括 DeepSeek、OpenAI、Gemini、Claude、Ollama、Codestral 等。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/codecompanion.nvim/README.md\"> codecompanion.nvim </a> </td>\n        <td> AI 驱动的编码，在 Neovim 中无缝集成。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"jetbrains\">JetBrains 插件</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/a18792721831/studyplugin/535b9cab69da0f97b42dcaebb00bb0d4ed15c8a6/translate/src/main/resources/META-INF/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/18336-chinese-english-translate\">Chinese-English Translate</a> </td>\n        <td> 集成了多家国内翻译和AI厂商，将中文翻译到英文的插件。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/24851/659002/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/24851-ai-git-commit\">AI Git Commit</a> </td>\n        <td> 使用AI生成git commit message的插件。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/YiiGuxing/TranslationPlugin/blob/master/pluginIcon.svg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://intellij-translation.yiiguxing.top\">IntelliJ Translation Plugin</a> </td>\n        <td> IntelliJ Translation Plugin 是一个适用于基于 IntelliJ 的 IDE 的翻译插件，它集成了包括 OpenAI 翻译（兼容 DeepSeek，Doubao，Ollama，……）在内的众多翻译服务，让您能够随时在 IDE 中直接翻译代码中的任何文本，如代码注释和代码文档等。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"codeeditor\">AI Code编辑器</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://global.discourse-cdn.com/flex020/uploads/cursor1/original/2X/a/a4f78589d63edd61a2843306f8e11bad9590f0ca.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.cursor.com/\"> Cursor </a> </td>\n        <td> 基于VS Code进行扩展的AI Code编辑器 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://exafunction.github.io/public/images/windsurf/windsurf-app-icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://codeium.com/windsurf\"> WindSurf </a> </td>\n        <td> 另一个基于VS Code的AI Code编辑器，由Codeium出品 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/wusigram/assets/logo-512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wusigram/README_cn.md\"> 无思微程序 </a> </td>\n        <td> 移动端AI编程和运行工具，DeepSeek编程搭档 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"security\">安全</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/tencent/hunyuan.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tencent/AI-Infra-Guard\"> AI-Infra-Guard </a> </td>\n        <td> 腾讯混元安全-AI基础设施安全评估工具，发现和检测AI系统中的潜在安全风险。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n###  <span id=\"others\">其它</span>\n\n<table>\n    <tr>\n        <td></td>\n        <td> <a href=\"https://github.com/lunary-ai/abso/blob/main/README.md\"> Abso </a></td>\n        <td> TypeScript SDK 使用 OpenAI 格式与任何 LLM 提供商进行交互。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.imgur.com/IsQYInJ.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/djcopley/ShellOracle/\"> ShellOracle </a> </td>\n        <td> 一种用于智能 shell 命令生成的终端工具。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/fatwang2/siri-ultra\"> Siri Ultra </a> </td>\n        <td> GitHub 千星开源项目，支持联网、多轮对话，支持 DeepSeek 系列模型</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c1e47b01-1766-4f7e-bfe6-ab3cb3991c30\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/tree/main/docs/siri_deepseek_shortcut\"> 深度求索（快捷指令） </a> </td>\n        <td> 使用 DeepSeek API 增强Siri能力的快捷指令 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/n8n-io/n8n/blob/master/assets/n8n-logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/rubickecho/n8n-deepseek\"> n8n-nodes-deepseek </a> </td>\n        <td> 一个 N8N 的社区节点，支持直接使用 DeepSeek API 集成到工作流中 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.promptfoo.dev/img/logo-panda.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/promptfoo/README.md\"> promptfoo </a> </td>\n        <td> 测试和评估LLM提示，包括DeepSeek模型。比较不同的LLM提供商，捕获回归，并评估响应。 </td>\n    </tr>\n    <tr>\n        <td></td>\n        <td> <a href=\"https://github.com/AndersonBY/deepseek-tokenizer\"> deepseek-tokenizer </a> </td>\n        <td> 一个高效的轻量级tokenization库，仅依赖`tokenizers`库，不依赖`transformers`等重量级依赖。 </td>\n    </tr>\n    <tr>\n        <td></td>\n        <td> <a href=\"https://github.com/hustcer/deepseek-review\"> deepseek-review </a> </td>\n        <td> 🚀 使用 DeepSeek 进行代码审核，支持 GitHub Action 和本地 🚀 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/suqicloud/wp-ai-chat/raw/main/ic_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/suqicloud/wp-ai-chat\"> WordPress ai助手 </a> </td>\n        <td> 对接DeepSeek API用于WordPress站点的AI对话助手、AI文章生成、AI文章总结插件。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/ComfyUI-Copilot/assets/logo 2.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/AIDC-AI/ComfyUI-Copilot\"> ComfyUI-Copilot </a> </td>\n        <td> 基于Comfy-UI框架构建的智能助手，通过自然语言交互简化和增强AI算法调试和部署过程。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Optima-CityU/llm4ad/blob/main/assets/figs/logo_short.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> 是一个开源、简洁、模块化的基于大模型的自动算法设计平台，使用DeepSeek API进行算法设计。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/yincongcyincong/telegram-deepseek-bot/blob/main/static/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> 是一个集成deepseek-ai能力的telegram机器人。 </td>\n    </tr>\n    <tr>\n        <td></td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> 是一个基于人工智能的命令行工具，支持多后端大语言模型，能够生成上下文感知的 Shell 命令。它兼容 Shell 专用语法、提供只读系统工具支持，并允许接入自定义推理端点。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.godtierprompts.com/logo.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a> 是一个由社区驱动的排行榜，让最优秀的提示词脱颖而出。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/89342560?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Jeff2Ma/AlfredWorkflow-DeepSeek\">DeepSeek Alfred WorkFlow</a> </td>\n        <td> 在 Mac Alfred App 中快速调用 DeekSeek 的 workflow。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.imgur.com/zDgW8wB.png\" width=\"64\" alt=\"Icon\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/skypilot-org/skypilot\">SkyPilot</a> </td>\n        <td> <a href=\"https://github.com/skypilot-org/skypilot/tree/master/llm/deepseek-r1\">在任何云基础设施上部署DeepSeek模型</a>（Kubernetes、AWS、Azure、GCP或GPU云）。支持多区域、多集群和多云的自动扩展。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/cbf6193b-fd66-4b88-bcf7-98699becf046\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sally-suite/open-office-copilot\">Open Office Copilot</a> </td>\n        <td> Open Office Copilot 是一个开源的 Office 助手，支持 Microsoft Office 和 Google Workspace，基于 AI-Agent。它可以帮助你在 Word 中写作、在 PowerPoint 中生成幻灯片、在 Excel 中分析数据、在 Outlook 里帮你生成邮件等，现在已经集成了 DeepSeek。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目录\">^ 返回目录 ^</a></p>\n\n### Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=deepseek-ai/awesome-deepseek-integration&type=Date)](https://star-history.com/#deepseek-ai/awesome-deepseek-integration&Date)\n"
  },
  {
    "path": "README_es.md",
    "content": "<div align=\"center\">\n\n<p align=\"center\">\n<img width=\"1000px\" alt=\"Integraciones Asombrosas de DeepSeek\" src=\"docs/Awesome DeepSeek Integrations.png\">\n</p>\n\n# Integraciones Asombrosas de DeepSeek ![Destacado](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)\n\nIntegra la API de DeepSeek en softwares populares. Accede a la [Plataforma Abierta de DeepSeek](https://platform.deepseek.com/) para obtener una clave API.\n\n[English](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README.md)/[简体中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_cn.md)/[繁體中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_zh_tw.md)/[日本語](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_ja.md)/Español\n\n</div>\n\n</br>\n</br>\n\n## Tabla de contenidos\n\n- [Integraciones Asombrosas de DeepSeek ](#integraciones-asombrosas-de-deepseek-)\n  - [Tabla de contenidos](#tabla-de-contenidos)\n  - [Lista de proyectos](#lista-de-proyectos)\n    - [Aplicaciones](#aplicaciones)\n    - [Marcos de agentes de IA](#marcos-de-agentes-de-ia)\n    - [Marcos de aplicaciones de datos de IA](#marcos-de-aplicaciones-de-datos-de-ia)\n    - [Marcos RAG](#marcos-rag)\n    - [Marcos FHE (Cifrado Homomórfico Completo)](#marcos-fhe-cifrado-homomórfico-completo)\n    - [Marcos Solana](#marcos-solana)\n    - [Curación de datos sintéticos](#curación-de-datos-sintéticos)\n    - [Plugins de aplicaciones de mensajería instantánea](#plugins-de-aplicaciones-de-mensajería-instantánea)\n    - [Extensiones para Navegadores](#extensiones-para-navegadores)\n    - [Extensiones para VS Code](#extensiones-para-vs-code)\n    - [Extensiones de Visual Studio](#extensiones-de-visual-studio)\n    - [Extensiones de Neovim](#extensiones-de-neovim)\n    - [Extensiones de JetBrains](#extensiones-de-jetbrains)\n    - [Bots de Discord](#bots-de-discord)\n    - [Editor de Código Nativo con IA](#editor-de-código-nativo-con-ia)\n    - [Emacs](#emacs)\n    - [Seguridad](#seguridad)\n    - [Otros](#otros)\n    - [Historial de Estrellas](#historial-de-estrellas)\n\n## Lista de proyectos\n\n###  <span id=\"applications\">Aplicaciones</span>\n\n<table>\n    <tr>\n        <td><img src=\"docs/operit/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/AAswordman/Operit\">Operit AI</a></td>\n        <td>Un asistente de IA de integración de sistema de código abierto para la plataforma Android, que admite el uso casi completo de mcp y es altamente compatible con el sistema Android. El software ofrece alta personalización y bajo umbral de aprendizaje, con herramientas incorporadas para operaciones de archivos, búsquedas, clics automáticos, conversión de formatos y una página web API de DeepSeek integrada.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/eechat/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Lucassssss/eechat\">eechat</a></td>\n        <td>Una herramienta simple y fácil de usar para el despliegue local de modelos de lenguaje grandes, que admite el despliegue local privado de modelos de código abierto como DeepSeek-R1, DLlama 3, Phi-4, Mistral, Gemma 3, etc., y también es compatible con llamadas a API de LLM remotos.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/aingdesk/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/aingdesk/AingDesk\">AingDesk</a></td>\n        <td>Implementa modelos de IA en tu computadora con un solo clic, operación visualizada, interfaz de chat incorporada y elegante, se puede compartir en línea para uso compartido con otros, compatible con modelos como DeepSeek, búsqueda en la web y API de terceros.</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/dingtalk/assets/dingtalk_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.dingtalk.com/\">DingTalk</a></td>\n        <td>El Asistente de IA de DingTalk integra múltiples funciones de productos de IA de la plataforma DingTalk para asistir de manera inteligente en los flujos de trabajo diarios de las empresas. El Asistente de IA de DingTalk cuenta con diversas capacidades inteligentes, incluyendo, entre otras, comunicación inteligente, colaboración inteligente y gestión inteligente. A través de estas funciones, el asistente de IA puede resumir puntos clave dentro de la empresa, generar actas de reuniones y enviar a los usuarios recordatorios de tareas laborales y horarios relevantes. Además, el Asistente de IA de DingTalk puede utilizar su base de conocimientos para responder de manera inteligente a preguntas frecuentes de los empleados sobre los procesos administrativos de la empresa, las políticas de recursos humanos y otros temas relacionados.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://chatdoc.com/chatdoc/chatdoc.webp\" alt=\"Icono\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://chatdoc.com\">ChatDOC</a></td>\n        <td>ChatDOC es una herramienta de lectura de documentos basada en IA, equipada con sólidas funciones de trazabilidad, asegurando que la fuente de cada información sea clara y verificable, ayudándote a comprender eficientemente el núcleo de tus documentos.</td>\n    </tr>\n    <tr>\n<td> <img src=\"./docs/SwiftChat/assets/favicon.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n<td> <a href=\"docs/SwiftChat/README.md\">SwiftChat</a></td>\n<td> <a href=\"https://github.com/aws-samples/swift-chat\">SwiftChat</a> es una aplicación de chat con IA ultrarrápida y multiplataforma construida con React Native. Ofrece rendimiento nativo en Android, iOS, iPad, tabletas Android y macOS. Incluye funciones como chat en tiempo real, soporte enriquecido de Markdown (tablas, bloques de código, LaTeX), generación de imágenes con IA, indicaciones personalizables del sistema, cambio rápido de modelo y capacidades multimodales. Compatible con múltiples proveedores de IA como DeepSeek, Amazon Bedrock, Ollama y modelos compatibles con OpenAI, con una interfaz limpia y alto rendimiento.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://4everlogo.4everland.store/logo/logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/4EVERChat/README.md\">4EVERChat</a></td>\n        <td><a href=\"https://chat.4everland.org/\">4EVERChat</a> es una plataforma de selección de modelos inteligentes que integra cientos de LLMs, permitiendo la comparación en tiempo real del rendimiento de los modelos. Aprovechando el endpoint unificado de API de <a href=\"https://www.4everland.org/\">4EVERLAND</a> AI RPC, logra cambios de modelo sin costo y selecciona automáticamente combinaciones con respuestas rápidas y costos bajos.</td>\n    </tr>\n    <tr>\n        <td><img src=\"./docs/xhai_browser/assets/logo_512.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"./docs/xhai_browser/README.md\">xhai Browser</a></td>\n        <td>xhai Browser es un navegador de gestión de escritorio y AI para Android, donde DeepSeek es el motor de diálogo predeterminado impulsado por IA. Ofrece un rendimiento excepcional (0.2 segundos para iniciar), tamaño reducido (apk de 3M), sin anuncios, bloqueo de anuncios ultrarrápido, clasificación de pantallas, navegación por pantalla, caja de búsqueda múltiple y más.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://i.imgur.com/FkbmMVG.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://intellibar.app/\">IntelliBar</a></td>\n        <td>IntelliBar es un asistente elegante para Mac que te permite usar modelos avanzados como DeepSeek R1 con cualquier aplicación en tu Mac, por ejemplo: editar correos electrónicos en tu aplicación de correo o resumir artículos en tu navegador.</td>\n    </tr>\n    <tr>\n        <td><img src=\"./docs/gptbots/gptbots.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td><a href=\"https://www.gptbots.ai/es_ES/docs\">GPTBots</a></td>\n        <td><a href=\"https://www.gptbots.ai/es_ES/\">GPTBots</a> es una plataforma de construcción de agentes de IA sin necesidad de programación que integra importantes LLMs internacionales, incluyendo DeepSeek. Ofrece módulos para almacenamiento/recuperación de conocimiento basado en RAG, personalización/llamada de herramientas y orquestación de flujos de trabajo. Además, permite integrar agentes en múltiples plataformas principales (como WhatsApp, Telegram, etc.), proporcionando soluciones integrales de IA para empresas y ayudándolas a destacarse en la era de la IA.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/build/icon.png?raw=true\" alt=\"Icono\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/README.md\">DeepChat</a></td>\n        <td>DeepChat es un asistente inteligente de escritorio completamente gratuito, con un potente modelo grande DeepSeek, que admite conversaciones de múltiples rondas, búsqueda en internet, carga de archivos, bases de conocimiento y más.</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"https://avatars.githubusercontent.com/u/171659527?s=400&u=39906ab3b6e2066f83046096a66a77fb3f8bb836&v=4\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/quantalogic/quantalogic\">Quantalogic</a> </td>\n        <td> QuantaLogic es un marco ReAct (Razonamiento y Acción) para construir agentes de IA avanzados. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/224d547a-6fbc-47c8-859f-aa14813e2b0f\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatbox/README.md\">Chatbox</a> </td>\n        <td> Chatbox es un cliente de escritorio para múltiples modelos LLM de vanguardia, disponible en Windows, Mac y Linux. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/bb65404c-f867-42d8-ae2b-281fe953ab54\" alt=\"Icono\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_next_web/README.md\"> ChatGPT-Next-Web </a> </td>\n        <td> ChatGPT Next Web es una interfaz web multiplataforma para ChatGPT, con soporte para GPT3, GPT4 y Gemini Pro. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/Casibase/assets/casibase.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://casibase.org/es/docs/category/beginner-guide/\">Casibase</a></td>\n        <td> <a href=\"https://casibase.org\">Casibase</a> es un sistema de base de conocimientos y diálogo de IA de código abierto que combina las últimas tecnologías RAG, funcionalidades SSO y soporta varios modelos de IA principales. Su objetivo es proporcionar a empresas y desarrolladores una plataforma potente y flexible para la gestión de conocimientos y diálogo inteligente. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Coco AI/assets/favicon.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Coco AI/README.md\">Coco AI</a></td>\n        <td> <a href=\"https://coco.rs\">Coco AI</a> es una herramienta de búsqueda y productividad unificada, completamente de código abierto y multiplataforma, que conecta y busca en diversas fuentes de datos, incluyendo aplicaciones, archivos, Google Drive, Notion, Yuque, Hugo y más, tanto locales como en la nube. Al integrarse con modelos grandes como DeepSeek, Coco AI permite una gestión inteligente del conocimiento personal, destacando la privacidad y admitiendo despliegues privados, ayudando a los usuarios a acceder rápidamente a su información de manera inteligente.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/liubai/assets/liubai-logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/liubai/README.md\">Liubai</a> </td>\n        <td> Liubai permite que DeepSeek te ayude a gestionar tus notas, tareas, calendarios y listas de pendientes directamente en WeChat. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1ac9791b-87f7-41d9-9282-a70698344e1d\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/pal/README.md\"> Pal - Cliente de Chat AI<br/>(iOS, ipadOS) </a> </td>\n        <td> Pal es un espacio de chat personalizado en iOS. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.librechat.ai/librechat.svg\" alt=\"LibreChat\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/deepseek\">LibreChat</a> </td>\n        <td> LibreChat es una aplicación de código abierto personalizable que integra DeepSeek para interacciones mejoradas con IA. </td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/longevity-genie/chat-ui/11c6647c83f9d2de21180b552474ac5ffcf53980/static/geneticsgenie/icon-128x128.png\" alt=\"Icono\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/longevity-genie/just-chat\">Just-Chat</a> </td>\n        <td> ¡Crea tu agente LLM y chatea con él de forma simple y rápida!</td>\n     </tr>\n    <tr>\n        <td> <img src=\"https://www.papersgpt.com/images/logo/favicon.ico\" alt=\"PapersGPT\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/papersgpt/papersgpt-for-zotero\">PapersGPT</a> </td>\n        <td> PapersGPT es un plugin para Zotero que se integra perfectamente con DeepSeek y otros modelos de IA para leer rápidamente artículos en Zotero. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/rss-translator/RSS-Translator/main/core/static/favicon.ico\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/rss_translator/README.md\"> RSS Translator </a> </td>\n        <td> ¡Traduce feeds RSS a tu idioma! </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://relingo.net/assets/images/relingo-logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://relingo.net\"> Relingo </a> </td>\n        <td> ¡Construye y domina vocabulario mientras navegas por sitios web y ves YouTube! </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/enconvo/README.md\"> Enconvo </a> </td>\n        <td> Enconvo es el lanzador de la era de la IA, el punto de entrada para todas las funciones de IA y un asistente inteligente reflexivo.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/kangfenmao/cherry-studio/blob/main/src/renderer/src/assets/images/logo.png?raw=true\" alt=\"Icono\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cherrystudio/README.md\">Cherry Studio</a></td>\n        <td>Un asistente de IA de escritorio poderoso para productores</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://tomemo.top/images/logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/tomemo/README.md\"> ToMemo (iOS, ipadOS) </a> </td>\n        <td> Una aplicación de iOS que combina un libro de frases, registro del portapapeles y teclado, con modelado macro de IA integrado para una salida rápida desde el teclado.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/buxuku/video-subtitle-master/refs/heads/main/resources/icon.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/buxuku/video-subtitle-master\">Video Subtitle Master</a></td>\n        <td> Genera subtítulos para videos en lote, con la capacidad de traducir subtítulos a otros idiomas. Es una herramienta del lado del cliente que admite plataformas Mac y Windows, e integra múltiples servicios de traducción como Baidu, Volcengine, DeepLx, OpenAI, DeepSeek y Ollama.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/dist/assets/chatworm-72x72.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/README.md\">Chatworm</a> </td>\n        <td> Chatworm es una aplicación web para múltiples modelos LLM de vanguardia, de código abierto y también disponible en Android. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/tisfeng/ImageBed/main/uPic/icon_512x512@2x.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tisfeng/Easydict\">Easydict</a></td>\n        <td> Easydict es una aplicación de diccionario de traducción para macOS, sencilla y fácil de usar, que permite buscar palabras o traducir texto de manera elegante. Admite la llamada de APIs de modelos de lenguaje grande para traducción.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.raycast.com/favicon-production.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/raycast/README.md\">Raycast</a></td>\n        <td> <a href=\"https://raycast.com/?via=ViGeng\">Raycast</a> es una herramienta de productividad para macOS que te permite controlar tus herramientas con unos pocos atajos de teclado. Admite varias extensiones, incluyendo DeepSeek AI.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://niceprompt.app/favicon.ico\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td> <td> <a href=\"https://niceprompt.app\">Nice Prompt</a></td> <td> <a href=\"https://niceprompt.app\">Nice Prompt</a> Organiza, comparte y utiliza tus indicaciones en tu editor de código, con Cursor y VSCode.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/193405629?s=200&v=4\" alt=\"PHP Client\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-php-client/blob/master/README.md\">PHP Client</a> </td>\n        <td> Deepseek PHP Client es una biblioteca cliente PHP robusta y orientada a la comunidad para una integración perfecta con la API de Deepseek. </td>\n    </tr>\n        <tr>\n  <td>\n    <img\n      src=\"https://github.com/tornikegomareli/DeepSwiftSeek/blob/main/logo.webp\"\n      alt=\"DeepSwiftSeek Logo\"\n      width=\"64\"\n      height=\"auto\"\n    />\n  </td>\n  <td>\n    <a href=\"https://github.com/tornikegomareli/DeepSwiftSeek/blob/main/README.md\">DeepSwiftSeek</a>\n  </td>\n  <td>\n    DeepSwiftSeek es una biblioteca cliente Swift ligera pero poderosa, con una buena integración con la API de DeepSeek.\n    Proporciona concurrencia Swift fácil de usar para chat, streaming, FIM (Fill-in-the-Middle) completions y más.\n  </td>\n</tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/958072?s=200&v=4\" alt=\"Laravel Integration\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-laravel/blob/master/README.md\">Laravel Integration</a> </td>\n        <td> Laravel wrapper para el cliente PHP de Deepseek, para una integración perfecta de la API de Deepseek con aplicaciones Laravel.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/zotero/assets/zotero-icon.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/zotero/README_cn.md\">Zotero</a></td>\n        <td> <a href=\"https://www.zotero.org\">Zotero</a> es una herramienta gratuita y fácil de usar para ayudarte a recopilar, organizar, anotar, citar y compartir investigaciones. Puede usar Deepseek como servicio de traducción.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://b3log.org/images/brand/siyuan-128.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/SiYuan/README.md\">SiYuan</a> </td>\n        <td> SiYuan es un sistema de gestión de conocimiento personal centrado en la privacidad que admite un uso completamente offline, así como sincronización de datos cifrada de extremo a extremo.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/ArvinLovegood/go-stock/raw/master/build/appicon.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/ArvinLovegood/go-stock/blob/master/README.md\">go-stock</a> </td>\n        <td>go-stock es un visor de datos de acciones chinas construido por Wails con NativeUI y potenciado por LLM.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/102771702?s=200&v=4\" alt=\"Wordware\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wordware/README.md\">Wordware</a> </td>\n        <td><a href=\"https://www.wordware.ai/\">Wordware</a> es un kit de herramientas que permite a cualquiera construir, iterar y desplegar su pila de IA solo con lenguaje natural.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/xRJ6vNo9mUYeVNxt0KITXCXEuSk.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/langgenius/dify/\">Dify</a> </td>\n        <td> <a href=\"https://dify.ai/\">Dify</a> es una plataforma de desarrollo de aplicaciones LLM que admite modelos DeepSeek para crear asistentes, flujos de trabajo, generadores de texto y más. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/enricoros/big-AGI/refs/heads/v2-dev/public/favicon.ico\" alt=\"Big-AGI\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/enricoros/big-AGI/blob/v2-dev/README.md\">Big-AGI</a> </td>\n        <td><a href=\"https://big-agi.com/\">Big-AGI</a> es una suite de IA revolucionaria diseñada para democratizar el acceso a inteligencia artificial avanzada para todos.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/LiberSonora/LiberSonora/blob/main/assets/avatar.jpeg?raw=true\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/LiberSonora/LiberSonora/blob/main/README_en.md\">LiberSonora</a> </td>\n        <td> LiberSonora, que significa \"Voz de la Libertad\", es un kit de herramientas de audiolibros robusto y de código abierto impulsado por IA que incluye características como extracción inteligente de subtítulos, generación de títulos con IA, traducción multilingüe, con soporte para aceleración GPU y procesamiento por lotes sin conexión.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ripperhe/Bob/master/docs/_media/icon_128.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a></td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a> es una herramienta de traducción y OCR para macOS lista para usar en cualquier aplicación, ¡directamente desde la caja!</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://agenticflow.ai/favicon.ico\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a> es una plataforma sin necesidad de programación donde los especialistas en marketing construyen flujos de trabajo de IA agentica para la automatización de salida al mercado, impulsados por cientos de aplicaciones cotidianas como herramientas para tus agentes de IA.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/STranslate/STranslate/refs/heads/main/images/favicon.svg\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a></td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a>（Windows） es una herramienta de traducción OCR lista para usar desarrollada por WPF </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/5e16beb0-993e-47bf-807e-7c8804b313a2\" alt=\"Asp Client\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Anwar-alhitar/Deepseek.Asp.Client/blob/master/README.md\">ASP Client</a> </td>\n        <td><a href=\"https://github.com/Anwar-alhitar/Deepseek.Asp.Client/blob/master/README.md\">Deepseek.ASPClient</a> es un wrapper ligero para ASP.NET diseñado para simplificar el procesamiento de texto impulsado por IA en aplicaciones .NET.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.gptaiflow.tech/logo.png\" alt=\"gpt-ai-flow-logo\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.gptaiflow.tech/docs/product/api-keys-setup#setup-deepseek-api-keys\">GPT AI Flow</a></td>\n        <td>\n            La herramienta definitiva de productividad construida por ingenieros para entusiastas de la eficiencia (ellos mismos): <a href=\"https://www.gptaiflow.tech/\">GPT AI Flow</a>\n            <ul>\n                <li>`Shift+Alt+Space` Activa el hub inteligente de escritorio</li>\n                <li>Almacenamiento cifrado local</li>\n                <li>Motor de instrucciones personalizable</li>\n                <li>Llamadas bajo demanda sin suscripción agrupada</li>\n            </ul>\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/b09f17a8-936d-4dac-8b24-1682d52c9a3c\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/alecm20/story-flicks\">Story-Flicks</a></td>\n        <td>¡Con solo una oración, puedes generar rápidamente videos cortos de historias en alta definición, compatibles con modelos como DeepSeek!</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://prompt.16x.engineer/favicon.ico\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/16x_prompt/README.md\">16x Prompt</a> </td>\n        <td> <a href=\"https://prompt.16x.engineer/\">16x Prompt</a> es una herramienta de codificación con IA que incluye gestión de contexto. Ayuda a los desarrolladores a gestionar el contexto del código fuente y a crear indicaciones para tareas complejas en bases de código existentes.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/assets/favicon1.png?raw=true\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/README.md\"> Alpha Pai </a> </td>\n        <td> Asistente de Investigación AI / El portal de información financiera de próxima generación impulsado por IA.<br>Proxy para inversores para asistir a reuniones y tomar notas, así como proporcionar servicios de búsqueda y preguntas y respuestas para información financiera y análisis cuantitativo para investigación de inversiones.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://docs.xark-argo.com/img/logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.xark-argo.com\">argo</a> </td>\n        <td>Descarga y ejecuta localmente modelos Ollama y Huggingface con RAG en Mac/Windows/Linux. También admite API de LLM.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.petercat.ai/images/favicon.ico\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.petercat.ai\">PeterCat</a> </td>\n        <td> Un sistema de configuración de agentes de preguntas y respuestas conversacionales, soluciones de despliegue autohospedadas y un SDK de aplicación todo en uno conveniente, que permite crear bots inteligentes de preguntas y respuestas para tus repositorios de GitHub.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/labring/FastGPT/refs/heads/main/.github/imgs/logo.svg\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fastgpt.cn/en\">FastGPT</a> </td>\n        <td>\n            FastGPT es una plataforma de base de conocimientos de IA de código abierto construida sobre modelos de lenguaje grande (LLMs), compatible con varios modelos, incluyendo DeepSeek y OpenAI. Proporcionamos capacidades listas para usar para procesamiento de datos, invocación de modelos, recuperación RAG y orquestación visual de flujos de trabajo de IA, permitiéndote construir aplicaciones de IA sofisticadas sin esfuerzo.\n        </td>\n   </tr>\n   <tr>\n        <td> <img src=\"./docs/ruzhiai_note/assets/play_store_512.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/ruzhiai_note/README.md\">RuZhi AI Notes</a> </td>\n        <td>RuZhi AI Notes es una herramienta de gestión de conocimiento inteligente impulsada por IA, que proporciona servicios de gestión y aplicación de conocimiento todo en uno, incluyendo búsqueda y exploración con IA, conversión de resultados de IA a notas, gestión y organización de notas, presentación y compartición de conocimiento. Integrado con el modelo DeepSeek para proporcionar salidas más estables y de mayor calidad.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cdn.link-ai.tech/doc/CoW%20logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zhayujie/chatgpt-on-wechat\">Chatgpt-on-Wechat</a> </td>\n        <td> Chatgpt-on-Wechat(CoW) es un marco de chatbot flexible que admite la integración perfecta de múltiples LLMs, incluyendo DeepSeek, OpenAI, Claude, Qwen y otros, en plataformas comúnmente utilizadas o software de oficina como WeChat Official Accounts, WeCom, Feishu, DingTalk y sitios web. También admite una amplia gama de plugins personalizados. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://athenalab.ai/assets/favicon/favicon.svg\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://athenalab.ai/\">Athena</a> </td>\n        <td>La primera IA general autónoma del mundo con arquitectura cognitiva avanzada y capacidades de razonamiento humano, diseñada para abordar desafíos complejos del mundo real.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://maxkb.cn/images/favicon.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/1Panel-dev/MaxKB\">MaxKB</a> </td>\n        <td> <a href=\"https://maxkb.cn/\">MaxKB</a> es un chatbot RAG flexible y listo para usar. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/TigerGPT/assets/logo.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ttm.financial/gpt\">TigerGPT</a> </td>\n        <td>TigerGPT es el primer asistente de inversión financiera basado en IA de su tipo, desarrollado por Tiger Group. TigerGPT tiene como objetivo proporcionar soporte para la toma de decisiones de inversión inteligente para los inversores. El 18 de febrero de 2025, TigerGPT integró oficialmente el modelo DeepSeek-R1 para proporcionar a los usuarios servicios de preguntas y respuestas en línea que admiten razonamiento profundo. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/HIX.AI/assets/logo.svg\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://hix.ai\">HIX.AI</a> </td>\n        <td>Prueba DeepSeek gratis y disfruta de chat ilimitado con IA en HIX.AI. Usa DeepSeek R1 para chat con IA, escritura, programación y más. ¡Experimenta el chat de próxima generación con IA ahora!</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/sharmt1411/askanywhere/blob/main/icon/Depth_8,_Frame_0explore-%E8%A7%92%E6%A0%87.png?raw=true\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sharmt1411/askanywhere\">Askanywhere</a> </td>\n        <td>Selecciona texto en cualquier lugar y comienza una conversación con Deepseek</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/OJZen/1chat/raw/refs/heads/main/doc/assets/icon.ico?raw=true\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/OJZen/1chat\">1chat</a> </td>\n        <td>Una aplicación iOS que te permite chatear con el modelo DeepSeek-R1 localmente.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://chatlabsai.com/assets/logo/logo.png\" alt=\"iOS AI Chatbot\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chatlabsai.com\">Accede a más de 250 modelos de texto e imagen LLM en una sola aplicación</a> </td>\n        <td> El chatbot 1AI para iOS integra más de 250 modelos de texto, imagen y voz, permitiendo a los usuarios chatear con cualquier modelo en el mundo, incluyendo los modelos Deepseek R1 y Deepseek V3.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/PopAi/assets/logo.svg\" alt=\"PopAi\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://popai.pro\">PopAi</a> </td>\n        <td>PopAi lanza DeepSeek R1. Disfruta de un rendimiento ultrarrápido sin retrasos con PopAi. Cambia sin problemas la búsqueda en línea activada/desactivada.</td>\n     </tr>\n    <tr>\n        <td> <img src=\"https://pot-app.com/logo/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a></td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a> 🌈 Un software multiplataforma de traducción de palabras y OCR. </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Byaidu/PDFMathTranslate/raw/main/docs/images/banner.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Byaidu/PDFMathTranslate\">PDFMathTranslate</a></td>\n        <td>Esta extensión puede ayudar a los desarrolladores a traducir anotaciones, cadenas, consejos de código, mensajes de error y nombres de variables en el Código.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Richasy/Bili.Copilot/raw/master/assets/StoreLogo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Richasy/Bili.Copilot\">Bili.Copilot</a></td>\n        <td>Cliente de escritorio Windows de terceros en la estación b, una aplicación nativa construida con el SDK de la aplicación Windows.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://www.tensorbounce.com/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.tensorbounce.com/\">LawAgent</a></td>\n        <td>LawAgent es un producto de IA legal desarrollado por el equipo de Tensorbounce, que integra una base de conocimientos con capacidades de Agente IA. Cuenta con un vasto repositorio de decenas de millones de datos oficiales relacionados con el ámbito legal y también permite configuraciones personalizadas de la base de conocimientos. El modo profesional aprovecha las capacidades de razonamiento de DeepSeek-R1 para asistir a los usuarios en análisis legales, revisión de contratos, generación de documentos, traducción de archivos y otros escenarios legales.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://h1.appinn.me/file/1741929316827_21.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n<td><a href=\"https://github.com/jiqi136/DS-AI\">Asistente de IA con conexión en tiempo real</a></td>\n<td> BEl asistente de IA admite conexión directa a la interfaz DeepSeek-V3.1 con el potente modelo de código Claude Code, permitiendo su uso sin intermediarios de red (reducción de costes del 90%). Soporta lectura de imágenes y archivos PDF con generación gratuita de imágenes; permite integración personalizada con otros modelos de IA; habilita búsqueda en tiempo real en la web mediante navegador local. Además, ofrece opciones gratuitas como el modelo R1.\n</td>\n\t</tr>\n    <tr>\n    <td><img src=\"docs/DocKit/assets/dockit.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n    <td><a href=\"https://dockit.geekfun.club/\">DocKit</a></td>\n    <td>DocKit es un cliente GUI de escritorio potenciado por IA diseñado para bases de datos NoSQL, compatible con Elasticsearch y OpenSearch en Mac, Windows y Linux. Mediante la integración con modelos grandes como DeepSeek, DocKit puede ayudar a los desarrolladores a escribir consultas DSL complejas y proporcionar una mejor experiencia para la gestión y análisis de datos.</td>\n    </tr> \n    <tr>\n        <td> <img src=\"docs/zenfeed/assets/icon.png\" alt=\"Icono\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/glidea/zenfeed\">zenfeed</a> </td>\n        <td> Potencia RSS con IA, filtra, resume y envía automáticamente información importante para superar la sobrecarga de información. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/NoteGen/NoteGen.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/codexu/note-gen\">NoteGen</a> </td>\n        <td> NoteGen es una aplicación multiplataforma de notas Markdown que se enfoca en utilizar inteligencia artificial para construir un puente entre la recopilación de información y la escritura, organizando conocimientos fragmentados en notas legibles. </td>\n    </tr>\n    </tr>\n        <tr>\n        <td> </td>\n        <td> <a href=\"https://github.com/SamYuan1990/i18n-agent-action\">i18n-agent-action</a> </td>\n        <td> El i18n Agent es una herramienta impulsada por inteligencia artificial diseñada para simplificar y automatizar los flujos de trabajo de internacionalización (i18n) y localización (l10n). Al aprovechar el procesamiento avanzado de lenguaje natural (NLP) y el aprendizaje automático, ayuda a desarrolladores, traductores y equipos de productos a gestionar contenido multilingüe de manera eficiente, eliminando errores manuales y acelerando los despliegues globales. </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://raw.githubusercontent.com/rockbenben/subtitle-translator/main/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/rockbenben/subtitle-translator\">Subtitle Translator</a></td>\n        <td>Herramienta de traducción de subtítulos por lotes para formatos SRT/ASS/VTT/LRC, compatible con DeepSeek y otras interfaces de LLM y traducción automática.</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/turtlenoir/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://turtlenoir.com/\"> Turtle Noir </a> </td>\n        <td> <a href=\"https://turtlenoir.com/\"> Turtle Noir </a> Un juego de enigmas de pensamiento lateral tipo \"Sopa de Tortuga\" con un anfitrión de IA basado en DeepSeek, disponible para uno o varios jugadores. La IA modera la partida e interactúa con humor, guiando la deducción mediante respuestas de \"Sí / No / Irrelevante\". Ofrece una experiencia inmersiva con una fuerte atmósfera narrativa, gestión del ritmo y un sistema de pistas para evitar bloqueos. Integra búsqueda vectorial y DeepSeek para evitar la repetición de acertijos e incluye moderación de contenido. Ideal para entrenar la creatividad y como entretenimiento social en línea. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"agent\">Marcos de agentes de IA</span>\n\n<table>\n    <tr>\n        <td width=80> <img src=\"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolagents/mascot_smol.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/huggingface/smolagents/tree/main\"> smolagents </a> </td>\n        <td> La forma más sencilla de construir grandes agentes de IA. Los agentes utilizan código en Python para invocar herramientas y coordinar otros agentes. ¡Soporte prioritario para modelos abiertos como DeepSeek-R1! </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://yomo.run/yomo-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/yomo/README.md\">YoMo</a></td>\n        <td>Marco sin servidor para llamadas de funciones LLM con estado y soporte para lenguajes fuertemente tipados.</td>\n     </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/superagentxai/superagentX/refs/heads/master/docs/logo/icononly_transparent_nobuffer.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/superagentx/README.md\">SuperAgentX</a> </td>\n        <td>SuperAgentX: Un marco de IA de código abierto y ligero diseñado para aplicaciones autónomas de múltiples agentes con capacidades de Inteligencia Artificial Generalizada (AGI).</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://panda.fans/_assets/favicons/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/anda/README.md\">Anda</a> </td>\n        <td>Un marco en Rust para el desarrollo de agentes de IA, diseñado para construir una red altamente componible, autónoma y con memoria perpetua de agentes de IA.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://rig.rs/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" alt=\"Rig (Rust)\" /> </td>\n        <td> <a href=\"https://rig.rs\">RIG</a> </td>\n        <td>Construye aplicaciones LLM modulares y escalables en Rust.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/longevity-genie/chat-ui/11c6647c83f9d2de21180b552474ac5ffcf53980/static/geneticsgenie/icon-128x128.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/longevity-genie/just-agents\">Just-Agents</a> </td>\n        <td>Una biblioteca ligera y sencilla para agentes LLM: sin ingeniería excesiva, solo simplicidad.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://alice.fun/alice-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bob-robert-ai/bob/blob/main/alice/readme.md\">Alice</a> </td>\n        <td>Un agente de IA autónomo en blockchain, que aprovecha LLMs como DeepSeek para la toma de decisiones en cadena. Alice combina análisis de datos en tiempo real con una personalidad lúdica para gestionar tokens, minar BOB y gobernar ecosistemas.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Upsonic/Upsonic/blob/9d2e6d43b44defc6744817330625661ca3a2184e/Upsonic%20pp.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Upsonic/Upsonic\">Upsonic</a> </td>\n        <td>Upsonic ofrece un marco de agentes listo para empresas de última generación donde puedes orquestar llamadas LLM, agentes y uso de computadoras para completar tareas de manera rentable.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/173022229\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/APRO-com\">ATTPs</a> </td>\n        <td>Un marco de protocolo fundamental para la comunicación confiable entre agentes. Cualquier agente basado en DeepSeek, al integrarse con el SDK de <a href=\"https://docs.apro.com/attps\">ATTPs</a>, puede acceder a funciones como registro de agentes, envío de datos verificables y recuperación de datos verificables. Así, puede establecer una comunicación confiable con agentes de otras plataformas.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/translate.js/assets/icon.png\" alt=\"图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/translate.js/README.md\">translate.js</a> </td>\n        <td> IA i18n para desarrolladores front-end. Puede lograr traducción automática completa de HTML con solo dos líneas de JavaScript. Puedes cambiar entre docenas de idiomas con un solo clic. No es necesario modificar la página, no se requieren archivos de configuración de idiomas y admite docenas de instrucciones de extensión de ajuste fino. Es compatible con SEO. Además, abre una interfaz estándar de API de traducción de texto.</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/agentUniverse/assets/agentUniverse_logo_s.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/antgroup/agentUniverse\"> agentUniverse </a> </td>\n        <td> agentUniverse es un marco de colaboración multi-agente diseñado para escenarios empresariales complejos. Ofrece capacidades de desarrollo rápidas y fáciles de usar para aplicaciones de agentes LLM, con un enfoque en mecanismos como programación colaborativa de agentes, toma de decisiones autónoma y retroalimentación dinámica. El marco se origina en las prácticas empresariales del mundo real del Grupo Ant en la industria financiera. En junio de 2024, agentUniverse logró soporte de integración completa para la serie de modelos DeepSeek. </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/BotSharp/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/SciSharp/BotSharp\"> BotSharp </a> </td>\n        <td> BotSharp es un marco de desarrollo de aplicaciones multiagente de código abierto. Desde simples chatbots hasta colaboración multiagente y tareas complejas como el marco \"Text To SQL\", ofrece métodos listos para usar. Permite integrar rápidamente las capacidades de grandes modelos en sistemas empresariales existentes, y cuenta con funciones integradas de gestión de conocimiento y gestión de conversaciones. El marco ha sido probado exhaustivamente con el modelo DeepSeek V3, y gracias al rendimiento de DeepSeek V3, el marco no tiene nada que envidiar a otros modelos propietarios. </td>\n    </tr>\n     <tr>\n            <td width=80> <img src=\"docs/eino/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n            <td> <a href=\"https://github.com/cloudwego/eino\"> Eino </a> </td>\n            <td> Eino (pronounced like \"I know\") aims to be the best LLM application development framework in the Go language. It draws on the design concept of excellent LLM frameworks in open source communities such as LangChain and LlamaIndex, while absorbing cutting-edge research results and practical application experience, providing a LLM application development framework that is more in line with Go programming conventions, emphasizing simplicity, scalability, reliability and efficiency. </td>\n        </tr>\n    <tr>\n        <td width=80> <img src=\"https://raw.githubusercontent.com/Tencent/Youtu-agent/924aeeb6c49ee524b8bb4de2642a3dc84b7b86b9/docs/assets/mascot.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> es un marco flexible y de alto rendimiento para construir, ejecutar y evaluar agentes autónomos. Más allá de encabezar los puntos de referencia (benchmarks), este marco ofrece capacidades potentes para agentes, como análisis de datos, procesamiento de archivos e investigación profunda, todo ello con modelos de código abierto. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"data\">Marcos de aplicaciones de datos de IA</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/user-attachments/assets/a327d72f-755f-4256-8a37-32a518a55df3\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td width=\"120\"> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/dbgpt/README.md\"> DB-GPT </a> </td>\n        <td> 🤖 DB-GPT es un marco de desarrollo de aplicaciones de datos nativo de IA de código abierto con AWEL (Lenguaje de Expresión de Flujo de Trabajo Agente) y agentes. El propósito es construir infraestructura en el campo de los grandes modelos, a través del desarrollo de múltiples capacidades técnicas como gestión de múltiples modelos (SMMF), optimización de efectos Text2SQL, marco y optimización RAG, colaboración de marcos de múltiples agentes, AWEL (orquestación de flujo de trabajo de agentes), etc. Lo que hace que las aplicaciones de grandes modelos con datos sean más simples y convenientes.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"rag\">Marcos RAG</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/ragflow/README.md\"> RAGFlow </a> </td>\n        <td> Un motor RAG (Generación Aumentada por Recuperación) de código abierto basado en la comprensión profunda de documentos. Ofrece un flujo de trabajo RAG simplificado para empresas de cualquier escala, combinando LLM (Modelos de Lenguaje Grande) para proporcionar capacidades de respuesta a preguntas veraces, respaldadas por referencias sólidas extraídas de datos complejos y variados.</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/pingcap/tidb.ai/main/frontend/app/public/nextra/icon-dark.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/autoflow/README.md\"> Autoflow </a> </td>\n        <td> <a href=\"https://github.com/pingcap/autoflow\">AutoFlow</a> es una herramienta de base de conocimiento de código abierto basada en GraphRAG (Generación Aumentada por Recuperación basada en Grafos), construida sobre <a href=\"https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community\">TiDB</a> Vector, LlamaIndex y DSPy. Proporciona una interfaz de búsqueda similar a Perplexity y permite una integración fácil de la ventana de búsqueda conversacional de AutoFlow en tu sitio web mediante la inserción de un simple fragmento de JavaScript.</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://assets.zilliz.com/Zilliz_Logo_Mark_White_20230223_041013_86057436cc.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zilliztech/deep-searcher\"> DeepSearcher </a> </td>\n        <td> DeepSearcher combina potentes LLMs (DeepSeek, OpenAI, etc.) y bases de datos vectoriales (Milvus, etc.) para realizar búsquedas, evaluaciones y razonamientos basados en datos privados, proporcionando respuestas altamente precisas e informes completos.</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/OpenSPG/openspg/089188f3e7b0392221f5a8e8f1a3629b6352a6f9/LOGO.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/OpenSPG/KAG/blob/master/README.md\"> KAG </a> </td>\n        <td> KAG es un marco de razonamiento lógico y preguntas y respuestas basado en el motor <a href=\"https://github.com/OpenSPG/openspg\">OpenSPG</a> y modelos de lenguaje grandes, que se utiliza para construir soluciones de razonamiento lógico y preguntas y respuestas para bases de conocimiento de dominio vertical. KAG puede superar eficazmente la ambigüedad del cálculo de similitud vectorial tradicional de RAG y el problema de ruido introducido por GraphRAG mediante OpenIE. KAG admite razonamiento lógico y preguntas y respuestas de hechos de múltiples saltos, etc.</td>\n    </tr>\n\t<tr>\n    <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/TencentCloudADP/youtu-graphrag/refs/heads/main/assets/logo.png\" alt=\"Icono de Youtu-GraphRAG\" width=\"64\" height=\"auto\"/> </td>\n    <td> <a href=\"https://github.com/TencentCloudADP/Youtu-GraphRAG\"> Youtu-GraphRAG </a> </td>\n    <td>Youtu-GraphRAG propone un nuevo paradigma de generación aumentada por recuperación en grafos (GraphRAG) que unifica verticalmente la construcción, indexación y recuperación de grafos mediante esquemas. Avanza el GraphRAG hacia aplicaciones de nivel empresarial, permitiendo una adaptación perfecta entre dominios con mínima intervención humana, mediante (i) una extracción dinámica acotada por esquemas; (ii) un algoritmo integral de detección de comunidades y (iii) una descomposición de consultas guiada por esquemas para la reflexión iterativa y el razonamiento.</td>\n</tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"fhe\">Marcos FHE (Cifrado Homomórfico Completo)</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/fhe.mind-network/mind-network-log.png\" alt=\"Icon\" width=\"200\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\"> Mind FHE Rust SDK </a> </td>\n        <td> <p>Un SDK de código abierto para cifrar IA con Cifrado Homomórfico Completo (FHE) e integrarse con Mind Network para el consenso de agentes. FHE se considera el <b>santo grial de la criptografía</b>, permitiendo cálculos directamente en datos cifrados sin necesidad de descifrado. Con FHE, los agentes pueden proteger su privacidad mientras usan Deepseek, garantizando tanto la integridad del modelo como el consenso de resultados -<b> todo sin exponer sus datos </b>- al conectarse a Mind Network. El código fuente del SDK <a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\"> está implementado en puro <b>Rust</b></a> y el paquete también está disponible en <a href=\"https://crates.io/crates/mind_sdk_deepseek\"> crates.io </a>. </p> </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"solana\">Marcos Solana</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/solana-agent-kit/assets/sendai-logo.png\" alt=\"Icon\" width=\"128\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/solana-agent-kit/README.md\"> Solana Agent Kit </a> </td>\n        <td>Un kit de herramientas de código abierto para conectar agentes de IA a protocolos Solana. Ahora, cualquier agente, utilizando cualquier LLM Deepseek, puede ejecutar de forma autónoma más de 60 operaciones en el ecosistema Solana.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"sythetic\">Curación de datos sintéticos</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/bespokelabsai/curator/main/docs/Bespoke-Labs-Logomark-Red-crop.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/curator/README.md\"> Curator </a> </td>\n        <td> Una herramienta de código abierto para curar conjuntos de datos a gran escala para el entrenamiento posterior de LLMs. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/8455694b-c52e-40ec-847e-adf6a5ac064f\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Kiln-AI/Kiln\"> Kiln </a> </td>\n        <td>Genera conjuntos de datos sintéticos y destila modelos R1 en ajustes personalizados.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/192579850?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/DataEval/dingo\"> Dingo </a> </td>\n        <td>Dingo: Una herramienta integral de evaluación de calidad de datos. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"im\">Plugins de aplicaciones de mensajería instantánea</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/huixiangdou.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/huixiangdou/README_cn.md\">HuixiangDou<br/>(wechat,lark)</a> </td>\n        <td>Asistente de conocimiento de dominio en WeChat personal y Feishu, enfocado en responder preguntas.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/RockChinQ/LangBot/blob/master/res/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/RockChinQ/LangBot\">LangBot<br/>（QQ, Lark, WeCom）</a> </td>\n        <td> Marco de bots de mensajería instantánea basado en LLM, compatible con plataformas como QQ, Lark y WeCom.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://nonebot.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/KomoriDev/nonebot-plugin-deepseek\">NoneBot<br/>（QQ, Lark, Discord, TG, etc.）</a> </td>\n        <td> Basado en el marco NoneBot, proporciona funciones de chat inteligente y pensamiento profundo, compatible con QQ, Lark, Discord, TG y más plataformas.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"browser\">Extensiones para Navegadores</span>\n\n<table>\n    <tr>\n        <td><img src=\"./docs/SelectTranslate/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://selecttranslate.com/\">SelectTranslate</a></td>\n        <td>Extensión de traducción con IA gratuita y abierta, compatible con traducción bilingüe de páginas web, traducción seleccionada por IA (traducción de copias), traducción de introducido y traducción de PDF.\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9d3f42b8-fcd0-47ab-8b06-1dd0554dd80e\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_translate/README.md\"> Immersive Translate </a> </td>\n        <td> Immersive Translate es una extensión de traducción bilingüe para páginas web. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lh3.googleusercontent.com/K9i0qJb8phasC5wWf5tU68rhnfvX4swsE0hrhJP-WB3WV7MwE5KpMUIJvHKNHHRE6GKNIvIdTNSWoDMl_NggrmUsaw=s120\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_reading_guide/README.md\"> Immersive Reading Guide </a> </td>\n        <td> Sin barra lateral: resúmenes inmersivos de páginas web con IA y posibilidad de realizar preguntas. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/8a301619-a3de-489b-81fd-69aaa7c1c561\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_box/README.md\"> ChatGPT Box </a> </td>\n        <td> ChatGPT Box es una integración de ChatGPT en el navegador, completamente gratis. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c3d9d100-247a-41cc-97c1-10b01ed25e70\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/hcfy/README.md\"> hcfy (划词翻译) </a> </td>\n        <td> hcfy (划词翻译) es una extensión para navegadores que integra múltiples servicios de traducción. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.eudic.net/web/trans/en_trans.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Lulu Translate/README.md\"> Lulu Translate </a> </td>\n        <td> El plugin ofrece traducción seleccionando texto con el ratón, comparación párrafo por párrafo y traducción de documentos PDF. Puede utilizar varios motores de traducción como DeepSeek AI, Bing, GPT, Google, etc. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Bistutu/FluentRead/raw/refs/heads/main/public/icon/192.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fluent.thinkstu.com/\"> FluentRead </a> </td>\n        <td> Un revolucionario plugin de traducción de navegador de código abierto que permite a todos tener una experiencia de lectura nativa. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.ncurator.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.ncurator.com/\"> Ncurator </a> </td>\n        <td> Asistente de preguntas y respuestas basado en IA para bases de conocimiento: permite que la IA te ayude a organizar y analizar el conocimiento. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/oinzen/RSSFlow-doc/blob/main/docs/images/en/icon64.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://rssflow.oinchain.com\"> RssFlow </a> </td>\n        <td>Un lector RSS inteligente con resúmenes impulsados por IA y vistas de feeds multidimensionales. Soporta configuración del modelo DeepSeek para una mejor comprensión del contenido. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Hedwi/deepchat/refs/heads/main/images/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chromewebstore.google.com/detail/deepchat-power-of-deepsee/femhcibnncinlabdboehojdhfcihpkpl?hl=en\"> DeepChat </a> </td>\n        <td>Una extensión para Chrome que permite a los usuarios chatear con DeepSeek abriendo una barra lateral en cualquier sitio web. Además, proporciona un menú flotante debajo de cualquier texto seleccionado que permite generar resúmenes, revisar problemas gramaticales y traducir contenido. </td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://www.typral.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.typral.com/\"> Typral </a> </td>\n        <td> Asistente rápido de escritura con IA: permite que la IA te ayude a optimizar rápidamente artículos, documentos y textos. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.trancy.org/assets/trancy_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.trancy.org/\"> Trancy </a> </td>\n        <td>Traducción bilingüe inmersiva, subtítulos bilingües para videos, extensión para traducción de frases/palabras seleccionadas. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://ziziyi.com/svg/anything_copilot.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/baotlake/anything-copilot\"> Anything Copilot </a> </td>\n        <td> Anything Copilot es una extensión de navegador que permite un acceso fluido a herramientas de IA principales directamente desde tu barra lateral. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cliprun.com/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://cliprun.com/\"> Cliprun </a> </td>\n        <td> Ejecutor de código Python y espacio de pruebas. Haz clic derecho sobre el código Python en DeepSeek para ejecutarlo al instante en tu navegador. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"http://cdn.docky.ai/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/docky-ai/README.md\"> Docky AI </a> </td>\n        <td>Docky AI es una poderosa extensión de navegador que permite interacciones en tiempo real con múltiples modelos de IA a través de una barra lateral. Soporta comunicación simultánea con múltiples modelos y puede asistirte en la lectura de páginas web, escritura, traducción y creación de imágenes. </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://readfrog.mengxi.work/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://readfrog.mengxi.work\"> 🐸 Read Frog </a></td>\n        <td>Traduce y comprende en profundidad cualquier página web con la ayuda de la IA.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Rearview/assets/favicon.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"./docs/Rearview/README_es.md\"> RearView </a> </td>\n        <td>Rearview es una extensión de gestión del historial del navegador que admite la búsqueda de texto completo del contenido de navegación histórico y convierte el historial de navegación en una base de conocimientos conversacional.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"vscode\">Extensiones para VS Code</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/continuedev/continue/blob/main/docs/static/img/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continue es un piloto automático de código abierto para IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/assets/favicon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/README.md\"> Cline </a> </td>\n        <td> Conoce a Cline: un asistente de IA que puede trabajar con tu CLI y editor. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Sitoi/ai-commit/refs/heads/main/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Sitoi/ai-commit/blob/main/README.md\"> AI Commit </a> </td>\n        <td> Usa IA para generar mensajes de commit en git desde VS Code. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/titusTong/seekCodeCopilot/blob/main/assets/SeekCodeCopilotLogo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/titusTong/seekCodeCopilot/blob/main/README.md\"> SeekCode Copilot </a> </td>\n        <td> Asistente inteligente de codificación para VS Code que admite la configuración de modelos DeepSeek desplegados localmente. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/intellism/vscode-comment-translate/blob/master/doc/image/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/intellism/vscode-comment-translate/blob/master/README.md\"> Comment Translation </a> </td>\n        <td> Esta extensión ayuda a los desarrolladores a traducir anotaciones, cadenas, consejos de código, mensajes de error y nombres de variables en el Código. </td>\n    </tr>\n        <tr>\n            <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/AITK/assets/AIToolkit.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n            <td> <a href=\"https://code.visualstudio.com/docs/intelligentapps/overview\"> AI Toolkit </a> </td>\n            <td> AI Toolkit para Visual Studio Code es una extensión integral que permite a desarrolladores e ingenieros de IA construir, probar y desplegar aplicaciones inteligentes utilizando modelos de IA generativa. </td>\n        </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/joygqz/commit-genie/refs/heads/main/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=joygqz.commit-genie\"> Commit Genie </a> </td>\n        <td> Revisión de código con IA y generador de mensajes de confirmación para VS Code. Revisa automáticamente los cambios de código y genera mensajes de confirmación estándar y relevantes. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/JohnnyZ93/oai-compatible-copilot/blob/main/assets/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/oai-compatible-copilot/README.md\"> OAI Compatible Provider for Copilot </a> </td>\n        <td> Una extensión de código abierto para VS Code para usar proveedores de inferencia compatibles con OpenAI en GitHub Copilot. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"vs\">Extensiones de Visual Studio</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/comment2gpt/2.0.5/1739475434185/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.Comment2GPT\"> Comment2GPT </a> </td>\n        <td> Utiliza OpenAI ChatGPT, Google Gemini, Anthropic Claude, DeepSeek y Ollama a través de tus comentarios </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/codelens2gpt/2.0.5/1739475875714/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.CodeLens2GPT\"> CodeLens2GPT </a> </td>\n        <td> Utiliza OpenAI ChatGPT, Google Gemini, Anthropic Claude, DeepSeek y Ollama a través de Lente de Código (CodeLens) </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/uca-lite/1.4.2/1739392928984/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.UCA-Lite\"> Unity Code Assist Lite </a> </td>\n        <td> Asistencia de código para scripts de Unity </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"neovim\">Extensiones de Neovim</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/c316f70a-0a3c-4a32-b148-4df15e609acc\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/avante.nvim/README.md\"> avante.nvim </a> </td>\n        <td> avante.nvim es un piloto automático de código abierto en IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/llm.nvim/README.md\"> llm.nvim </a> </td>\n        <td> Un plugin gratuito de modelo de lenguaje grande (LLM) que permite interactuar con LLM en Neovim. Compatible con cualquier LLM, como DeepSeek, GPT, GLM, Kimi o LLM locales (como Ollama). </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/codecompanion.nvim/README.md\"> codecompanion.nvim </a> </td>\n        <td> Codificación impulsada por IA, perfectamente integrada en Neovim. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/minuet-ai.nvim/README.md\"> minuet-ai.nvim </a> </td>\n        <td> Minuet ofrece autocompletado de código mientras escribes, utilizando LLM populares como DeepSeek, OpenAI, Gemini, Claude, Ollama, Codestral y más. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"jetbrains\">Extensiones de JetBrains</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/21520/412905/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ide.unitmesh.cc/quick-start\"> AutoDev </a> </td>\n        <td>‍AutoDev es un asistente de codificación con IA de código abierto en el IDE de JetBrains. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/21410/561595/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/21410-onegai-copilot\"> Onegai Copilot </a> </td>\n        <td>Onegai Copilot es un asistente de codificación con IA en el IDE de JetBrains. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/continuedev/continue/blob/main/docs/static/img/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continue es un piloto automático de código abierto en IDE. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/a18792721831/studyplugin/535b9cab69da0f97b42dcaebb00bb0d4ed15c8a6/translate/src/main/resources/META-INF/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/18336-chinese-english-translate\">Traducción Chino-Inglés</a> </td>\n        <td> Traducción Chino-Inglés es un servicio de traducción múltiple en el IDE de JetBrains. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/24851/659002/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/24851-ai-git-commit\">AI Git Commit</a> </td>\n        <td> Este plugin utiliza IA para generar automáticamente mensajes de commit basados en los cambios en tu código. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/YiiGuxing/TranslationPlugin/blob/master/pluginIcon.svg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://intellij-translation.yiiguxing.top/#/en/\">IntelliJ Translation Plugin</a> </td>\n        <td> Un complemento de traducción para IDEs basados en IntelliJ que integra múltiples servicios de traducción, incluyendo OpenAI Translator (compatible con DeepSeek, Doubao, Ollama, etc.), permitiendo traducir directamente textos de código como comentarios y documentación dentro del IDE en cualquier momento. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"discord\">Bots de Discord</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://geneplore.com/img/geneplore_color_logo_circular.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Geneplore AI/README.md\"> Geneplore AI </a> </td>\n        <td> Geneplore AI opera uno de los bots de Discord con IA más grandes, ahora con DeepSeek v3 y R1. </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"codeeditor\">Editor de Código Nativo con IA</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://global.discourse-cdn.com/flex020/uploads/cursor1/original/2X/a/a4f78589d63edd61a2843306f8e11bad9590f0ca.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.cursor.com/\"> Cursor </a> </td>\n        <td>‍El Editor de Código con IA basado en VS Code (Visual Studio Code)</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://exafunction.github.io/public/images/windsurf/windsurf-app-icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://codeium.com/windsurf\"> WindSurf </a> </td>\n        <td>Otro Editor de Código con IA basado en VS Code por Codeium</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/wusigram/assets/logo-512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wusigram/README.md\"> 无思微程序 </a> </td>\n        <td>Herramientas de programación y operación de IA móvil, socio de programación de DeepSeek</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"emacs\">Emacs</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/karthink/gptel\"> gptel </a> </td>\n        <td>Un cliente LLM simple para Emacs</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/milanglacier/minuet-ai.el\"> Minuet AI </a> </td>\n        <td>Trabaja con inteligencia en tu código</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"security\">Seguridad</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/lukehinds/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/codegate.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/stacklok/codegate/\"> CodeGate </a> </td>\n        <td> CodeGate: generación de código seguro con IA</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/tencent/hunyuan.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tencent/AI-Infra-Guard\"> AI-Infra-Guard </a> </td>\n        <td> Herramienta para evaluar la seguridad de infraestructuras de IA y detectar riesgos potenciales.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n###  <span id=\"others\">Otros</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://i.imgur.com/IsQYInJ.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/djcopley/ShellOracle/\"> ShellOracle </a> </td>\n        <td> Una utilidad de terminal para la generación inteligente de comandos shell. </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/178783630?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bolna-ai/bolna/\"> Bolna </a> </td>\n        <td> Usa DeepSeek como el LLM para agentes de voz conversacionales con IA</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/fatwang2/siri-ultra\"> Siri Ultra </a> </td>\n        <td> Un proyecto de GitHub con 1000 estrellas, que soporta conectividad a internet, conversaciones de múltiples turnos y modelos de la serie DeepSeek </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/yincongcyincong/telegram-deepseek-bot/blob/main/static/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> es un bot de Telegram integrado con las capacidades de DeepSeek AI. </td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> es una herramienta CLI impulsada por IA para generar comandos de shell conscientes del contexto, con soporte para múltiples backends de LLM. Admite sintaxis específica de shell, herramientas de sistema de solo lectura y puntos de inferencia personalizados.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.godtierprompts.com/logo.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a> es una clasificación impulsada por la comunidad donde los mejores prompts llegan a lo más alto.</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#tabla-de-contenidos\">^ Volver al índice ^</a></p>\n\n### Historial de Estrellas\n\n[![Star History Chart](https://api.star-history.com/svg?repos=deepseek-ai/awesome-deepseek-integration&type=Date)](https://star-history.com/#deepseek-ai/awesome-deepseek-integration&Date)\nEste gráfico muestra la evolución de las estrellas del repositorio en GitHub a lo largo del tiempo.\n"
  },
  {
    "path": "README_ja.md",
    "content": "<div align=\"center\">\n\n<p align=\"center\">\n<img width=\"1000px\" alt=\"Awesome DeepSeek Integrations\" src=\"docs/Awesome DeepSeek Integrations.png\">\n</p>\n\n# Awesome DeepSeek Integrations ![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)\n\nDeepSeek API を人気のソフトウェアに統合します。API キーを取得するには、[DeepSeek Open Platform](https://platform.deepseek.com/)にアクセスしてください。\n\n[English](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README.md) / [简体中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_cn.md) / [繁體中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_zh_tw.md) / 日本語 / [Español](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_es.md)\n</div>\n\n</br>\n</br>\n\n## 目次\n\n- [Awesome DeepSeek Integrations ](#awesome-deepseek-integrations-)\n  - [目次](#目次)\n  - [プロジェクト一覧](#プロジェクト一覧)\n    - [アプリケーション](#アプリケーション)\n    - [AI エージェントフレームワーク](#ai-エージェントフレームワーク)\n    - [AIデータアプリケーション開発フレームワーク](#aiデータアプリケーション開発フレームワーク)\n    - [RAG フレームワーク](#rag-フレームワーク)\n    - [FHE フレームワーク](#fhe-フレームワーク)\n    - [Solana フレームワーク](#solana-フレームワーク)\n    - [合成データのカテゴリ化](#合成データのカテゴリ化)\n    - [IM アプリケーションプラグイン](#im-アプリケーションプラグイン)\n    - [ブラウザ拡張機能](#ブラウザ拡張機能)\n    - [VS Code 拡張機能](#vs-code-拡張機能)\n    - [neovim 拡張機能](#neovim-拡張機能)\n    - [JetBrains 拡張機能](#jetbrains-拡張機能)\n    - [AI コードエディタ](#ai-コードエディタ)\n    - [Emacs](#emacs)\n    - [その他](#その他)\n\n## プロジェクト一覧\n\n###  <span id=\"applications\">アプリケーション</span>\n\n<table>\n    <tr>\n        <td><img src=\"docs/operit/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/AAswordman/Operit\">Operit AI</a></td>\n        <td>Androidプラットフォーム向けのオープンソースシステム統合AIアシスタントで、ほぼ完全なmcp使用をサポートし、Androidシステムと高い互換性を持っています。このソフトウェアは高度なカスタマイズと低い学習障壁を特徴とし、ファイル操作、検索、自動クリック、フォーマット変換などの組み込みツールと統合DeepSeek APIウェブページを備えています。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/eechat/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Lucassssss/eechat\">eechat</a></td>\n        <td>シンプルで使いやすい大規模言語モデルのローカル展開ツールです。DeepSeek-R1、DLlama 3、Phi-4、Mistral、Gemma 3などのオープンソースモデルのローカルでのプライバシー保護された展開をサポートし、リモートの大規模言語モデルAPIの呼び出しにも対応しています。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/aingdesk/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/aingdesk/AingDesk\">AingDesk</a></td>\n        <td>ワンクリックでAIモデルをパソコンにデプロイ可能。操作は視覚化され、美しいチャットインターフェースが内蔵されており、オンラインで他人と共有して利用できます。DeepSeekなどの他のモデルにも対応し、インターネット検索やサードパーティAPIもサポートしています。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/dingtalk/assets/dingtalk_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.dingtalk.com/\">DingTalk</a></td>\n        <td>DingTalk AIアシスタントは、DingTalkプラットフォームのさまざまなAI機能を統合し、企業の日常業務プロセスをインテリジェントにサポートします。DingTalk AIアシスタントは、スマートコミュニケーション、スマートコラボレーション、スマートマネジメントなど、多様なインテリジェント機能を備えています。これらの機能を活用し、企業内の要点を整理し、会議議事録を作成し、関連する業務タスクやスケジュールのリマインダーをユーザーに通知することができます。さらに、DingTalk AIアシスタントはナレッジベースを活用し、企業の管理プロセスや人事ポリシーなどに関する従業員からの一般的な質問に対して、インテリジェントに回答することも可能です。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://chatdoc.com/chatdoc/chatdoc.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://chatdoc.com\">ChatDOC</a></td>\n        <td>ChatDOCは、AIを活用したドキュメントリーディングツールで、強力なトレーサビリティ機能を備えており、すべての情報の出所が明確で確認可能です。これにより、ドキュメントの核心を効率的かつ正確に把握するのに役立ちます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/SwiftChat/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n<td> <a href=\"docs/SwiftChat/README.md\">SwiftChat</a></td>\n<td> <a href=\"https://github.com/aws-samples/swift-chat\">SwiftChat</a> は React Native で構築された超高速なクロスプラットフォームAIチャットアプリケーションです。Android、iOS、macOSでネイティブなパフォーマンスを提供します。リアルタイムストリーミングチャット、豊富なMarkdownサポート、AI画像生成、カスタマイズ可能なシステムプロンプト、クイックモデル切り替え、マルチモーダル機能などを備えています。DeepSeek、Amazon Bedrock、Ollama、OpenAI 互換モデルなど複数のAIプロバイダーをサポートし、シンプルなUIと高性能を実現しています。</td>\n    </tr>\n <tr>\n    <td><img src=\"https://4everlogo.4everland.store/logo/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n    <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/4EVERChat/README_ja.md\">4EVERChat</a></td>\n    <td><a href=\"https://chat.4everland.org/\">4EVERChat</a>は、数百のLLMを統合したインテリジェントなモデル選択プラットフォームで、モデルのパフォーマンスをリアルタイムで比較可能です。<a href=\"https://www.4everland.org/\">4EVERLAND</a> AI RPCの統一APIエンドポイントを活用し、コストフリーでモデル切り替えを実現し、応答が速くコストの低い組み合わせを自動的に選択します。</td>\n</tr>\n    <tr>\n        <td><img src=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/build/icon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/README.md\">DeepChat</a></td>\n        <td>DeepChat は、強力な DeepSeek モデルを内蔵した完全に無料のデスクトップ インテリジェント アシスタントです。複数ラウンドの会話、オンライン検索、ファイルのアップロード、ナレッジ ベースなどの複数の機能をサポートします。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/171659527?s=400&u=39906ab3b6e2066f83046096a66a77fb3f8bb836&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/quantalogic/quantalogic\">Quantalogic</a> </td>\n        <td> QuantaLogicは、高度なAIエージェントを構築するためのReAct（推論と行動）フレームワークです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/gptbots/gptbots.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.gptbots.ai/ja_JP/docs\">GPTBots</a> </td>\n        <td> <a href=\"https://www.gptbots.ai/ja_JP\">GPTBots</a>は、Deepseekを含む国際的な主要LLMを統合したノーコードのAIエージェント構築プラットフォームです。RAGに基づく知識ストレージ/検索、ツールのカスタマイズ/呼び出し、ワークフローのオーケストレーションなどのモジュールを提供しています。また、エージェントを複数の主流プラットフォーム（WhatsApp、Telegramなど）に統合することができ、企業にエンドツーエンドのAIソリューションを提供し、AI時代において企業が際立つ手助けをします。\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/224d547a-6fbc-47c8-859f-aa14813e2b0f\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatbox/README.md\">Chatbox</a> </td>\n        <td> Chatboxは、Windows、Mac、Linuxで利用可能な複数の最先端LLMモデルのデスクトップクライアントです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/bb65404c-f867-42d8-ae2b-281fe953ab54\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_next_web/README.md\"> ChatGPT-Next-Web </a> </td>\n        <td> ChatGPT Next Webは、GPT3、GPT4、Gemini ProをサポートするクロスプラットフォームのChatGPTウェブUIです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/Casibase/assets/casibase.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://casibase.org/ja/docs/category/beginner-guide/\">Casibase</a></td>\n        <td> <a href=\"https://casibase.org\">Casibase</a>は、最新のRAG技術、SSO機能を組み合わせ、様々な主要なAIモデルをサポートするオープンソースのAIナレッジベースと対話システムです。企業や開発者に、強力で柔軟なナレッジ管理とインテリジェントな対話プラットフォームを提供することを目指しています。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Coco AI/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Coco AI/README.md\">Coco AI</a></td>\n        <td> <a href=\"https://coco.rs\">Coco AI</a> は、完全にオープンソースでクロスプラットフォーム対応の統合検索および生産性向上ツールで、アプリケーション、ファイル、Google Drive、Notion、Yuque、Hugoなど、ローカルおよびクラウドのさまざまなデータソースを接続して検索できます。DeepSeekなどの大規模モデルと連携することにより、Coco AIはインテリジェントな個人のナレッジ管理を実現し、プライバシーを重視し、プライベートなデプロイにも対応。ユーザーが情報に迅速かつインテリジェントにアクセスできるようサポートします。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/liubai/assets/liubai-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/liubai/README.md\">Liubai</a> </td>\n        <td> Liubaiは、WeChat上でDeepSeekを使用してノート、タスク、カレンダー、ToDoリストを操作できるようにします！ </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1ac9791b-87f7-41d9-9282-a70698344e1d\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/pal/README.md\"> Pal - AI Chat Client<br/>(iOS, ipadOS) </a> </td>\n        <td> Palは、iOS上でカスタマイズされたチャットプレイグラウンドです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.librechat.ai/librechat.svg\" alt=\"LibreChat\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/deepseek\">LibreChat</a> </td>\n        <td> LibreChatは、DeepSeekをシームレスに統合してAIインタラクションを強化するカスタマイズ可能なオープンソースアプリです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/rss-translator/RSS-Translator/main/core/static/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/rss_translator/README.md\"> RSS Translator </a> </td>\n        <td> RSSフィードをあなたの言語に翻訳します！ </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://relingo.net/assets/images/relingo-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://relingo.net\"> Relingo </a> </td>\n        <td> ウェブサイトを閲覧したり、YouTubeを視聴しながら語彙を増やし、マスターしよう！ </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/enconvo/README.md\"> Enconvo </a> </td>\n        <td> Enconvoは、AI時代のランチャーであり、すべてのAI機能のエントリーポイントであり、思いやりのあるインテリジェントアシスタントです。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/kangfenmao/cherry-studio/blob/main/src/renderer/src/assets/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cherrystudio/README.md\">Cherry Studio</a></td>\n        <td>プロデューサーのための強力なデスクトップAIアシスタント</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://tomemo.top/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/tomemo/README.md\"> ToMemo (iOS, ipadOS) </a> </td>\n        <td> フレーズブック+クリップボード履歴+キーボードiOSアプリで、キーボードでの迅速な出力にAIマクロモデリングを統合しています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/buxuku/video-subtitle-master/refs/heads/main/resources/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/buxuku/video-subtitle-master\">Video Subtitle Master</a></td>\n        <td> ビデオの字幕を一括生成し、字幕を他の言語に翻訳することができます。これはクライアントサイドのツールで、MacとWindowsの両方のプラットフォームをサポートし、Baidu、Volcengine、DeepLx、OpenAI、DeepSeek、Ollamaなどの複数の翻訳サービスと統合されています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/dist/assets/chatworm-72x72.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/README.md\">Chatworm</a> </td>\n        <td> Chatwormは、複数の最先端LLMモデルのためのウェブアプリで、オープンソースであり、Androidでも利用可能です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/tisfeng/ImageBed/main/uPic/icon_512x512@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tisfeng/Easydict\">Easydict</a></td>\n        <td> Easydictは、単語の検索やテキストの翻訳を簡単かつエレガントに行うことができる、簡潔で使いやすい翻訳辞書macOSアプリです。大規模言語モデルAPIを呼び出して翻訳を行うことができます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.raycast.com/favicon-production.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/raycast/README.md\">Raycast</a></td>\n        <td> <a href=\"https://raycast.com/?via=ViGeng\">Raycast</a>は、macOSの生産性ツールで、いくつかのキーストロークでツールを制御できます。DeepSeek AIを含むさまざまな拡張機能をサポートしています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/chatpdflocal/assets/chatpdflocal-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatpdflocal.com\">ChatPDFLocal</a> </td>\n        <td> ChatPDFLocalはAIを搭載したMac OSアプリで、DeepSeekやその他の複数のAIモデルとシームレスに連携し、PDFの読書効率を向上させます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/193405629?s=200&v=4\" alt=\"PHP Client\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-php-client/blob/master/README.md\">PHP Client</a> </td>\n        <td> Deepseek PHP Clientは、Deepseek APIとのシームレスな統合のための堅牢でコミュニティ主導のPHPクライアントライブラリです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/958072?s=200&v=4\" alt=\"Laravel Integration\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-laravel/blob/master/README.md\">Laravel Integration</a> </td>\n        <td> LaravelアプリケーションとのシームレスなDeepseek API統合のためのLaravelラッパー。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/zotero/assets/zotero-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/zotero/README.md\">Zotero</a></td>\n        <td> <a href=\"https://www.zotero.org\">Zotero</a>は、研究成果を収集、整理、注釈、引用、共有するのに役立つ無料で使いやすいツールです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://b3log.org/images/brand/siyuan-128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/SiYuan/README.md\">SiYuan</a> </td>\n        <td> SiYuanは、完全にオフラインで使用できるプライバシー優先の個人知識管理システムであり、エンドツーエンドの暗号化データ同期を提供します。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/ArvinLovegood/go-stock/raw/master/build/appicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/ArvinLovegood/go-stock/blob/master/README.md\">go-stock</a> </td>\n        <td>go-stockは、Wailsを使用してNativeUIで構築され、LLMによって強化された中国株データビューアです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/102771702?s=200&v=4\" alt=\"Wordware\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wordware/README.md\">Wordware</a> </td>\n        <td><a href=\"https://www.wordware.ai/\">Wordware</a>は、誰でも自然言語だけでAIスタックを構築、反復、デプロイできるツールキットです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/xRJ6vNo9mUYeVNxt0KITXCXEuSk.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/langgenius/dify/\">Dify</a> </td>\n        <td> <a href=\"https://dify.ai/\">Dify</a>は、アシスタント、ワークフロー、テキストジェネレーターなどのアプリケーションを作成するためのDeepSeekモデルをサポートするLLMアプリケーション開発プラットフォームです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/enricoros/big-AGI/refs/heads/v2-dev/public/favicon.ico\" alt=\"Big-AGI\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/enricoros/big-AGI/blob/v2-dev/README.md\">Big-AGI</a> </td>\n        <td><a href=\"https://big-agi.com/\">Big-AGI</a>は、誰もが高度な人工知能にアクセスできるようにするための画期的なAIスイートです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/LiberSonora/LiberSonora/blob/main/assets/avatar.jpeg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/LiberSonora/LiberSonora/blob/main/README_en.md\">LiberSonora</a> </td>\n        <td> LiberSonoraは、「自由の声」を意味し、AIによって強化された強力なオープンソースのオーディオブックツールキットであり、インテリジェントな字幕抽出、AIタイトル生成、多言語翻訳などの機能を備え、GPUアクセラレーションとバッチオフライン処理をサポートしています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ripperhe/Bob/master/docs/_media/icon_128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a></td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a>は、任意のアプリで使用できるmacOSの翻訳およびOCRツールです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://agenticflow.ai/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a>は、マーケターがAIエージェントのためのエージェンティックAIワークフローを構築するためのノーコードプラットフォームであり、数百の毎日のアプリをツールとして使用します。</td>\n    </tr>\n<tr>\n        <td> <img src=\"https://raw.githubusercontent.com/STranslate/STranslate/refs/heads/main/images/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a></td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a> (Windows) は、WPF を使用して開発された、すぐに使用できる翻訳 OCR ツールです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/assets/favicon1.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/README_ja.md\"> Alphaパイ </a> </td>\n        <td> AI投資研究エージェント/次世代の金融情報エントリーポイント。投資家を代理して会議に出席し、AI議事録を取るほか、金融投資情報の検索・質問応答やエージェント駆使した定量分析など、投資研究業務を支援します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://docs.xark-argo.com/img/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.xark-argo.com\">argo</a> </td>\n        <td>ローカルでダウンロードし、Mac、Windows、Linux 上でOllamaとHuggingfaceモデルをRAGで実行します。LLM APIもサポートしています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://5ire.app/favicon.ico\" alt=\"5ire-logo\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/nanbingxyz/5ire\">5ire</a> </td>\n        <td> <a href=\"https://github.com/nanbingxyz/5ire\">5ire</a>はデザインが優れたクロスプラットフォームのオープンソース大型モデルデスクトップインテリジェントアシスタントで、市場に出回っている主流の大型モデルと互換性があり、MCPサーバー、ローカルの知識ベース、プロンプトライブラリ、さらに多くの実用的な機能をサポートしています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.petercat.ai/images/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.petercat.ai\">PeterCat</a> </td>\n        <td> 会話型Q&Aエージェントの構成システム、自ホスト型デプロイメントソリューション、および便利なオールインワンアプリケーションSDKを提供し、GitHubリポジトリのためのインテリジェントQ&Aボットをワンクリックで作成し、さまざまな公式ウェブサイトやプロジェクトに迅速に統合し、コミュニティのためのより効率的な技術サポートエコシステムを提供します。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/labring/FastGPT/refs/heads/main/.github/imgs/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fastgpt.cn/ja\">FastGPT</a> </td>\n        <td>\n            FastGPT は大規模言語モデル（LLM）を基盤としたオープンソースAIナレッジベース構築プラットフォームで、DeepSeekやOpenAIなど様々なモデルをサポートしています。データ処理、モデル呼び出し、RAG検索、ビジュアルAIワークフロー設計などの導入即使用可能な機能を提供し、複雑なAIアプリケーションの構築を容易に実現します。\n        </td>\n   </tr>\n   <tr>\n        <td> <img src=\"https://cdn.link-ai.tech/doc/CoW%20logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zhayujie/chatgpt-on-wechat\">Chatgpt-on-Wechat</a> </td>\n        <td> ChatGPT-on-WeChat (CoW) プロジェクトは、DeepSeek、OpenAI、Claude、Qwen など複数の LLM を、WeChat 公式アカウント、企業微信、飛書、DingTalk、ウェブサイトなどの一般的なプラットフォームやオフィスソフトにシームレスに統合できる柔軟なチャットボットフレームワークです。また、豊富なカスタムプラグインもサポートしています。 </td>\n    </tr>\n        <tr>\n        <td> <img src=\"./docs/TigerGPT/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ttm.financial/gpt\">TigerGPT</a> </td>\n        <td>TigerGPT は、OpenAI に基づく最初の金融 AI 投資アシスタントで、虎のグループによって開発されています。TigerGPT は、投資家に対して、深い推理をサポートするオンライン Q&A サービスを提供することを目的としています。2025年2月18日、TigerGPT は DeepSeek-R1 モデルを正式に統合し、ユーザーにオンライン Q&A サービスを提供することで、深い推理をサポートします。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/HIX.AI/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://hix.ai\">HIX.AI</a> </td>\n        <td>DeepSeek を無料でお試しいただき、 HIX.AI で AI チャットを無制限にお楽しみください。AI チャット、ライティング、コーディングなどに DeepSeek R1 をご利用ください。今すぐ次世代の AI チャットを体験してください!</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/sharmt1411/askanywhere/blob/main/icon/Depth_8,_Frame_0explore-%E8%A7%92%E6%A0%87.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sharmt1411/askanywhere\">Askanywhere</a> </td>\n        <td>どこでも単語を選択して、Deepseekとの会話を素早く開くことができる単語選択AIアシスタント！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/OJZen/1chat/raw/refs/heads/main/doc/assets/icon.ico?raw=true\" alt=\"アイコン\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/OJZen/1chat\">1chat</a> </td>\n        <td>DeepSeek-R1モデルとローカルでチャットできるiOSアプリです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://chatlabsai.com/assets/logo/logo.png\" alt=\"iOS AI チャットボット\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chatlabsai.com\">1つのアプリで250以上のテキスト、画像の大規模モデルにアクセス</a> </td>\n        <td> 1AI iOSチャットボットは250以上のテキスト、画像、音声モデルと統合されており、OpenRouterやReplicateの任意のモデル、Deepseek推論およびDeepseek V3モデルと話すことができます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/PopAi/assets/logo.svg\" alt=\"PopAi\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://popai.pro\">PopAi</a> </td>\n        <td>PopAiがDeepSeek R1を発表！PopAiで遅延のない、超高速なパフォーマンスをお楽しみください。 オンライン検索のオン/オフをシームレスに切り替え可能です。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pot-app.com/logo/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a></td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a> 🌈クロスプラットフォームの単語翻訳とOCRソフトウェア </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Byaidu/PDFMathTranslate/raw/main/docs/images/banner.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Byaidu/PDFMathTranslate\">PDFMathTranslate</a></td>\n        <td>この拡張プログラムは、開発者がコード内のコメント、文字列、コードヒント、エラー情報、変数名を翻訳するのに役立ちます。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Richasy/Bili.Copilot/raw/master/assets/StoreLogo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Richasy/Bili.Copilot\">Bili.Copilot</a></td>\n        <td>B局のサードパーティ製Windowsデスクトップクライアント、Windows App SDKを使用して構築されたネイティブアプリケーション。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://www.tensorbounce.com/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.tensorbounce.com/\">LawAgent</a></td>\n        <td>LawAgentは、Tensorbounceチームによって開発された、知識ベースとAIエージェント機能を統合した法律AI製品です。公式の法律関連データを数千万件も保有しており、カスタム知識ベースの設定も可能です。プロフェッショナルモードでは、DeepSeek-R1の推論能力を活用し、ユーザーの法律分析、契約審査、文書生成、ファイル翻訳などの法律シーンをサポートします。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://h1.appinn.me/file/1741929316827_21.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n<td><a href=\"https://github.com/jiqi136/DS-AI\">リアルタイム接続可能なAIアシスタント</a></td>\n<td> AIアシスタントはDeepSeek-V3.1インターフェイスによる最強Claude Codeコードモデルの直連をサポートし、ネットワーク中継サーサーバーを経由せずに利用可能（コスト90%削減）。 画像・PDFファイルの読み込みと無料画像生成機能を搭載；他のAIモデルのカスタム接続が可能；ローカルブラウザを呼び出してリアルタイムWeb検索を実現。さらにR1など無料モデルも選択可能。\n</td>\n\t</tr>\n    <tr>\n    <td><img src=\"docs/remio/assets/remio_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n    <td><a href=\"https://www.remio.ai/\">remio</a></td>\n    <td>remio は AI を活用したパーソナルナレッジハブです。閲覧したウェブコンテンツを自動的に収集し、ローカルファイルを解析し、個人のメモを統合することで、パーソナライズされたナレッジベースを構築します。パーソナルナレッジベース内での検索と自然言語による Q&A を可能にし、即座に洞察を得られるようにします。さらに、あなたのライティングスタイルに適応し、ドラフト作成や改良、コンテンツ完成を簡単に進めるスマートライティング支援も提供します。ローカル優先のストレージ設計により、remio はデータのプライバシーを重視しながら、断片化した情報を一元化し、最大限の生産性を実現します。</td>\n    </tr> \n    <tr>\n    <td><img src=\"docs/DocKit/assets/dockit.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n    <td><a href=\"https://dockit.geekfun.club/\">DocKit</a></td>\n    <td>DocKitは、NoSQLデータベース向けに設計されたAI搭載のデスクトップGUIクライアントで、Mac、Windows、Linuxに対応したElasticsearchとOpenSearchをサポートしています。DeepSeekのような大規模モデルと統合することで、DocKitは開発者が複雑なDSLクエリを作成するのを支援し、データ管理と分析のためのより良い体験を提供します。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/zenfeed/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/glidea/zenfeed\">zenfeed</a> </td>\n        <td> AIでRSSを強化し、重要な情報を自動的にフィルタリング、要約、プッシュして、情報過多を克服します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/NoteGen/NoteGen.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/codexu/note-gen\">NoteGen</a> </td>\n        <td> NoteGenは、AIを使用して記録と執筆を橋渡しし、断片化された知識を読みやすいノートに整理することに専念するクロスプラットフォームのMarkdownノートアプリケーションです。 </td>\n    </tr>\n        <tr>\n        <td> </td>\n        <td> <a href=\"https://github.com/SamYuan1990/i18n-agent-action\">i18n-agent-action</a> </td>\n        <td> i18n Agentは、AIを駆使したツールであり、国際化（i18n）と現地化（l10n）のワークフローを効率化し自動化するように設計されています。先進的な自然言語処理（NLP）と機械学習技術を活用することで、開発者、翻訳者、製品チームが多言語コンテンツを効率的に管理できるよう支援し、人的ミスを排除しつつ全球展開の速度を加速します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://3min.top/imgs/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://3min.top/en\">3mintop</a> </td>\n        <td> DeepSeekモデルを活用して、わずか3分で任意のコンテンツを素早く要約し理解できる強力なAIツール。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cantian.ai/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://cantian.ai/\">Cantian AI</a></td>\n        <td>伝統的な東洋文化に基づく深く構造化された知識ベースを活用する、AIネイティブの専用八字占いサービスです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://obsidian.md/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/TarsLab/obsidian-tars\">Obsidian Tars</a></td>\n        <td> Obsidianのノート編集にLLMの会話を統合し、deepseek-reasonerのチェーン・オブ・ソート(CoT)出力をコールアウト形式で表示します。 </td>\n    </tr>\n        <tr>\n        <td> <img src=\"https://www.chatbotbuilder.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bobbylkchao/chatbotBuilder\">AI Chatbot Builder</a> </td>\n        <td> <a href=\"www.chatbotbuilder.dev/\">Chatbot Builder</a> はオープンソースのプラットフォームで、DeepSeekとOpenAIモデルを統合し、さまざまな対話シナリオに対応したカスタマイズ可能なチャットボットを作成できます。ローコードかつ設定可能な方法で、簡単にインテリジェントな対話体験を構築できます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://bibigpt.co/icons/lucid/icon_32x32@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"http://bibigpt.co\">BibiGPT</a> </td>\n        <td> <a href=\"http://bibigpt.co\">BibiGPT</a> は、ビリビリ動画、YouTube、小紅書、ポッドキャストなどの主要プラットフォームのコンテンツ分析と要約をサポートするAI音声・動画アシスタントで、音声・動画コンテンツの素早い視聴、簡単な検索、効果的な活用を実現します。コンテンツの要約、インタラクティブなQ&A、記事生成などの機能を提供。動画ファイルのアップロード、メモアプリの連携、DeepSeek R1とV3モデルをサポート。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lobehub.com/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://lobehub.com/ja/docs/usage/providers/deepseek\">LobeChat</a> </td>\n        <td> <a href=\"https://lobehub.com\">LobeChat</a> - オープンソースのモダンな AI チャットフレームワーク。DeepSeek R1、ナレッジベース（ファイルアップロード/知識管理/RAG）、マルチモーダル機能（画像認識/音声合成/プラグイン/アーティファクト）に対応。わずか1クリックで、独自の DeepSeek アプリケーションを無料でデプロイ可能。</td>\n    </tr>\n        <tr>\n        <td> <img src=\"./docs/ruzhiai_note/assets/play_store_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/ruzhiai_note/README_cn.md\">如知AIノート</a> </td>\n        <td>如知AIノートは、AIを活用したインテリジェントな知識管理ツールで、AI検索・探索、AI結果のノート変換、ノート管理・整理、知識の表示・共有など、ワンストップの知識管理・応用サービスを提供します。DeepSeek深層思考モデルを統合し、より安定した、より高品質な出力を提供します。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.weiyuai.cn/logo.png\" alt=\"AI Customer Service\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Bytedesk/bytedesk\">Bytedesk</a> </td>\n        <td> AI を活用したライブ チャット、電子メール サポート、オムニチャネル カスタマー サービス、チーム IM を備えた、Slack + zendesk/intercom に代わるエンタープライズ IM ソリューション.</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://raw.githubusercontent.com/rockbenben/subtitle-translator/main/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/rockbenben/subtitle-translator\">Subtitle Translator</a></td>\n        <td>SRT/ASS/VTT/LRC形式に対応したバッチ字幕翻訳ツール。DeepSeekを含む多様なLLMおよび機械翻訳インターフェースと互換性があります。</td>\n    </tr>\n        <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/songquanpeng/one-api/main/web/default/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/songquanpeng/one-api\">One API</a> </td>\n        <td> One API は LLM API 管理＆キー再配布システムで、OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek など複数のプロバイダーを統一 API で管理できます。シングルバイナリ、Docker 対応、すぐに使えます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/guyoung/AIMatrices/raw/main/docs/assets/logo/ai-matrices1.png\" alt=\"AIMatrices 图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/guyoung/AIMatrices/blob/main/README.md\">AIMatrices</a> </td>\n        <td>AIMatricesは、効率的で便利なaiアプリケーション開発体験を開発者に提供するために設計された、軽量、高性能、スケーラブルでオープンソースのaiアプリケーション迅速構築プラットフォームです。複数の高度なテクノロジとツールを統合することで、複雑なコードをゼロから作成することなく、ユーザーがaiアプリケーションを迅速に構築、展開、維持できるようになります。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"agent\">AI エージェントフレームワーク</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://panda.fans/_assets/favicons/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/anda/README.md\">Anda</a> </td>\n        <td>高度にコンポーザブルで自律的かつ永続的な記憶を持つAIエージェントネットワークを構築するために設計されたRustフレームワーク。</td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/173022229\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/APRO-com\">ATTPs</a> </td>\n        <td>エージェント間の信頼できる通信のための基本プロトコルフレームワークです。利用者は<a href=\"https://docs.apro.com/attps\">ATTPs</a>のSDKを導入することで、エージェントの登録、検証可能なデータの送信、検証可能なデータの取得などの機能を利用することができます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/translate.js/assets/icon.png\" alt=\"图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/translate.js/README_ja.md\">translate.js</a> </td>\n        <td>フロントエンド開発者向けのAI i 18 n、2行のjsはhtmlの全自動翻訳を実現し、数十言語のワンクリック切り替えで、ページを変更する必要がなく、言語プロファイルがなく、数十個の微調整拡張命令をサポートし、SEOに友好的である。また、標準テキスト翻訳APIインタフェースを開放する</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/turtlenoir/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://turtlenoir.com/\"> Turtle Noir </a> </td>\n        <td> <a href=\"https://turtlenoir.com/\"> Turtle Noir </a> DeepSeekをベースにしたAI司会者によるウミガメのスープ（水平思考パズル）ゲームで、シングルプレイやマルチプレイに対応しています。AIがゲームの進行やツッコミを行い、「はい / いいえ / 無関係」の回答で推理を進めます。没入感のあるゲームプレイ（より強いストーリーの雰囲気とリズム誘導）、ヒント機能、行き詰まり防止メカニズムを提供し、ベクトル検索 + DeepSeek を組み合わせて問題の重複を防ぎ、コンテンツのモデレーション機能も備えています。気軽な脳トレやオンラインでの交流に適しています。 </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/agentUniverse/assets/agentUniverse_logo_s.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/antgroup/agentUniverse\"> agentUniverse </a> </td>\n        <td> agentUniverseは、複雑なビジネスシーン向けに設計されたマルチエージェント協調フレームワークです。迅速で使いやすい大規模モデルのインテリジェントエージェントアプリケーション構築能力を提供し、特にエージェント間の協調スケジューリング、自律的な意思決定、動的なフィードバックなどのメカニズムに重点を置いています。これは、Ant Groupの金融業界における実践的なビジネス経験に基づいて開発されました。agentUniverseは、2024年6月にDeepSeekシリーズモデルのサポートを全面的に統合しました。  </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/BotSharp/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/SciSharp/BotSharp\"> BotSharp </a> </td>\n        <td> BotSharpは、オープンソースのマルチエージェントアプリケーション開発フレームワークです。シンプルなチャットボットからマルチエージェントの協調、複雑なタスク（例：Text To SQL）まで、すぐに使える方法を提供し、大規模モデルの能力を既存のビジネスシステムに迅速に統合できます。さらに、ナレッジベースや会話管理機能も内蔵しています。このフレームワークはDeepSeek V3モデルで詳細にテストされており、DeepSeek V3の性能のおかげで、他のクローズドソースモデルに劣らないパフォーマンスを発揮します。</td>\n    </tr>\n     <tr>\n        <td width=80> <img src=\"docs/eino/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n            <td> <a href=\"https://github.com/cloudwego/eino\"> Eino </a> </td>\n            <td> Eino (I knowと発音が似ている)は、Go言語で最も優れたLLMアプリケーション開発フレームワークとなることを目指しています。LangChain、LlamaIndexなどのオープンソースコミュニティの優れたLLMフレームワークの設計理念を参考にしながら、最先端の研究成果と実用的な経験を取り入れ、シンプルさ、スケーラビリティ、信頼性、効率性を強調したGo言語プログラミング慣行に準拠したLLMアプリケーション開発フレームワークを提供しています。 </td>\n        </tr>\n    <tr>\n        <td width=80> <img src=\"https://raw.githubusercontent.com/Tencent/Youtu-agent/924aeeb6c49ee524b8bb4de2642a3dc84b7b86b9/docs/assets/mascot.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> は、自律エージェントを構築、実行、および評価するための柔軟で高性能なフレームワークです。ベンチマークテストで最高の成績を収めるだけでなく、このフレームワークは、オープンソースモデルを使用して、データ分析、ファイル処理、詳細な調査などの強力なエージェント機能を提供します。 </td>\n    </tr>\n\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"data\">AIデータアプリケーション開発フレームワーク</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/user-attachments/assets/a327d72f-755f-4256-8a37-32a518a55df3\" alt=\"Icon\" width=\"96\" height=\"auto\" /> </td>\n        <td width=\"120\"> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/dbgpt/README.md\"> DB-GPT </a> </td>\n        <td> DB-GPT は、AWEL (Agentic Workflow Expression Language) とエージェントを備えたオープンソースの AI ネイティブ データ アプリ開発フレームワークです。\nその目的は、マルチモデル管理 (SMMF)、Text2SQL 効果の最適化、RAG フレームワークと最適化、マルチエージェント フレームワークのコラボレーション、AWEL (エージェント ワークフロー オーケストレーション) などの複数の技術機能を開発することにより、大規模モデルの分野でインフラストラクチャを構築し、データベースを中心とした大規模モデル アプリケーションの構築をより簡単かつ便利にすることです。\n </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"rag\">RAG フレームワーク</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/ragflow/README.md\"> RAGFlow </a> </td>\n        <td> 深い文書理解に基づいたオープンソースのRAG（Retrieval-Augmented Generation）エンジン。RAGFlowは、あらゆる規模の企業や個人に対して、ユーザーのさまざまな複雑な形式のデータに対して信頼性のある質問応答と根拠のある引用を提供するための簡素化されたRAGワークフローを提供します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/pingcap/tidb.ai/main/frontend/app/public/nextra/icon-dark.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/autoflow/README.md\"> Autoflow </a> </td>\n        <td> <a href=\"https://github.com/pingcap/autoflow\">AutoFlow</a> は、GraphRAGに基づくオープンソースのナレッジベースツールであり、<a href=\"https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community\">TiDB</a> Vector、LlamaIndex、DSPy の上に構築されています。Perplexity のような検索インターフェースを提供し、シンプルな JavaScript スニペットを埋め込むことで、AutoFlow の対話型検索ウィンドウを簡単にウェブサイトに統合できます。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://assets.zilliz.com/Zilliz_Logo_Mark_White_20230223_041013_86057436cc.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zilliztech/deep-searcher\"> DeepSearcher </a> </td>\n        <td> DeepSearcher は、強力な大規模言語モデル（DeepSeek、OpenAI など）とベクトルデータベース（Milvus など）を組み合わせて、私有データに基づく検索、評価、推論を行い、高精度な回答と包括的なレポートを提供します。</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/OpenSPG/openspg/089188f3e7b0392221f5a8e8f1a3629b6352a6f9/LOGO.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/OpenSPG/KAG/blob/master/README_ja.md\"> KAG </a> </td>\n        <td>KAG は、<a href=\"https://github.com/OpenSPG/openspg\">OpenSPG</a> エンジンと大規模言語モデルに基づく論理的推論質問応答フレームワークです。垂直ドメイン知識ベース用の論理的推論質問応答ソリューションを構築するために使用されます。 KAG は、従来の RAG ベクトル類似度計算の曖昧さと、OpenIE によって導入された GraphRAG のノイズ問題を効果的に克服できます。 KAG は、論理的推論、マルチホップの事実に基づく質問への回答などをサポートします。</td>\n    </tr>\n\t<tr>\n    <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/TencentCloudADP/youtu-graphrag/refs/heads/main/assets/logo.png\" alt=\"Youtu-GraphRAGのアイコン\" width=\"64\" height=\"auto\"/> </td>\n    <td> <a href=\"https://github.com/TencentCloudADP/Youtu-GraphRAG\"> Youtu-GraphRAG </a> </td>\n    <td>Youtu-GraphRAGは、スキーマを通じてグラフの構築、インデックス化、検索を垂直的に統合する新しいグラフ検索拡張生成（GraphRAG）のパラダイムを提案します。これはGraphRAGをエンタープライズレベルアプリケーションへ進化させ、人的介入を最小限に抑えつつシームレスなクロスドメイン適応を可能にします。その特徴は、(i) 動的スキーマ境界抽出、(ii) 包括的なコミュニティ検出アルゴリズム、そして (iii) 反復的な反省と推論のためのスキーマ主導クエリ分解です。</td>\n</tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"fhe\">FHE フレームワーク</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/fhe.mind-network/mind-network-log.png\" alt=\"Icon\" width=\"200\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\"> Mind FHE Rust SDK </a> </td>\n        <td> <p>AI を<b>完全準同型暗号（FHE）</b>で暗号化し、<b>Mind Network</b> と統合してエージェントのコンセンサスを実現するオープンソース SDK。FHE は<b>暗号学の聖杯</b>とされており、<b>復号せずに</b>暗号化データ上で直接計算を実行できます。FHE を活用することで、エージェントは <b>Deepseek</b> を使用しながらプライバシーを保護し、モデルの整合性と計算結果の合意を確保できます。さらに、<b>データを一切公開することなく</b> <b>Mind Network</b> に接続することで、このプロセスが実現されます。この SDK の<a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\">ソースコード</a> は<b>純 Rust</b> で実装されており、<a href=\"https://crates.io/crates/mind_sdk_deepseek\">crates.io</a> からも入手可能です。</p></td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"solana\">Solana フレームワーク</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/solana-agent-kit/assets/sendai-logo.png\" alt=\"Icon\" width=\"128\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sendaifun/solana-agent-kit\"> Solana Agent Kit </a> </td>\n        <td>AIエージェントをSolanaプロトコルに接続するためのオープンソースツールキット。DeepSeek LLMを使用する任意のエージェントが、60以上のSolanaアクションを自律的に実行できます。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"sythetic\">合成データのカテゴリ化</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/192579850?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/DataEval/dingo\"> Dingo </a> </td>\n        <td> 総合的なデータ品質評価ツール。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"im\">IM アプリケーションプラグイン</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/huixiangdou.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/huixiangdou/README_cn.md\">HuixiangDou<br/>(wechat,lark)</a> </td>\n        <td>個人のWeChatおよびFeishuでのドメイン知識アシスタントで、質問に答えることに焦点を当てています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/RockChinQ/QChatGPT/blob/master/res/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/RockChinQ/QChatGPT\">QChatGPT<br/>（QQ）</a> </td>\n        <td> 高い安定性、プラグインサポート、リアルタイムネットワーキングを備えたQQチャットボット。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://nonebot.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/KomoriDev/nonebot-plugin-deepseek\"\">NoneBot<br/>（QQ, Lark, Discord, TG, etc.）</a> </td>\n        <td> NoneBotフレームワークを基に、インテリジェントな会話と深い思考機能をサポートします。QQ/飛書/Discord/Telegram等多种多様なメッセージプラットフォームに対応しています </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Soulter/AstrBot/raw/refs/heads/master/dashboard/src/assets/images/logo-normal.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Soulter/AstrBot/\">AstrBot<br/>（QQ, WeChat, WeCom, Lark, TG, etc.）</a> </td>\n        <td> 大規模言語モデルをサポートするマルチプラットフォームチャットボットおよび開発フレームワーク。RAG、長期記憶、ウェブ検索などの各種LLMエージェント機能をサポートし、プラグイン開発にも対応。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"browser\">ブラウザ拡張機能</span>\n\n<table>\n    <tr>\n        <td><img src=\"./docs/SelectTranslate/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://selecttranslate.com/\">SelectTranslate</a></td>\n        <td>SelectTranslateは、バイリンガルウェブページ翻訳、AI最適翻訳（コピー翻訳）、入力翻訳、PDF翻訳など、革新的で実用的な翻訳機能を備えた、無料かつオープンなAI翻訳拡張機能です。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9d3f42b8-fcd0-47ab-8b06-1dd0554dd80e\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_translate/README.md\"> Immersive Translate </a> </td>\n        <td> Immersive Translateは、バイリンガルのウェブページ翻訳プラグインです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lh3.googleusercontent.com/K9i0qJb8phasC5wWf5T68rhnfvX4swsE0hrhJP-WB3WV7MwE5KpMUIJvHKNHHRE6GKNIvIdTNSWoDMl_NggrmUsaw=s120\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_reading_guide/README.md\"> Immersive Reading Guide </a> </td>\n        <td> サイドバーなし!!! 没入型のAIウェブ要約、質問をする... </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/8a301619-a3de-489b-81fd-69aaa7c1c561\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_box/README.md\"> ChatGPT Box </a> </td>\n        <td> ChatGPT Boxは、ブラウザに統合されたChatGPTで、完全に無料です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c3d9d100-247a-41cc-97c1-10b01ed25e70\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/hcfy/README.md\"> hcfy (划词翻译) </a> </td>\n        <td> hcfy (划词翻译)は、複数の翻訳サービスを統合するウェブブラウザ拡張機能です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.eudic.net/web/trans/en_trans.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Lulu Translate/README.md\"> Lulu Translate </a> </td>\n        <td> このプラグインは、マウス選択翻訳、段落ごとの比較翻訳、およびPDF文書の翻訳機能を提供します。DeepSeek AI、Bing、GPT、Googleなどのさまざまな翻訳エンジンを利用できます。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Bistutu/FluentRead/raw/refs/heads/main/public/icon/192.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fluent.thinkstu.com/\"> FluentRead </a> </td>\n        <td> 誰もが母国語のような読書体験を持つことができる革新的なオープンソースのブラウザ翻訳プラグイン </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/oinzen/RSSFlow-doc/blob/main/docs/images/en/icon64.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://rssflow.oinchain.com\"> RssFlow </a> </td>\n        <td>AIを活用したRSS要約と多次元フィードビューを備えたインテリジェントなRSSリーダーブラウザ拡張機能。コンテンツ理解を強化するためのDeepSeekモデル設定をサポートしています。</td>\n    </tr>\n    <tr>\n<td> <img src=\"./docs/refinereader/assets/refinereader-128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://refinereader.cuihuaer.com\"> Refine Reader </a> </td>\n        <td> AI（DeepSeek、OpenAI等）を使用して記事を素早く理解し要約するためのChrome拡張機能。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Hedwi/deepchat/refs/heads/main/images/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chromewebstore.google.com/detail/deepchat-power-of-deepsee/femhcibnncinlabdboehojdhfcihpkpl?hl=en\"> DeepChat </a> </td>\n        <td>任意のウェブサイト上でサイドバーを開いてDeepSeekとチャットできるChrome拡張機能です。さらに、任意のウェブサイト上の選択したテキストの下にフローティングメニューを表示し、テキストの要約生成、文法チェック、コンテンツの翻訳を行うことができます。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.ncurator.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.ncurator.com/\"> Ncurator </a> </td>\n        <td> ナレッジベース AI Q&Aアシスタント – AIがあなたの知識の整理と分析をお手伝いします</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.typral.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.typral.com/\"> Typral </a> </td>\n        <td>超高速AIライティングアシスタント - AIがあなたの日報、記事、テキストなどを素早く最適化します</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.trancy.org/assets/trancy_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.trancy.org/\"> Trancy </a> </td>\n        <td>イマーシブな二か国語対照翻訳、動画の二か国語字幕、文/単語の選択翻訳プラグイン</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://ziziyi.com/svg/anything_copilot.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/baotlake/anything-copilot\"> Anything Copilot </a> </td>\n        <td> Anything Copilotは、サイドバーから直接主要なAIツールにシームレスにアクセスできるようにするブラウザ拡張機能です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"http://cdn.docky.ai/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/docky-ai/README_ja.md\"> Docky AI </a> </td>\n        <td>Docky AI は強力なブラウザ拡張機能で、サイドバーを通じて複数のAIモデルとリアルタイムで会話することができます。複数モデルとの同時交流をサポートし、ウェブページの閲覧、執筆、翻訳、画像作成を支援します</td>\n    </tr>\n        <tr>\n        <td> <img src=\"./docs/Rearview/assets/favicon.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"./docs/Rearview/README_ja.md\"> RearView </a> </td>\n        <td>Rearview はブラウザ履歴管理拡張機能で、履歴ブラウジング内容の全文検索をサポートし、履歴を会話可能な知識ベースに変換します。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.chatgot.io/chat/assets/imgs/logo@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatgot.io/\"> ChatGOT </a> </td>\n        <td> 生産性を向上させるための無料のAIチャットボットアシスタント </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"vscode\">VS Code 拡張機能</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/e4d082de-6f64-44b9-beaa-0de55d70cfab\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continueは、IDEのオープンソースの自動操縦です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/assets/favicon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/README.md\"> Cline </a> </td>\n        <td> Clineは、CLIとエディタを使用できるAIアシスタントです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Sitoi/ai-commit/refs/heads/main/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Sitoi/ai-commit/blob/main/README.md\"> AI Commit </a> </td>\n        <td> VS Code で AI を使用して git commit message を生成するプラグイン。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/titusTong/seekCodeCopilot/blob/main/assets/SeekCodeCopilotLogo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/titusTong/seekCodeCopilot/blob/main/README.md\"> SeekCode Copilot </a> </td>\n        <td> vscode インテリジェント コーディング アシスタントは、ローカルにデプロイされた DeepSeek モデルの構成をサポートします </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/intellism/vscode-comment-translate/blob/master/doc/image/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/intellism/vscode-comment-translate/blob/master/README_JA.md\"> Comment Translation </a> </td>\n        <td> この拡張により、開発者はコード内のコメント、文字列、コードヒント、エラーメッセージ、変数名を翻訳できます。 </td>\n    </tr>\n        <tr>\n            <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/AITK/assets/AIToolkit.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n            <td> <a href=\"https://code.visualstudio.com/docs/intelligentapps/overview\"> AI Toolkit </a> </td>\n            <td> Visual Studio Code 用 AI Toolkit は、開発者や AI エンジニアが生成 AI モデルを使用してインテリジェントなアプリケーションを構築、テスト、およびデプロイすることを可能にする包括的な拡張機能です。 </td>\n        </tr>\n        <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/joygqz/commit-genie/refs/heads/main/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=joygqz.commit-genie\"> Commit Genie </a> </td>\n        <td> VS Code 用の AI コードレビューおよびコミットメッセージジェネレーター。コードの変更を自動的にレビューし、意味のある標準的なコミットメッセージを生成します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/JohnnyZ93/oai-compatible-copilot/blob/main/assets/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/oai-compatible-copilot/README.md\"> OAI Compatible Provider for Copilot </a> </td>\n        <td> GitHub Copilot で OpenAI 互換の推論プロバイダーを使用するためのオープンソースの VS Code 拡張機能です。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"neovim\">neovim 拡張機能</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/avante.nvim/README.md\"> avante.nvim </a> </td>\n        <td> avante.nvimは、IDEのオープンソースの自動操縦です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/llm.nvim/README.md\"> llm.nvim </a> </td>\n        <td> NeovimでLLMと対話できる無料の大規模言語モデル（LLM）プラグイン。Deepseek、GPT、GLM、Kimi、またはローカルLLM（ollamaなど）など、任意のLLMをサポートします。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/codecompanion.nvim/README.md\"> codecompanion.nvim </a> </td>\n        <td> Neovimでシームレスに統合されたAI駆動のコーディング。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"jetbrains\">JetBrains 拡張機能</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/21520/412905/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ide.unitmesh.cc/quick-start\"> AutoDev </a> </td>\n        <td>‍AutoDevは、JetBrainのIDEでのオープンソースのAIコーディングアシスタントです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/21410/561595/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/21410-onegai-copilot\"> Onegai Copilot </a> </td>\n        <td>Onegai Copilotは、JetBrainのIDEでのAIコーディングアシスタントです。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/e4d082de-6f64-44b9-beaa-0de55d70cfab\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continueは、IDEのオープンソースの自動操縦です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/a18792721831/studyplugin/535b9cab69da0f97b42dcaebb00bb0d4ed15c8a6/translate/src/main/resources/META-INF/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/18336-chinese-english-translate\">Chinese-English Translate</a> </td>\n        <td> JetBrainのIDEでの複数の翻訳サービス。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/24851/659002/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/24851-ai-git-commit\">AI Git Commit</a> </td>\n        <td> このプラグインは、コードの変更に基づいてコミットメッセージを自動生成するためにAIを使用します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/YiiGuxing/TranslationPlugin/blob/master/pluginIcon.svg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://intellij-translation.yiiguxing.top/#/ja/\">IntelliJ Translation Plugin</a> </td>\n        <td> IntelliJベースのIDE向け翻訳プラグイン。OpenAI Translator（DeepSeek・Doubao・Ollamaなど互換）を含む複数翻訳サービスを統合し、IDE内でコメントやドキュメント等のコードテキストを随時直接翻訳可能にします。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"codeeditor\">AI コードエディタ</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://global.discourse-cdn.com/flex020/uploads/cursor1/original/2X/a/a4f78589d63edd61a2843306f8e11bad9590f0ca.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.cursor.com/\"> Cursor </a> </td>\n        <td>‍AIコードエディタ</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://exafunction.github.io/public/images/windsurf/windsurf-app-icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://codeium.com/windsurf\"> WindSurf </a> </td>\n        <td>CodeiumによるVS CodeをベースにしたのAIコードエディタ</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/wusigram/assets/logo-512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wusigram/README.md\"> 无思微程序 </a> </td>\n        <td>モバイルAIプログラミングおよび運用ツール、DeepSeekプログラミングパートナー</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"emacs\">Emacs</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/karthink/gptel\"> gptel </a> </td>\n        <td>EmacsのためのシンプルなLLMクライアント</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/milanglacier/minuet-ai.el\"> Minuet AI </a> </td>\n        <td>コードでインテリジェンスとダンス💃</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n\n###  <span id=\"others\">その他</span>\n\n<table>\n    <tr>\n        <td style=\"font-size: 64px\">🤖</td>\n        <td> <a href=\"https://github.com/wangrongding/wechat-bot/blob/main/README.md\"> Wechat-Bot </a></td>\n        <td> WeChaty をベースに、DeepSeek とその他の AI サービスを組み合わせた WeChat ボットです。 </td>\n    </tr>\n    <tr>\n        <td style=\"font-size: 64px\">&#128032;</td>\n        <td> <a href=\"https://github.com/lunary-ai/abso/blob/main/README.md\"> Abso </a></td>\n        <td> OpenAIフォーマットを使用するあらゆるLLMプロバイダと対話するためのTypeScript SDK.</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/fatwang2/siri-ultra\"> Siri Ultra </a> </td>\n        <td> GitHubで1000以上のスターを獲得した、インターネット接続、マルチターン会話、DeepSeekシリーズモデルをサポートするプロジェクト </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c1e47b01-1766-4f7e-bfe6-ab3cb3991c30\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/tree/main/docs/siri_deepseek_shortcut\"> siri_deepseek_shortcut </a> </td>\n        <td> DeepSeek APIを装備したSiri </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/n8n-io/n8n/blob/master/assets/n8n-logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/rubickecho/n8n-deepseek\"> n8n-nodes-deepseek </a> </td>\n        <td> DeepSeek APIをワークフローに直接統合するためのN8Nコミュニティノード。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/8rF2JOaZ8l9AvM4H6ezliw44aI.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/BerriAI/litellm\"> LiteLLM </a> </td>\n        <td> 100以上のLLM APIをOpenAI形式で呼び出すためのPython SDK、プロキシサーバー（LLMゲートウェイ）。DeepSeek AIもサポートし、コスト追跡も可能です。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.postimg.cc/k5Z4YWjt/Screenshot-2025-01-23-at-6-08-01-PM.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mem0ai/mem0\"> Mem0 </a> </td>\n        <td> Mem0は、AIアシスタントにインテリジェントなメモリレイヤーを追加し、パーソナライズされたインタラクションと継続的な学習を可能にします。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://geneplore.com/img/geneplore_color_logo_circular.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://geneplore.com/bot\"> Geneplore AI </a> </td>\n        <td> Geneplore AIは、Deepseek v3およびR1を搭載した最大のAI Discordボットの1つを運営しています。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.promptfoo.dev/img/logo-panda.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/promptfoo/README.md\"> promptfoo </a> </td>\n        <td> LLMプロンプトをテストおよび評価し、DeepSeekモデルを含む。さまざまなLLMプロバイダーを比較し、回帰をキャッチし、応答を評価します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/ComfyUI-Copilot/assets/logo 2.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/AIDC-AI/ComfyUI-Copilot\"> ComfyUI-Copilot </a> </td>\n        <td> Comfy-UIフレームワーク上に構築されたインテリジェントアシスタント。自然言語による対話を通じて、AIアルゴリズムのデバッグおよびデプロイプロセスを簡素化し、効率化します。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Optima-CityU/llm4ad/blob/main/assets/figs/logo_short.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> は、大規模言語モデル（LLM）を活用した自動アルゴリズム設計のための統一されたオープンソースのPythonベースのプラットフォームです。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/tencent/hunyuan.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tencent/AI-Infra-Guard\"> AI-Infra-Guard </a> </td>\n        <td> テンセント混元セキュリティチーム - AIインフラのセキュリティ評価ツールで、AIシステムにおける潜在的なセキュリティリスクを発見・検出することを目的としています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/yincongcyincong/telegram-deepseek-bot/blob/main/static/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> はDeepSeek AI機能を統合したTelegramボットです。 </td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> は、マルチバックエンドLLMサポートを備えたAI駆動のCLIツールで、コンテキストを考慮したシェルコマンドを生成します。シェル固有の構文、読み取り専用システムツール、カスタム推論エンドポイントに対応しています。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.godtierprompts.com/logo.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a> はコミュニティ主導のリーダーボードで、最高のプロンプトが上位に浮上します。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/89342560?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Jeff2Ma/AlfredWorkflow-DeepSeek\">DeepSeek Alfred WorkFlow</a> </td>\n        <td> MacのAlfredアプリでDeekSeekのワークフローを素早く呼び出す。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/cbf6193b-fd66-4b88-bcf7-98699becf046\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sally-suite/open-office-copilot\">Open Office Copilot</a> </td>\n        <td> Open Office Copilot は、Microsoft Office と Google Workspace をサポートするオープンソースの Office アシスタントで、AI-Agent をベースにしています。Word での執筆、PowerPoint でのスライド生成、Excel でのデータ分析、Outlook でのメール作成などを支援します。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目次\">^ 目次に戻る ^</a></p>\n"
  },
  {
    "path": "README_zh_tw.md",
    "content": "<div align=\"center\">\n\n<p align=\"center\">\n<img width=\"1000px\" alt=\"Awesome DeepSeek Integrations\" src=\"docs/Awesome DeepSeek Integrations.png\">\n</p>\n\n# 精彩的 DeepSeek 整合 ![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)\n\n將 DeepSeek API 整合到流行的軟體中。前往 [DeepSeek 開放平台](https://platform.deepseek.com/) 獲取 API 金鑰。\n\n[English](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README.md)/[簡體中文](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_cn.md)/繁體中文/[日本語](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_ja.md)/[Español](https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/README_es.md)\n</div>\n\n</br>\n</br>\n\n## 目錄\n\n- [精彩的 DeepSeek 整合 ](#精彩的-deepseek-整合-)\n  - [目錄](#目錄)\n  - [項目列表](#項目列表)\n    - [應用](#應用)\n    - [AI 智慧體框架](#ai-智慧體框架)\n    - [數據 AI 應用框架](#數據-ai-應用框架)\n    - [RAG 框架](#rag-框架)\n    - [FHE（全同態加密）框架](#fhe全同態加密框架)\n    - [Solana 框架](#solana-框架)\n    - [合成資料策展](#合成資料策展)\n    - [即時通訊應用插件](#即時通訊應用插件)\n    - [Office插件](#office插件)\n    - [瀏覽器擴展](#瀏覽器擴展)\n    - [VS Code 擴充功能](#vs-code-擴充功能)\n    - [Visual Studio 擴充功能](#visual-studio-擴充功能)\n    - [neovim 擴充功能](#neovim-擴充功能)\n    - [JetBrains 擴充功能](#jetbrains-擴充功能)\n    - [Discord 機器人](#discord-機器人)\n    - [原生 AI 程式碼編輯器](#原生-ai-程式碼編輯器)\n    - [Emacs](#emacs)\n    - [安全性](#安全性)\n    - [供應商](#供應商)\n    - [其他](#其他)\n    - [Star 歷史](#star-歷史)\n\n## 項目列表\n\n###  <span id=\"applications\">應用</span>\n\n<table>\n        <tr>\n        <td><img src=\"docs/operit/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/AAswordman/Operit\">Operit AI</a></td>\n        <td>面向安卓平台的開源系統集成 AI 助手，支持幾乎完整的 mcp 使用，與安卓系統高度兼容。軟件同時具備高度自定義和低門檻的上手體驗，內建文件操作、搜索、自動點擊、格式轉換等工具，並整合了 DeepSeek API 網頁。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/openEuler Intelligence/intelligence_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.openeuler.org/zh/projects/intelligence/\">openEuler Intelligence</a></td>\n        <td>基於 openEuler 的大模型智能平台，深度整合了包括 DeepSeek 在內的主流大語言模型，並具備本地知識庫建構能力。平台提供語義介面註冊、MCP 服務管理、智慧體（Agent）開發及自動化工作流編排等核心功能，同時支援 Web 端和桌面客戶端雙模式存取，顯著提升開發效率與企業級應用體驗！</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/OpenXLab/migo/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://migo.intern-ai.org.cn/\">覓果</a></td>\n        <td> 免費的 AI 創新加速工具，提供智慧問答、論文深度理解、前沿 AI 工具以及個人學術知識庫。作為探索的夥伴，覓果助你發現並實現卓越創意！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/eechat/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://github.com/Lucassssss/eechat\">eechat</a></td>\n        <td> 簡潔易用的大型模型本地部署工具，支援開源模型 DeepSeek-R1、DLlama 3、Phi-4、Mistral、Gemma 3 等模型的本地化隱私部署，同時支援遠端大型模型 API 呼叫。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/aingdesk/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://github.com/aingdesk/AingDesk\">AingDesk</a></td>\n        <td> 一鍵將AI模型部署在你的電腦上，操作可視化，內建精美聊天界面，可線上分享供他人共用，支援 DeepSeek 等其他模型，並提供聯網搜索及第三方API支持。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/dingtalk/assets/dingtalk_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://www.dingtalk.com/\">釘釘</a></td>\n        <td> 釘釘 AI 助理融合了釘釘平台的多項 AI 產品功能，以智能化的方式輔助企業日常工作流程。釘釘 AI 助理具備多種智能能力，包括但不限於智能溝通、智能協同、智能管理等。通過這些功能，AI 助理能夠在企業內部歸納要點、生成會議紀要，並且能夠為用戶推送相關工作任務和日程提醒。此外，釘釘 AI 助理還能夠通過知識庫的能力，智能地回答員工關於企業行政流程、人力資源政策等多個方面的常見問題。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://chatdoc.com/chatdoc/chatdoc.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://chatdoc.com\">ChatDOC</a></td>\n        <td> ChatDOC 是一款由 AI 驅動的文件閱讀工具，配備強大的可追溯性功能，確保每條資訊的來源清晰可驗證，幫助您高效準確地掌握文件的核心內容。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/SwiftChat/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n<td> <a href=\"docs/SwiftChat/README.md\">SwiftChat</a></td>\n<td> <a href=\"https://github.com/aws-samples/swift-chat\">SwiftChat</a> 是一款基於 React Native 構建的閃電般快速的跨平台 AI 聊天應用。它在 Android、iOS 和 macOS 上提供原生性能。功能包括實時流式聊天、豐富的 Markdown 支持、AI 圖像生成、可自定義系統提示、快速模型切換和多模態能力。支持包括 DeepSeek、Amazon Bedrock、Ollama 和 OpenAI 相容模型在內的多個 AI 提供商，具有簡潔的 UI 和高性能。</td>\n    </tr>\n    </tr>\n    <tr>\n        <td> <img src=\"https://4everlogo.4everland.store/logo/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/4EVERChat/README.md\">4EVERChat</a></td>\n        <td> <a href=\"https://chat.4everland.org/\">4EVERChat</a> 是一個整合數百個 LLM 的智慧模型選擇平台，實現模型效能的即時比較。利用 <a href=\"https://www.4everland.org/\">4EVERLAND</a> AI RPC 的統一 API 端點，實現免費切換模型，並自動選擇響應快速且成本低的組合。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/xhai_browser/assets/logo_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"./docs/xhai_browser/README.md\">xhai Browser</a></td>\n        <td> xhai Browser 是一款 Android 桌面管理與 AI 瀏覽器，DeepSeek 是其預設的 AI 對話引擎。具備極致效能（啟動僅需 0.2 秒）、輕量化（apk 僅 3M）、無廣告、超快速廣告攔截、多螢幕分類、螢幕導航、多搜索框、一框多搜索等功能！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.imgur.com/FkbmMVG.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://intellibar.app/\">IntelliBar</a></td>\n        <td> IntelliBar 是一款美觀的 Mac 助手，讓您可以在 Mac 上的任何應用中使用先進的模型，例如 DeepSeek R1——例如在郵件應用中編輯電子郵件或在瀏覽器中摘要文章。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/gptbots/gptbots.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.gptbots.ai/zh_TW/docs\">GPTBots</a></td>\n        <td> <a href=\"https://www.gptbots.ai/zh_TW/\">GPTBots</a> 是一個免程式設計的 AI 智慧體構建平台，整合了多個國際 LLM，包括 DeepSeek。提供基於 RAG 的知識存儲/檢索、工具自訂/調用和工作流程編排模組。此外，還允許將智慧體整合到多個主流平台（如 WhatsApp、Telegram 等），為企業提供端到端的 AI 解決方案，幫助它們在 AI 時代脫穎而出。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/build/icon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td> <a href=\"https://github.com/ThinkInAIXYZ/deepchat/blob/main/README.md\">DeepChat</a></td>\n        <td> DeepChat 是一款完全免費的桌面智慧助手，搭載強大的 DeepSeek 大模型，支援多輪對話、網路搜索、文件上傳、知識庫等功能。</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"https://avatars.githubusercontent.com/u/171659527?s=400&u=39906ab3b6e2066f83046096a66a77fb3f8bb836&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/quantalogic/quantalogic\">Quantalogic</a> </td>\n        <td> QuantaLogic 是一個用於構建先進 AI 智慧體的 ReAct（推理與行動）框架。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/224d547a-6fbc-47c8-859f-aa14813e2b0f\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatbox/README.md\">Chatbox</a> </td>\n        <td> Chatbox 是一款適用於多個尖端 LLM 模型的桌面客戶端，支援 Windows、Mac 和 Linux。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/bb65404c-f867-42d8-ae2b-281fe953ab54\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_next_web/README.md\"> ChatGPT-Next-Web </a> </td>\n        <td> ChatGPT Next Web 是一款跨平台支援的 ChatGPT 網頁 UI，支援 GPT3、GPT4 和 Gemini Pro。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/Casibase/assets/casibase.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://casibase.org/docs/category/beginner-guide/\">Casibase</a></td>\n        <td> <a href=\"https://casibase.org\">Casibase</a> 是一個開源的 AI 知識庫和對話系統，它結合了最新的 RAG 技術、SSO 功能，並支援各種主流 AI 模型。旨在為企業和開發者提供一個功能強大、靈活易用的知識管理和智慧對話平台。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Coco AI/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Coco AI/README.md\">Coco AI</a></td>\n        <td> <a href=\"https://coco.rs\">Coco AI</a> 是一款完全開源、跨平台的統一搜索與生產力工具，連接並搜索各種數據來源，包括應用、文件、Google Drive、Notion、語雀、Hugo 等，涵蓋本地和雲端。通過整合 DeepSeek 等大模型，Coco AI 實現智慧的個人知識管理，注重隱私並支援私人部署，幫助用戶快速且智慧地訪問信息。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/liubai/assets/liubai-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/liubai/README.md\">Liubai</a> </td>\n        <td> Liubai 讓 DeepSeek 擁有手腳，能夠在微信上操作您的筆記、任務、日曆和待辦事項！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1ac9791b-87f7-41d9-9282-a70698344e1d\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/pal/README.md\"> Pal - AI Chat Client<br/>(iOS, ipadOS) </a> </td>\n        <td> Pal 是一款 iOS 上的自訂聊天遊樂場。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.librechat.ai/librechat.svg\" alt=\"LibreChat\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/deepseek\">LibreChat</a> </td>\n        <td> LibreChat 是一款可定制的開源 App，無縫整合 DeepSeek 提升 AI 互動體驗。</td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/longevity-genie/chat-ui/11c6647c83f9d2de21180b552474ac5ffcf53980/static/geneticsgenie/icon-128x128.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/longevity-genie/just-chat\">Just-Chat</a> </td>\n        <td> 快速簡單地創建您的 LLM 智慧體並與之聊天！</td>\n     </tr>\n    <tr>\n        <td> <img src=\"https://www.papersgpt.com/images/logo/favicon.ico\" alt=\"PapersGPT\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/papersgpt/papersgpt-for-zotero\">PapersGPT</a> </td>\n        <td> PapersGPT 是一款 Zotero 插件，無縫整合 DeepSeek 和其他多個 AI 模型，快速閱讀 Zotero 中的論文。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/rss-translator/RSS-Translator/main/core/static/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/rss_translator/README.md\"> RSS Translator </a> </td>\n        <td> 將 RSS 源翻譯成您的語言！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://relingo.net/assets/images/relingo-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://relingo.net\"> Relingo </a> </td>\n        <td> 在瀏覽網站和觀看 YouTube 時構建和掌握詞彙！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/enconvo/README.md\"> Enconvo </a> </td>\n        <td> Enconvo 是 AI 時代的啟動器，是所有 AI 功能的入口點，也是貼心的智慧助手。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/kangfenmao/cherry-studio/blob/main/src/renderer/src/assets/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" style=\"border-radius: 10px\" /></td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cherrystudio/README.md\">Cherry Studio</a></td>\n        <td> 一款為生產者設計的強大桌面 AI 助手。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://tomemo.top/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/tomemo/README.md\"> ToMemo (iOS, ipadOS) </a> </td>\n        <td> 一款短語簿 + 剪貼板歷史 + 鍵盤的 iOS App，整合 AI 巨型建模，用於快速鍵盤輸出。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/buxuku/video-subtitle-master/refs/heads/main/resources/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/buxuku/video-subtitle-master\">Video Subtitle Master</a></td>\n        <td> 批次生成影片字幕，並能將字幕翻譯成其他語言。這是一款客戶端工具，支援 Mac 和 Windows 平台，並整合了多個翻譯服務，如百度、火山引擎、DeepLx、OpenAI、DeepSeek 和 Ollama。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/dist/assets/chatworm-72x72.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/UnknownEnergy/chatgpt-api/blob/master/README.md\">Chatworm</a> </td>\n        <td> Chatworm 是一款適用於多個尖端 LLM 模型的網頁 App，開源且適用於 Android。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/tisfeng/ImageBed/main/uPic/icon_512x512@2x.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tisfeng/Easydict\">Easydict</a></td>\n        <td> Easydict 是一款簡潔易用的翻譯字典 macOS App，讓您輕鬆優雅地查詢單詞或翻譯文本。支援調用大型語言模型 API 進行翻譯。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.raycast.com/favicon-production.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/raycast/README.md\">Raycast</a></td>\n        <td> <a href=\"https://raycast.com/?via=ViGeng\">Raycast</a> 是一款 macOS 的生產力工具，讓您通過幾個按鍵控制工具。支援包括 DeepSeek AI 在內的各種擴展。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/chatpdflocal/assets/chatpdflocal-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.chatpdflocal.com\">ChatPDFLocal</a> </td>\n        <td> ChatPDFLocal 是一款基於 AI 的 macOS App，可以幫助您快速地理解 PDF，它可與 DeepSeek 及多種 AI 模型無縫地協作，提高您的閱讀效率。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://niceprompt.app/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td> \n\t<td> <a href=\"https://niceprompt.app\">Nice Prompt</a></td> \n\t<td> <a href=\"https://niceprompt.app\">Nice Prompt</a> 在您的程式碼編輯器中組織、分享和使用您的提示，支援 Cursor 和 VSCode。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/193405629?s=200&v=4\" alt=\"PHP Client\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-php-client/blob/master/README.md\">PHP Client</a> </td>\n        <td> Deepseek PHP Client 是一個強大且由社群驅動的 PHP 客戶端庫，用於與 Deepseek API 無縫整合。</td>\n    </tr>\n    <tr>\n      <td>\n        <img\n          src=\"https://github.com/tornikegomareli/DeepSwiftSeek/blob/main/logo.webp\"\n          alt=\"DeepSwiftSeek Logo\"\n          width=\"64\"\n          height=\"auto\"\n        />\n      </td>\n      <td>\n        <a href=\"https://github.com/tornikegomareli/DeepSwiftSeek/blob/main/README.md\">DeepSwiftSeek</a>\n      </td>\n      <td>\n        DeepSwiftSeek 是一個輕量但強大的 Swift 客戶端庫，與 DeepSeek API 的整合非常出色。\n        它提供了易於使用的 Swift 並發功能，用於聊天、串流、FIM（中間填充）補全等。\n      </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/958072?s=200&v=4\" alt=\"Laravel Integration\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-php/deepseek-laravel/blob/master/README.md\">Laravel Integration</a> </td>\n        <td> Laravel 的 Deepseek PHP 客戶端封裝，用於與 Laravel 應用無縫整合 Deepseek API。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/cohesion-org/deepseek-go/refs/heads/main/internal/images/deepseek-go.png\" alt=\"Go Client\" width=\"64\" height=\"auto\"> </td>\n        <td> <a href=\"https://github.com/cohesion-org/deepseek-go/blob/main/README.md\">Deepseek Go</a> </td>\n        <td> Go 的 Deepseek 用戶端，支援聊天與推理模型。 同時支援 Azure、OpenRouter 等外部供應商。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/zotero/assets/zotero-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/zotero/README_cn.md\">Zotero</a></td>\n        <td> <a href=\"https://www.zotero.org\">Zotero</a> 是一款免費、易用的工具，幫助您收集、組織、註解、引用和分享研究資料。可使用 Deepseek 作為翻譯服務。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://b3log.org/images/brand/siyuan-128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/SiYuan/README.md\">SiYuan</a> </td>\n        <td> SiYuan 是一款注重隱私的個人知識管理系統，支援完全離線使用以及端到端加密數據同步。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/ArvinLovegood/go-stock/raw/master/build/appicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/ArvinLovegood/go-stock/blob/master/README.md\">go-stock</a> </td>\n        <td> go-stock 是一款由 Wails 使用 NativeUI 構建的中國股票數據查看器，並由 LLM 提供支援。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/102771702?s=200&v=4\" alt=\"Wordware\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wordware/README.md\">Wordware</a> </td>\n        <td> <a href=\"https://www.wordware.ai/\">Wordware</a> 是一款工具包，讓任何人僅使用自然語言即可構建、迭代和部署其 AI 堆棧。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/xRJ6vNo9mUYeVNxt0KITXCXEuSk.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/langgenius/dify/\">Dify</a> </td>\n        <td> <a href=\"https://dify.ai/\">Dify</a> 是一個 LLM 應用開發平台，支援 DeepSeek 模型，用於創建助手、工作流程、文本生成器等。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/enricoros/big-AGI/refs/heads/v2-dev/public/favicon.ico\" alt=\"Big-AGI\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/enricoros/big-AGI/blob/v2-dev/README.md\">Big-AGI</a> </td>\n        <td><a href=\"https://big-agi.com/\">Big-AGI</a> 是一款突破性的 AI 套件，旨在讓每個人都能平等地獲得先進的人工智慧。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/LiberSonora/LiberSonora/blob/main/assets/avatar.jpeg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/LiberSonora/LiberSonora/blob/main/README_en.md\">LiberSonora</a> </td>\n        <td> LiberSonora，意為「自由之聲」，是一款由 AI 驅動的強大開源有聲書工具包，包含智慧字幕提取、AI 標題生成、多語言翻譯等功能，支援 GPU 加速和批次離線處理。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/ripperhe/Bob/master/docs/_media/icon_128.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a></td>\n        <td> <a href=\"https://bobtranslate.com/\">Bob</a> 是一款 macOS 翻譯與 OCR 工具，可直接在任何應用中使用，開箱即用！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://agenticflow.ai/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a> </td>\n        <td> <a href=\"https://agenticflow.ai/\">AgenticFlow</a> 是一個免程式設計的平台，讓行銷人員構建代理型 AI 工作流程，用於市場推廣自動化，並由數百個日常應用作為 AI 智慧體的工具提供支援。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/STranslate/STranslate/refs/heads/main/images/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a></td>\n        <td> <a href=\"https://stranslate.zggsong.com/\">STranslate</a>（Windows）是一款由 WPF 開發的即用型翻譯 OCR 工具。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://devinci.onicai.com/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://devinci.onicai.com/\">DeVinci</a></td>\n        <td> <a href=\"https://devinci.onicai.com/\">DeVinci</a> 是端到端去中心化 AI 聊天應用程式，可與開源 LLM 私下聊天。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/5e16beb0-993e-47bf-807e-7c8804b313a2\" alt=\"Asp Client\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Anwar-alhitar/Deepseek.Asp.Client/blob/master/README.md\">ASP Client</a> </td>\n        <td> <a href=\"https://github.com/Anwar-alhitar/Deepseek.Asp.Client/blob/master/README.md\">Deepseek.ASPClient</a> 是一款輕量級的 ASP.NET 封裝，用於簡化 .NET 應用中的 AI 驅動文本處理。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.gptaiflow.tech/logo.png\" alt=\"gpt-ai-flow-logo\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.gptaiflow.tech/docs/product/api-keys-setup#setup-deepseek-api-keys\">GPT AI Flow</a></td>\n        <td>\n            工程師為效率愛好者（自己）打造的終極生產力武器：<a href=\"https://www.gptaiflow.tech/\">GPT AI Flow</a>\n            <ul>\n                <li>`Shift+Alt+Space` 啟動桌面智慧中樞</li>\n                <li>本地加密儲存</li>\n                <li>自定義指令引擎</li>\n                <li>按需使用，無需訂閱綁定</li>\n            </ul>\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/b09f17a8-936d-4dac-8b24-1682d52c9a3c\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/alecm20/story-flicks\">Story-Flicks</a></td>\n        <td> 只需一句話，即可快速生成高清故事短影片，支援 DeepSeek 等模型。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://prompt.16x.engineer/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/16x_prompt/README.md\">16x Prompt</a> </td>\n        <td> <a href=\"https://prompt.16x.engineer/\">16x Prompt</a> 是一款具備情境管理功能的 AI 編碼工具。幫助開發者管理源代碼情境，並為現有代碼庫中的複雜編碼任務生成提示。</td>\n    </tr>\n        <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/assets/favicon1.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/Alpha派/README.md\"> Alpha 派 </a> </td>\n        <td> AI 研究助理 / 下一代由 AI 驅動的金融資訊門戶。<br>代替投資者參加會議並記錄筆記，同時提供金融資訊搜索與問答服務，以及投資研究的定量分析。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://docs.xark-argo.com/img/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.xark-argo.com\">argo</a> </td>\n        <td>在 Mac/Windows/Linux 上本地下載並運行 Ollama 和 Huggingface 模型，並支援 RAG。也支援 LLM API。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.petercat.ai/images/favicon.ico\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.petercat.ai\">PeterCat</a> </td>\n        <td> 一個對話式問答代理配置系統，提供自託管部署解決方案，以及方便的一體化應用 SDK，讓您能為您的 GitHub 存儲庫創建智慧問答機器人。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/labring/FastGPT/refs/heads/main/.github/imgs/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fastgpt.cn/en\">FastGPT</a> </td>\n        <td>\n            FastGPT 是一個基於大型語言模型（LLMs）的開源 AI 知識庫平台，支援包括 DeepSeek 和 OpenAI 在內的多種模型。我們提供即開即用的數據處理、模型調用、RAG 檢索和可視化 AI 工作流編排功能，讓您輕鬆構建複雜的 AI 應用。\n        </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/ruzhiai_note/assets/play_store_512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/ruzhiai_note/README.md\">RuZhi AI Notes</a> </td>\n        <td> RuZhi AI Notes 是一款由 AI 驅動的智慧知識管理工具，提供一站式知識管理與應用服務，包括 AI 搜索與探索、將 AI 結果轉換為筆記、筆記管理與組織、知識展示與分享。整合 DeepSeek 模型，提供更穩定和高質量的輸出。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cdn.link-ai.tech/doc/CoW%20logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zhayujie/chatgpt-on-wechat\">Chatgpt-on-Wechat</a> </td>\n        <td> Chatgpt-on-Wechat(CoW) 是一個靈活的聊天機器人框架，支援將多個 LLM（包括 DeepSeek、OpenAI、Claude、Qwen 等）無縫整合到常用平台或辦公軟體中，如微信公眾號、企業微信、飛書、釘釘和網站。還支援廣泛的自定義插件。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://athenalab.ai/assets/favicon/favicon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://athenalab.ai/\">Athena</a> </td>\n        <td> 全球首個具備先進認知架構和類人推理能力的自動化通用 AI，旨在解決複雜的現實世界挑戰。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://maxkb.cn/images/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/1Panel-dev/MaxKB\">MaxKB</a> </td>\n        <td> <a href=\"https://maxkb.cn/\">MaxKB</a> 是一款即開即用且靈活的 RAG 聊天機器人。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/TigerGPT/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ttm.financial/gpt\">TigerGPT</a> </td>\n        <td> TigerGPT 是基於 OpenAI 的首款金融 AI 投資助理，由老虎集團開發。TigerGPT 旨在為投資者提供智慧投資決策支援。2025 年 2 月 18 日，TigerGPT 正式整合 DeepSeek-R1 模型，為用戶提供支援深度推理的在線問答服務。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/HIX.AI/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://hix.ai\">HIX.AI</a> </td>\n        <td> 免費試用 DeepSeek，享受無限制的 AI 聊天。在 HIX.AI 上使用 DeepSeek R1 進行 AI 聊天、寫作、編碼等。立即體驗下一代 AI 聊天！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/sharmt1411/askanywhere/blob/main/icon/Depth_8,_Frame_0explore-%E8%A7%92%E6%A0%87.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/sharmt1411/askanywhere\">Askanywhere</a> </td>\n        <td> 隨時選擇文字並開始與 DeepSeek 對話。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/OJZen/1chat/raw/refs/heads/main/doc/assets/icon.ico?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/OJZen/1chat\">1chat</a> </td>\n        <td> 一款 iOS 應用，可讓您在本機與 DeepSeek-R1 模型進行聊天。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://chatlabsai.com/assets/logo/logo.png\" alt=\"iOS AI Chatbot\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chatlabsai.com\">Access 250+ text, image LLMs in one app</a> </td>\n        <td> 1AI iOS 聊天機器人整合了 250 多種文本、圖像、語音模型，讓用戶能與包括 DeepSeek R1 和 DeepSeek V3 模型在內的任何模型進行聊天。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/PopAi/assets/logo.svg\" alt=\"PopAi\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://popai.pro\">PopAi</a> </td>\n        <td> PopAi 推出 DeepSeek R1！享受零延遲與超高速效能，輕鬆切換在線搜索開關。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pot-app.com/logo/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a></td>\n        <td> <a href=\"https://pot-app.com/\">Pot</a> 🌈一個跨平臺的劃詞翻譯和OCR軟件 </td>\n    </tr>\n    <tr>\n        <td><img src=\"https://github.com/Byaidu/PDFMathTranslate/raw/main/docs/images/banner.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/Byaidu/PDFMathTranslate\">PDFMathTranslate</a></td>\n        <td> PDFMathTranslate 是一款以 AI 為基礎的全文雙語翻譯工具，可完全保留 PDF 文件的版面設計。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Richasy/Bili.Copilot/raw/master/assets/StoreLogo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://github.com/Richasy/Bili.Copilot\">嗶哩助理</a></td>\n        <td> Bilibili 第三方 Windows 桌面用戶端，使用 Windows App SDK 構建的原生應用。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.tensorbounce.com/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://github.com/jiqi136/DS-AI\">LawAgent</a></td>\n        <td> LawAgent 是 Tensorbounce 團隊出品的知識庫結合 AI Agent 的法律 AI 產品，擁有上千萬官方法律相關知識庫數據，也允許客製化的知識庫配置。專業模式利用 DeepSeek-R1 的推理能力，協助使用者進行法律分析、合約審查、文件產生、檔案翻譯及其他法律情境。</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/AlphaBot/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://alphabot.x-pai.com/\">AlphaBot</a> </td>\n        <td> AlphaBot 是一款智慧型股票分析助手，結合多源資料與 AI 分析技術，提供技術分析、預測、風險評估等功能，協助投資人做出以資料為導向的交易決策。 支援一鍵部署，操作簡單，支援Windows/Linux/MacOS等平台。</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://h1.appinn.me/file/1741929316827_21.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/jiqi136/DS-AI\">即時連網AI助手</a></td>\n        <td> AI助手支援DeepSeek-V3.1介面直連最強Claude Code代碼模型，無需網路中轉即可使用（成本直降90%）。 支援圖片、PDF檔案讀取及免費生成圖片；可自訂接入其他AI模型；支援呼叫本地瀏覽器即時聯網檢索海量網頁內容。另提供R1等免費模型選擇。\n</td>\n\t</tr>\n    <tr>\n        <td><img src=\"docs/remio/assets/remio_icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://www.remio.ai/\">remio</a></td>\n        <td> remio 是一個 AI 驅動的個人知識中心，通過自動捕獲瀏覽的網頁內容、解析本地文件並整合個人筆記，構建個性化的知識庫。它支持在個人知識庫中進行搜索和自然語言問答，以提供即時洞察，同時提供智能寫作輔助——適應您的寫作風格，輕鬆簡化起草、潤色和完成內容的過程。remio 採用本地優先儲存設計，優先保護數據隱私，同時集中管理零散信息，以實現最大化的生產力。</td>\n    </tr> \n    <tr>\n        <td><img src=\"docs/DocKit/assets/dockit.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://dockit.geekfun.club/\">DocKit</a></td>\n        <td>DocKit是一個AI驅動的桌面GUI客戶端，專為NoSQL數據庫設計，支持Mac、Windows和Linux上的Elasticsearch和OpenSearch。通過集成DeepSeek等大型模型，DocKit可以幫助開發者編寫複雜的DSL查詢，並為數據管理和分析提供更好的體驗。 </td>\n    </tr> \n    <tr>\n        <td> <img src=\"docs/zenfeed/assets/icon.png\" alt=\"圖示\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/glidea/zenfeed\">zenfeed</a> </td>\n        <td> 用 AI 賦能 RSS，自動篩選、總結、推送重要資訊，告別資訊過載。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/NoteGen/NoteGen.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/codexu/note-gen\">NoteGen</a> </td>\n        <td> NoteGen 是一款跨平台的 Markdown 筆記應用，致力於使用 AI 建立記錄和寫作的橋樑，將碎片化知識整理成一篇可讀的筆記。 </td>\n    </tr>\n    <tr>\n        <td> </td>\n        <td> <a href=\"https://github.com/SamYuan1990/i18n-agent-action\">i18n-agent-action</a> </td>\n        <td> i18n Agent是一款人工智能驱动的工具，旨在简化和自动化国际化（i18n）与本地化（l10n）工作流程。它通过先进的自然语言处理（NLP）和机器学习技术，帮助开发者、翻译人员和产品团队高效管理多语言内容——既能消除人工错误，又能加速全球部署进程。 </td>\n    </tr>\n        <tr>\n        <td><img src=\"https://raw.githubusercontent.com/rockbenben/subtitle-translator/main/public/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/rockbenben/subtitle-translator\">Subtitle Translator</a></td>\n        <td>支援 SRT/ASS/VTT/LRC 格式的批量字幕翻譯工具，兼容 DeepSeek 等多種大模型接口和機器翻譯接口。</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/turtlenoir/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://haiguitang.net/\"> Turtle Noir </a> </td>\n        <td> <a href=\"https://haiguitang.net/\"> Turtle Noir </a> 基於 DeepSeek 的 AI 主持人海龜湯 / 側向思維解謎產品，可單人或者多人遊玩。AI 進行控場與吐槽，圍繞「是 / 否 / 無關」的問答推進推理；提供沉浸式玩法（更強劇情氛圍與節奏引導）、引導提示與防卡關機制，同時結合向量檢索 + DeepSeek 進行題目去重，並提供內容審核能力。適合輕量腦洞訓練與在線陪玩。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"agent\">AI 智慧體框架</span>\n\n<table>\n    <tr>\n        <td width=80> <img src=\"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolagents/mascot_smol.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/huggingface/smolagents/tree/main\"> smolagents </a> </td>\n        <td> 建立優質智慧體的最簡單方式。開發者撰寫 Python 程式碼來調用工具並協調其他智慧體。優先支援像 DeepSeek-R1 這樣的開放模型！</td>\n    </tr>\n    <tr>\n        <td><img src=\"https://yomo.run/yomo-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/yomo/README.md\">YoMo</a></td>\n        <td> 有狀態的無伺服器大型語言模型（LLM）函數調用框架，支援強類型語言。</td>\n     </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/superagentxai/superagentX/refs/heads/master/docs/logo/icononly_transparent_nobuffer.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/superagentx/README.md\">SuperAgentX</a> </td>\n        <td> SuperAgentX：一個輕量級的開源 AI 框架，專為具備 AGI 能力的自主多智慧體應用設計。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://panda.fans/_assets/favicons/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/anda/README.md\">Anda</a> </td>\n        <td> 一個用於 AI 智慧體開發的 Rust 框架，旨在構建高度可組合、自主且持續記憶的 AI 智慧體網絡。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://rig.rs/assets/favicon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" alt=\"Rig (Rust)\" /> </td>\n        <td> <a href=\"https://rig.rs\">RIG</a> </td>\n        <td> 在 Rust 中構建模組化且可擴展的大型語言模型應用程式。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/longevity-genie/chat-ui/11c6647c83f9d2de21180b552474ac5ffcf53980/static/geneticsgenie/icon-128x128.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/longevity-genie/just-agents\">Just-Agents</a> </td>\n        <td> 一個輕量級、簡單明瞭的大型語言模型智慧體庫——沒有過度設計，只有簡單易用！</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://alice.fun/alice-logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bob-robert-ai/bob/blob/main/alice/readme.md\">Alice</a> </td>\n        <td> 一個基於 ICP 的自主 AI 智慧體，利用大型語言模型（如 DeepSeek）進行鏈上決策。Alice 結合了實時數據分析和生動有趣的個性，來管理代幣、挖掘 BOB 並治理生態系統。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Upsonic/Upsonic/blob/9d2e6d43b44defc6744817330625661ca3a2184e/Upsonic%20pp.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Upsonic/Upsonic\">Upsonic</a> </td>\n        <td> Upsonic 提供了一個尖端的企業級智慧體框架，您可以協調大型語言模型調用、智慧體和計算機使用，以具成本效益地完成任務。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/173022229\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/APRO-com\">ATTPs</a> </td>\n        <td> 一個用於智慧體之間可信通信的基礎協議框架。任何基於 DeepSeek 的智慧體，通過整合 <a href=\"https://docs.apro.com/attps\">ATTPs</a> SDK，可以訪問智慧體註冊、發送可驗證數據和檢索可驗證數據等功能，從而實現與其他平台智慧體的可信通信。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/translate.js/assets/icon.png\" alt=\"图标\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/translate.js/README.md\">translate.js</a> </td>\n        <td> 專為前端開發者設計的 AI 國際化工具。只需兩行 JavaScript 即可實現全自動 HTML 翻譯。您可以一鍵切換多種語言，無需修改頁面或語言配置檔案，並支援多種微調擴展指令。對搜尋引擎優化（SEO）友好。此外，它還開放了一個標準文本翻譯 API 介面。</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/agentUniverse/assets/agentUniverse_logo_s.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/antgroup/agentUniverse\"> agentUniverse </a> </td>\n        <td> agentUniverse 是一個專為複雜業務場景設計的多智慧體協作框架。它為大型語言模型智慧體應用提供快速且易於使用的開發能力，專注於智慧體協作調度、自主決策和動態反饋等機制。該框架源自螞蟻集團在金融行業的實際業務實踐。2024 年 6 月，agentUniverse 正式支援 DeepSeek 系列模型。</td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"docs/BotSharp/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/SciSharp/BotSharp\"> BotSharp </a> </td>\n        <td> BotSharp 是一個開源的多智慧體應用開發框架，從簡單的聊天機器人，到多智慧體協作，以及複雜的任務如【Text To Sql】框架都提供了開箱即用的使用方法，可以快速地將大模型的能力接入到現有的業務系統中，並且內建知識庫和會話管理功能等，框架使用 DeepSeek V3 的模型進行了詳細的測試，得益於 DeepSeek V3 的性能，框架的表現不輸其他的閉源模型。 </td>\n    </tr>\n     <tr>\n        <td width=80> <img src=\"docs/eino/assets/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n            <td> <a href=\"https://github.com/cloudwego/eino\"> Eino </a> </td>\n            <td> Eino（發音類似\"I know\"）旨在成為Go語言中最優秀的LLM應用開發框架。它借鑒了LangChain、LlamaIndex等開源社區優秀LLM框架的設計理念，同時吸收了前沿研究成果和實際應用經驗，提供了一個更符合Go語言編程慣例的LLM應用開發框架，強調簡潔性、可擴展性、可靠性和高效性。 </td>\n    </tr>\n    <tr>\n        <td width=80> <img src=\"https://raw.githubusercontent.com/Tencent/Youtu-agent/924aeeb6c49ee524b8bb4de2642a3dc84b7b86b9/docs/assets/mascot.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> </td>\n        <td> <a href=\"https://github.com/Tencent/Youtu-agent/\"> Youtu-Agent </a> 是一個靈活、高性能的框架，用於構建、運行和評估自主智能體。除了在基準測試中名列前茅，該框架還提供了強大的智能體能力，採用開源模型即可實現例如數據分析、文件處理、深度研究等功能。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"data\">數據 AI 應用框架</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/user-attachments/assets/a327d72f-755f-4256-8a37-32a518a55df3\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td width=\"120\"> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/dbgpt/README.md\"> DB-GPT </a> </td>\n        <td> 🤖 DB-GPT 是一個開源 AI 原生數據應用開發框架，具備 AWEL（智慧體工作流程表達語言）和智慧體功能。\n其目的是在大模型領域構建基礎設施，通過多種技術能力的開發，如多模型管理 (SMMF)、Text2SQL 效果優化、RAG 框架及優化、多智慧體框架協作、AWEL（智慧體工作流程編排）等，讓數據的大模型應用變得更簡單、更方便。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"rag\">RAG 框架</span>\n\n<table>\n    <tr>\n        <td width=\"80\"> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/ragflow/README.md\"> RAGFlow </a> </td>\n        <td> 一個基於深度文件理解的開源 RAG（檢索增強生成）引擎。它為任何規模的企業提供簡化的 RAG 工作流程，結合 LLM（大型語言模型）提供準確的問答能力，並以來自各種複雜格式資料的可信引用為支撐。</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/pingcap/tidb.ai/main/frontend/app/public/nextra/icon-dark.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/autoflow/README.md\"> Autoflow </a> </td>\n        <td> <a href=\"https://github.com/pingcap/autoflow\">AutoFlow</a> 是一個基於 GraphRAG（基於圖的檢索增強生成）的開源知識庫工具，構建於 <a href=\"https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community\">TiDB</a> Vector、LlamaIndex 和 DSPy 之上。它提供類似 Perplexity 的搜尋介面，並允許透過嵌入簡單的 JavaScript 程式碼片段，輕鬆將 AutoFlow 的對話式搜尋視窗整合到您的網站中。</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://assets.zilliz.com/Zilliz_Logo_Mark_White_20230223_041013_86057436cc.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/zilliztech/deep-searcher\"> DeepSearcher </a> </td>\n        <td> DeepSearcher 結合了強大的 LLM（DeepSeek、OpenAI 等）和向量資料庫（Milvus 等），基於私有資料進行搜尋、評估和推理，提供高度準確的答案和全面的報告。</td>\n    </tr>\n    <tr>\n        <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/OpenSPG/openspg/089188f3e7b0392221f5a8e8f1a3629b6352a6f9/LOGO.png\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://github.com/OpenSPG/KAG/blob/master/README.md\"> KAG </a> </td>\n        <td> KAG 是一個基於 <a href=\"https://github.com/OpenSPG/openspg\">OpenSPG</a> 引擎和大型語言模型的邏輯推理與問答框架，用於構建垂直領域知識庫的邏輯推理與問答解決方案。KAG 能夠有效克服傳統 RAG 向量相似性計算的模糊性以及 OpenIE 引入的 GraphRAG 噪音問題。KAG 支援邏輯推理和多跳事實問答等功能。</td>\n    </tr>\n\t<tr>\n    <td width=\"80\"> <img src=\"https://raw.githubusercontent.com/TencentCloudADP/youtu-graphrag/refs/heads/main/assets/logo.png\" alt=\"Youtu-GraphRAG 圖示\" width=\"64\" height=\"auto\"/> </td>\n    <td> <a href=\"https://github.com/TencentCloudADP/Youtu-GraphRAG\"> Youtu-GraphRAG </a> </td>\n    <td>Youtu-GraphRAG 提出了一種新的圖檢索增強生成範式，通過模式垂直統一了圖構建、索引和檢索。它將 GraphRAG 推向企業級應用，只需最少的人為干預即可實現無縫跨領域適應，具有：(i) 動態模式邊界提取；(ii) 全面的社群檢測算法；以及 (iii) 用於迭代反思和推理的模式指導查詢分解。</td>\n</tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"fhe\">FHE（全同態加密）框架</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/fhe.mind-network/mind-network-log.png\" alt=\"Icon\" width=\"200\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\"> Mind FHE Rust SDK </a> </td>\n        <td> <p>一個用於加密 AI 的開源 SDK，基於全同態加密（FHE）並與 Mind Network 整合以實現代理共識。FHE 被認為是密碼學的<b>最高境界</b>，允許直接在加密資料上進行運算而無需解密。透過 FHE，代理可以在使用 Deepseek 的同時保護隱私，確保模型完整性和結果共識——<b>完全不暴露資料</b>——透過連接到 Mind Network。該 SDK 的<a href=\"https://github.com/mind-network/mind-sdk-deepseek-rust\">原始碼</a>完全使用<b>Rust</b>實現，並且該套件也可在<a href=\"https://crates.io/crates/mind_sdk_deepseek\">crates.io</a>上獲得。</p> </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"solana\">Solana 框架</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/solana-agent-kit/assets/sendai-logo.png\" alt=\"Icon\" width=\"128\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/solana-agent-kit/README.md\"> Solana Agent Kit </a> </td>\n        <td> 一個用於將 AI 智慧體連接到 Solana 協議的開源工具包。現在，任何使用 Deepseek LLM 的智慧體都可以自主執行 60 多個 Solana 操作，例如交易處理和智慧合約部署：</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"sythetic\">合成資料策展</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/bespokelabsai/curator/main/docs/Bespoke-Labs-Logomark-Red-crop.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/curator/README.md\"> Curator </a> </td>\n        <td> 一個用於後訓練 LLM 的大規模資料集策展的開源工具。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/8455694b-c52e-40ec-847e-adf6a5ac064f\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Kiln-AI/Kiln\"> Kiln </a> </td>\n        <td>生成合成資料集並將 R1 模型蒸餾為自訂微調模型。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/192579850?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/DataEval/dingo\"> Dingo </a> </td>\n        <td> Dingo：一個全面的資料品質評估工具。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"im\">即時通訊應用插件</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/huixiangdou.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/huixiangdou/README_cn.md\">HuixiangDou<br/>(微信, 飛書)</a> </td>\n        <td> 專為專業用戶設計的個人微信和飛書中的領域知識助手，專注於回答問題。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/RockChinQ/LangBot/blob/master/res/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/RockChinQ/LangBot\">LangBot<br/>（QQ, 飛書, 企業微信）</a> </td>\n        <td> 基於 LLM 的即時通訊機器人框架，適用於多種企業場景，支援 QQ、飛書、企業微信等多個平台。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://nonebot.dev/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/KomoriDev/nonebot-plugin-deepseek\">NoneBot<br/>（QQ, 飛書, Discord, TG 等）</a> </td>\n        <td> 基於 NoneBot 框架，提供智慧聊天和深度思考功能，支援 QQ、飛書、Discord、TG 等多個平台。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Soulter/AstrBot/raw/refs/heads/master/dashboard/src/assets/images/logo-normal.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Soulter/AstrBot/\">AstrBot<br/>（QQ, 微信, 企業微信, 飛書, TG 等）</a> </td>\n        <td> 易上手的大模型多平台聊天機器人及開發框架。支援長期記憶、RAG、LLM 代理(agents)和外掛程式整合。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"office\">Office插件</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://www.44886.com/view/img/bukeng.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.bukenghezi.com/\">BKOffice</a> </td>\n        <td> 支援 Word、Excel 和 PPT 套件的 Office 外掛程式 (也支援 WPS 套件)，可為 Office 增加 300 多項功能。</td>\n    </tr>\n      <tr>\n        <td> <img src=\"https://www.aippt.cn/_nuxt/logo_cn.eYEokZzA.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.aippt.cn/\">AiPPT</a> </td>\n        <td> AiPPT.com，超過2000萬用戶選擇，一句話，一分鐘，一次點擊生成PPT。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/office-sec/OfficeAI/blob/main/logo/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/office-sec/OfficeAI\">OfficeAI Assistant</a> </td>\n        <td> OfficeAI Assistant 是一款免費的 Office 外掛程式，可在 Office 內提供 AI 問答、AI 校對、AI 排版、AI 創作、AI 資料處理等功能。 它可以提高辦公效率，並與 Microsoft Office 和 WPS Office 相容。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"browser\">瀏覽器擴展</span>\n\n<table>\n    <tr>\n        <td><img src=\"./docs/SelectTranslate/assets/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://selecttranslate.com/\">精挑翻譯</a></td>\n        <td>一款免費開放的 AI 翻譯插件，具備雙語網頁翻譯、擇優翻譯（文案翻譯）、輸入翻譯、PDF 翻譯等創新實用的翻譯功能。</td>\n    </tr>\n    <tr>\n        <td><img src=\"docs/OpenXLab/migo/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td><a href=\"https://chromewebstore.google.com/detail/cjapgnecnkblehipjghhegiccobeloka?utm_source=item-share-cb\">覓果</a></td>\n        <td> 提供全面的文本處理、資訊檢索與知識問答功能，靈活適配多種線上辦公與科研場景（如飛書、arXiv、Overleaf 等），助力高效智慧化工作流程。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9d3f42b8-fcd0-47ab-8b06-1dd0554dd80e\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_translate/README.md\"> Immersive Translate </a> </td>\n        <td> Immersive Translate 是一個雙語網頁翻譯插件，支援多種語言的即時切換。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://lh3.googleusercontent.com/K9i0qJb8phasC5wWf5tU68rhnfvX4swsE0hrhJP-WB3WV7MwE5KpMUIJvHKNHHRE6GKNIvIdTNSWoDMl_NggrmUsaw=s120\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/immersive_reading_guide/README.md\"> Immersive Reading Guide </a> </td>\n        <td> 無側邊欄！沉浸式 AI 網頁摘要，提問功能...</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/8a301619-a3de-489b-81fd-69aaa7c1c561\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/chatgpt_box/README.md\"> ChatGPT Box </a> </td>\n        <td> ChatGPT Box 是一個瀏覽器中的 ChatGPT 整合工具，完全免費。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c3d9d100-247a-41cc-97c1-10b01ed25e70\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/hcfy/README.md\"> hcfy (劃詞翻譯) </a> </td>\n        <td> hcfy (劃詞翻譯) 是一個網頁瀏覽器擴展，整合了多個翻譯服務。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.eudic.net/web/trans/en_trans.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Lulu Translate/README.md\"> Lulu Translate </a> </td>\n        <td> 該插件提供滑鼠選擇翻譯、逐段對比翻譯和 PDF 文件翻譯功能。它可以使用多種翻譯引擎，如 DeepSeek AI、Bing、GPT、Google 等。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Bistutu/FluentRead/raw/refs/heads/main/public/icon/192.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://fluent.thinkstu.com/\"> FluentRead </a> </td>\n        <td> 一個革命性的開源瀏覽器翻譯插件，讓每個人都能擁有母語般的閱讀體驗。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.ncurator.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.ncurator.com/\"> Ncurator </a> </td>\n        <td> 知識庫 AI 問答助手 - 讓 AI 幫助您整理和分析知識。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/oinzen/RSSFlow-doc/blob/main/docs/images/en/icon64.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://rssflow.oinchain.com\"> RssFlow </a> </td>\n        <td>一個智慧 RSS 閱讀器瀏覽器擴展，具有 AI 驅動的 RSS 摘要和多維度訂閱源檢視功能。支援 DeepSeek 模型配置以增強內容理解。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Hedwi/deepchat/refs/heads/main/images/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://chromewebstore.google.com/detail/deepchat-power-of-deepsee/femhcibnncinlabdboehojdhfcihpkpl?hl=en\"> DeepChat </a> </td>\n        <td> 一個 Chrome 擴展，允許用戶透過在任何網站上打開側邊欄與 DeepSeek 進行對話。此外，它還提供一個浮動選單，顯示在任何網站上選定文字下方，允許用戶生成文字摘要、檢查語法問題並翻譯內容。</td>\n    </tr>\n     <tr>\n        <td> <img src=\"https://www.typral.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.typral.com/\"> Typral </a> </td>\n        <td> 快速 AI 寫作助手 - 讓 AI 幫助您快速改進文章、論文、文本...</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://static.trancy.org/assets/trancy_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.trancy.org/\"> Trancy </a> </td>\n        <td> 沉浸式雙語翻譯、影片雙語字幕、句子/單詞選擇翻譯擴展。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://ziziyi.com/svg/anything_copilot.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/baotlake/anything-copilot\"> Anything Copilot </a> </td>\n        <td> Anything Copilot 是一個瀏覽器擴展，允許從側邊欄無縫訪問主流 AI 工具。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cliprun.com/apple-touch-icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://cliprun.com/\"> Cliprun </a> </td>\n        <td> Python 程式碼運行器和實驗場。右鍵點擊 DeepSeek 上的 Python 程式碼，即可在瀏覽器中立即運行。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://cdn.docky.ai/assets/logo.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/docky-ai/README.md\"> Docky AI </a> </td>\n        <td> Docky AI 是一個強大的瀏覽器擴展，允許您透過側邊欄與多個 AI 模型進行即時對話。它支援與多個模型的同時通訊，並能協助您閱讀網頁、寫作、翻譯和創建圖像。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/Rearview/assets/favicon.webp\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"./docs/Rearview/README_zh_tw.md\"> RearView </a> </td>\n        <td>Rearview 是一款瀏覽器歷史管理擴展，支援對歷史瀏覽內容的全文搜尋，並將瀏覽歷史轉換為可對話的知識庫。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"vscode\">VS Code 擴充功能</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/continuedev/continue/blob/main/docs/static/img/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continue 是一個開源的 IDE 自動化工具。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/assets/favicon.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/cline/README.md\"> Cline </a> </td>\n        <td> Cline 是一個能操作 CLI 和編輯器的 AI 助手。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/Sitoi/ai-commit/refs/heads/main/images/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Sitoi/ai-commit/blob/main/README.md\"> AI Commit </a> </td>\n        <td> 使用 AI 在 VS Code 中生成 Git 提交訊息。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/titusTong/seekCodeCopilot/blob/main/assets/SeekCodeCopilotLogo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/titusTong/seekCodeCopilot/blob/main/README.md\"> SeekCode Copilot </a> </td>\n        <td> 支援配置本地部署 DeepSeek 模型的 VS Code 智慧程式碼協助工具。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/intellism/vscode-comment-translate/blob/master/doc/image/icon.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/intellism/vscode-comment-translate/blob/master/README_ZH.md\"> Comment Translation </a> </td>\n        <td> 這款擴展程式能够幫助開發者翻譯程式碼中的注釋、字串、程式碼提示、錯誤資訊以及變數名。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/AITK/assets/AIToolkit.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://code.visualstudio.com/docs/intelligentapps/overview\"> AI Toolkit </a> </td>\n        <td> Visual Studio Code 的 AI Toolkit 是一個綜合性擴展，為開發人員和 AI 工程師提供使用生成式 AI 模型構建、測試和部署智能應用程序的能力。 </td>\n    </tr>\n        <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/joygqz/commit-genie/refs/heads/main/images/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=joygqz.commit-genie\"> Commit Genie </a> </td>\n        <td> 適用於 VS Code 的 AI 程式碼審查和提交訊息產生器。自動審查您的程式碼變更並產生有意義的標準提交訊息。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/JohnnyZ93/oai-compatible-copilot/blob/main/assets/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/oai-compatible-copilot/README.md\"> OAI Compatible Provider for Copilot </a> </td>\n        <td> 開源的 VS Code 擴充功能，可在 GitHub Copilot 中使用 OpenAI 相容的推理提供者。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"vs\">Visual Studio 擴充功能</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/comment2gpt/2.0.5/1739475434185/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.Comment2GPT\"> Comment2GPT </a> </td>\n        <td> 透過註解功能使用 OpenAI ChatGPT、Google Gemini、Anthropic Claude、DeepSeek 和 Ollama。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/codelens2gpt/2.0.5/1739475875714/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.CodeLens2GPT\"> CodeLens2GPT </a> </td>\n        <td> 透過 CodeLens 使用 OpenAI ChatGPT、Google Gemini、Anthropic Claude、DeepSeek 和 Ollama。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://merryyellow.gallerycdn.vsassets.io/extensions/merryyellow/uca-lite/1.4.2/1739392928984/Microsoft.VisualStudio.Services.Icons.Default\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://marketplace.visualstudio.com/items?itemName=MerryYellow.UCA-Lite\"> Unity Code Assist Lite </a> </td>\n        <td> Unity 腳本的程式碼協助工具。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"neovim\">neovim 擴充功能</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/c316f70a-0a3c-4a32-b148-4df15e609acc\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/avante.nvim/README.md\"> avante.nvim </a> </td>\n        <td> avante.nvim 是一個開源的 IDE 自動化工具。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/llm.nvim/README.md\"> llm.nvim </a> </td>\n        <td> 免費的大型語言模型 (LLM) 插件，讓您能在 Neovim 中與 LLM 互動。支援任何 LLM，例如 DeepSeek、GPT、GLM、Kimi 或本地 LLM（例如 Ollama）。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/codecompanion.nvim/README.md\"> codecompanion.nvim </a> </td>\n        <td> 在 Neovim 中無縫整合 AI 驅動的程式設計功能。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/user-attachments/assets/d66dfc62-8e69-4b00-8549-d0158e48e2e0\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/minuet-ai.nvim/README.md\"> minuet-ai.nvim </a> </td>\n        <td> Minuet 提供即時程式碼補全，來自包括 DeepSeek、OpenAI、Gemini、Claude、Ollama、Codestral 等流行的 LLM。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"jetbrains\">JetBrains 擴充功能</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/21520/412905/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://ide.unitmesh.cc/quick-start\"> AutoDev </a> </td>\n        <td> ‍AutoDev 是 JetBrain IDE 中的開源 AI 程式設計助手。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/21410/561595/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/21410-onegai-copilot\"> Onegai Copilot </a> </td>\n        <td> Onegai Copilot 是 JetBrain IDE 中的 AI 程式設計助手。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/continuedev/continue/blob/main/docs/static/img/logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/continue/README.md\"> Continue </a> </td>\n        <td> Continue 是一個開源的 IDE 自動化工具。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/a18792721831/studyplugin/535b9cab69da0f97b42dcaebb00bb0d4ed15c8a6/translate/src/main/resources/META-INF/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/18336-chinese-english-translate\">Chinese-English Translate</a> </td>\n        <td> Chinese-English Translate 是 JetBrain IDE 中的多語翻譯服務。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://plugins.jetbrains.com/files/24851/659002/icon/pluginIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\"/> </td>\n        <td> <a href=\"https://plugins.jetbrains.com/plugin/24851-ai-git-commit\">AI Git Commit</a> </td>\n        <td> 此插件使用 AI 根據程式碼變更自動生成提交訊息。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/YiiGuxing/TranslationPlugin/blob/master/pluginIcon.svg?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://intellij-translation.yiiguxing.top/#/en/\">IntelliJ Translation Plugin</a> </td>\n        <td> IntelliJ Translation Plugin 是一款適用於基於 IntelliJ 的 IDE 翻譯插件，它整合了包括 OpenAI 翻譯（相容 DeepSeek，Doubao，Ollama，……）在內的眾多翻譯服務，讓您能夠隨時在 IDE 中直接翻譯程式碼內的任意文字內容，例如程式碼註解與程式碼文件等。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"discord\">Discord 機器人</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://geneplore.com/img/geneplore_color_logo_circular.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/Geneplore AI/README.md\"> Geneplore AI </a> </td>\n        <td> Geneplore AI 運行著最大的 AI Discord 機器人之一，現在搭載 DeepSeek v3 和 R1。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"codeeditor\">原生 AI 程式碼編輯器</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://global.discourse-cdn.com/flex020/uploads/cursor1/original/2X/a/a4f78589d63edd61a2843306f8e11bad9590f0ca.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://www.cursor.com/\"> Cursor </a> </td>\n        <td> ‍以 VS Code 為基礎的 AI 程式碼編輯器。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://exafunction.github.io/public/images/windsurf/windsurf-app-icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://codeium.com/windsurf\"> WindSurf </a> </td>\n        <td> 由 Codeium 開發的另一款以 VS Code 為基礎的 AI 程式碼編輯器。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/wusigram/assets/logo-512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/wusigram/README_cn.md\"> 无思微程序 </a> </td>\n        <td>行動端AI程式設計與運行工具，DeepSeek程式設計搭檔</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"emacs\">Emacs</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/karthink/gptel\"> gptel </a> </td>\n        <td> 一個簡單的 Emacs LLM 客戶端。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://upload.wikimedia.org/wikipedia/commons/0/08/EmacsIcon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/milanglacier/minuet-ai.el\"> Minuet AI </a> </td>\n        <td> 在您的程式碼中與智慧共舞 💃。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"security\">安全性</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://github.com/lukehinds/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/codegate.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/stacklok/codegate/\"> CodeGate </a> </td>\n        <td> CodeGate：安全的 AI 程式碼生成。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"./docs/tencent/hunyuan.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/tencent/AI-Infra-Guard\"> AI-Infra-Guard </a> </td>\n        <td> 騰訊混元安全團隊 - AI 基礎設施安全評估工具，旨在發現和檢測 AI 系統中的潛在安全風險。 </td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"providers\">供應商</span>\n\n<table>\n    <tr>\n        <td> <img src=\"./docs/aimlapi/aimlapi_logo.png\"  alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://docs.aimlapi.com/api-references/text-models-llm?utm_source=awesome-deepseek-integrations&utm_medium=github&utm_campaign=integration\"> AI/ML API </a> </td>\n        <td> AI/ML API 讓使用者只需透過一個 API，就能以企業級的方式存取 200 種以上的模型。 這包括 Deepseek R1 和 V3，以及封閉和開源模型。 所有服務的正常運行時間均為 99%，並提供 24/7 全天候的人力支援。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n###  <span id=\"others\">其他</span>\n\n<table>\n    <tr>\n        <td> <img src=\"https://raw.githubusercontent.com/mlflow/mlflow/refs/heads/master/assets/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://mlflow.org/docs/latest/tracing/integrations/deepseek\"> MLflow </a></td>\n        <td> 使用 DeepSeek 建立、測試、部署和監控 AI 應用程式的開放原始碼 MLOps / LLMOps 平台。</td>\n    </tr>\n    <tr>\n        <td style=\"font-size: 64px\">🤖</td>\n        <td> <a href=\"https://github.com/wangrongding/wechat-bot/blob/main/README.md\"> Wechat-Bot </a></td>\n        <td> 基於 WeChaty 的微信機器人，結合 DeepSeek 和其他 AI 服務。 </td>\n    </tr>\n    <tr>\n        <td style=\"font-size: 64px\">&#128032;</td>\n        <td> <a href=\"https://github.com/lunary-ai/abso/blob/main/README.md\"> Abso </a></td>\n        <td> 使用 OpenAI 格式與任何 LLM 提供者互動的 TypeScript SDK。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.imgur.com/IsQYInJ.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/djcopley/ShellOracle/\"> ShellOracle </a> </td>\n        <td> 用於智慧生成 shell 命令的終端工具。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://avatars.githubusercontent.com/u/178783630?s=200&v=4\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/bolna-ai/bolna/\"> Bolna </a> </td>\n        <td> 使用 DeepSeek 作為對話式語音 AI 助手的 LLM。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/fatwang2/siri-ultra\"> Siri Ultra </a> </td>\n        <td> 一個在 GitHub 上擁有 1000 顆星的專案，支援網路連接、多輪對話和 DeepSeek 系列模型。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c1e47b01-1766-4f7e-bfe6-ab3cb3991c30\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/deepseek-ai/awesome-deepseek-integration/tree/main/docs/siri_deepseek_shortcut\"> siri_deepseek_shortcut </a> </td>\n        <td> Siri 搭載 DeepSeek API。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/n8n-io/n8n/blob/master/assets/n8n-logo.png?raw=true\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/rubickecho/n8n-deepseek\"> n8n-nodes-deepseek </a> </td>\n        <td> 一個 N8N 社群節點，支援將 DeepSeek API 直接整合到工作流程中。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/TSKshn2UFdTyvUi85EDMIXrXgs.png?scale-down-to=512\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Portkey-AI/gateway\"> Portkey AI </a> </td>\n        <td> Portkey 是一個統一的 API，支援與超過 1600 種 LLM 模型互動，為您的 DeepSeek 應用提供高級控制、可見性和安全性工具。提供 Python 和 Node SDK。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://framerusercontent.com/images/8rF2JOaZ8l9AvM4H6ezliw44aI.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/BerriAI/litellm\"> LiteLLM </a> </td>\n        <td> Python SDK，代理伺服器（LLM Gateway）以 OpenAI 格式調用 100+ LLM API。也支援 DeepSeek AI 並提供成本追蹤。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://i.postimg.cc/k5Z4YWjt/Screenshot-2025-01-23-at-6-08-01-PM.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/mem0ai/mem0\"> Mem0 </a> </td>\n        <td> Mem0 為 AI 助手提供智慧記憶層，實現個性化互動和持續學習。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://simplismart-public-assets.s3.ap-south-1.amazonaws.com/logos/Logo+Icon+Light.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://simplismart.ai/\"> Simplismart AI </a> </td>\n        <td> Simplismart 提供無縫的 GenAI 部署，為 LLM、Diffusion 和語音模型提供最快的推理速度。可在 Simplismart Cloud 或您自己的雲端上輕鬆部署 DeepSeek。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.promptfoo.dev/img/logo-panda.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"docs/promptfoo/README.md\"> promptfoo </a> </td>\n        <td> 測試和評估 LLM 提示，包括 DeepSeek 模型。比較不同的 LLM 提供者，捕捉回歸並評估回應。 </td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/AndersonBY/deepseek-tokenizer\"> deepseek-tokenizer </a> </td>\n        <td> 一個高效輕量的 DeepSeek 模型分詞庫。僅依賴於 `tokenizers` 庫，無需像 `transformers` 這樣的繁重依賴。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://langfuse.com/icon.svg\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://langfuse.com/docs/integrations/deepseek\"> Langfuse </a> </td>\n        <td> 開源的 LLM 可觀測性平台，幫助團隊協作調試、分析和迭代其 DeepSeek 應用。 </td>\n    </tr>\n    <tr>\n        <td> CR </td>\n        <td> <a href=\"https://github.com/hustcer/deepseek-review\"> deepseek-review </a> </td>\n        <td> 🚀 提升您的程式碼，信心滿滿地發佈 – 使用 DeepSeek 程式碼審查提升您的工作流程 🚀 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"http://gptlocalhost.com/wp-content/uploads/2025/01/icon_1024.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://youtu.be/T1my2gqi-7Q\"> GPTLocalost </a> </td>\n        <td> 在 Microsoft Word 本地使用 DeepSeek-R1。無推理成本。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/suqicloud/wp-ai-chat/raw/main/ic_logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/suqicloud/wp-ai-chat\"> WordPress ai助手 </a> </td>\n        <td> 將 DeepSeek API 整合到 WordPress 網站的 AI 對話助手、文章生成和文章摘要插件中。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"docs/ComfyUI-Copilot/assets/logo 2.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/AIDC-AI/ComfyUI-Copilot\"> ComfyUI-Copilot </a> </td>\n        <td> 基於 Comfy-UI 框架構建的智慧助手，透過自然語言互動簡化和增強 AI 演算法的調試與部署過程。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/Optima-CityU/llm4ad/blob/main/assets/figs/logo_short.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> </td>\n        <td> <a href=\"https://github.com/Optima-CityU/llm4ad\">LLM4AD</a> 是一個基於 Python 的統一開源平台，使用大型語言模型 (LLMs) 進行自動演算法設計 (AD)。 </td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/JiauZhang/chatchat\"> chatchat </a> </td>\n        <td> 大型語言模型 Python API。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://serpapi.com/android-chrome-512x512.png\" alt=\"Icon\" width=\"64\" height=\"auto\" />   </td>\n        <td> <a href=\"https://serpapi.com/blog/connect-deepseek-api-with-the-internet-google-search-and-more/#connect-deepseek-with-google-search-result\"> SerpApi </a> </td>\n        <td> 連接 DeepSeek API 與 Google 等搜尋結果。 </td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://github.com/yincongcyincong/telegram-deepseek-bot/blob/main/static/logo.png\" alt=\"Icon\" width=\"64\" height=\"auto\" /> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> </td>\n        <td> <a href=\"https://github.com/yincongcyincong/telegram-deepseek-bot\">telegram-deepseek-bot</a> 是一個集成 DeepSeek AI 能力的 Telegram 機器人。  </td>\n    </tr>\n    <tr>\n        <td>  </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> </td>\n        <td> <a href=\"https://github.com/eqld/nlsh\">nlsh</a> 是一款由 AI 驅動的命令列工具，能透過支援多種後端的大型語言模型（LLM），生成具有上下文感知能力的 Shell 指令。支援 Shell 專屬語法、唯讀系統工具，以及自訂的推理端點設定。</td>\n    </tr>\n    <tr>\n        <td> <img src=\"https://www.godtierprompts.com/logo.jpg\" alt=\"Icon\" width=\"64\" height=\"auto\" /></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a></td>\n        <td> <a href=\"https://www.godtierprompts.com\">God Tier Prompts</a> 是一個由社群驅動的排行榜，讓最優秀的提示詞脫穎而出。</td>\n    </tr>\n</table>\n\n<p style=\"text-align: right;\"><a href=\"#目錄\">^ 返回目錄 ^</a></p>\n\n### Star 歷史\n\n[![Star History Chart](https://api.star-history.com/svg?repos=deepseek-ai/awesome-deepseek-integration&type=Date)](https://star-history.com/#deepseek-ai/awesome-deepseek-integration&Date)\n"
  },
  {
    "path": "docs/16x_prompt/README.md",
    "content": "# [16x Prompt](https://prompt.16x.engineer/)\n\nAI Coding with Context Management.\n\n16x Prompt helps developers manage source code context and craft prompts for complex coding tasks on existing codebases.\n\n# UI\n\n![image](assets/16x_prompt_ui.png)\n\n## Integrate with DeepSeek API\n\n1. Click on the model selection button at bottom right\n2. Click on \"DeepSeek API\" to automatically fill in API Endpoint\n3. Enter model ID, for example `deepseek-chat` (for DeepSeek V3) or `deepseek-reasoner` (for DeepSeek R1)\n4. Enter your API key\n\n![image](assets/16x_prompt_integration.png)"
  },
  {
    "path": "docs/4EVERChat/README.md",
    "content": "<img src=\"https://4everlogo.4everland.store/icons/1024.png\" width=\"128\" height=\"auto\" /> \n\n# [4EVERChat](https://chat.4everland.org/)\n\n[4EVERChat](https://chat.4everland.org) is a large language model selection platform that seamlessly integrates hundreds of mainstream LLM models (such as ChatGPT, Deepseek, Grok, etc.). Developers can compare the response performance differences of various models in real-time, accurately identifying the optimal engine for their business needs. The platform requires no API key configuration and is ready to use out of the box.\n\nIts underlying technology relies on [4EVERLAND AI RPC](https://docs.4everland.org/ai/ai-rpc/quick-start), which not only enables zero-cost switching between hundreds of models through a unified API endpoint but also monitors service status in real-time and automatically activates backup nodes. It dynamically selects model combinations with fast response times and low inference costs, creating an AI development infrastructure that balances stability and cost-effectiveness.\n\n\n\n🔗 \n\n4EVERChat: https://chat.4everland.org/\n\n4EVERLAND: https://www.4everland.org/\n\n​ \n\n\n\n## UI\n\n####  4EVERChat\n\n<img src=\"https://markdown.4everland.store/4everchat_ui.jpg\" />\n\n#### 4EVER AI RPC\n\n<img src=\"https://markdown.4everland.store/4eveairpc_ui.png\" />\n\n\n\n## Add Deepseek Model\n\n<img src=\"https://markdown.4everland.store/4everchat_models.jpg\" />\n\n"
  },
  {
    "path": "docs/4EVERChat/README_cn.md",
    "content": "<img src=\"https://4everlogo.4everland.store/icons/1024.png\" width=\"128\" height=\"auto\" /> \r\n\r\n# [4EVERChat](https://chat.4everland.org/)\r\n\r\n[4EVERChat](https://chat.4everland.org)  是一个大语言模型选型平台，无缝集成数百款主流LLM模型（如ChatGPT、Deepseek、Grok等），开发者可实时对比不同模型的应答性能差异，精准定位最优业务引擎,平台无需配置API密钥即开即用。\r\n\r\n底层技术依托 [4EVERLAND AI RPC](https://docs.4everland.org/ai/ai-rpc/quick-start)，不仅能通过统一API端点实现百种模型的零成本切换，更会实时监测服务状态并自动启用备用节点，动态选择响应速度快、推理费用低的模型组合，打造兼顾稳定性与性价比的AI开发基础设施。\r\n\r\n\r\n🔗 \r\n\r\n4EVERChat: https://chat.4everland.org/\r\n\r\n4EVERLAND: https://www.4everland.org/\r\n\r\n## UI\r\n\r\n####  4EVERChat\r\n\r\n<img src=\"https://markdown.4everland.store/4everchat_ui.jpg\" />\r\n\r\n#### 4EVER AI RPC\r\n\r\n<img src=\"https://markdown.4everland.store/4eveairpc_ui.png\" />\r\n\r\n\r\n\r\n## 添加Deepseek 模型\r\n\r\n<img src=\"https://markdown.4everland.store/4everchat_models.jpg\" />\r\n\r\n"
  },
  {
    "path": "docs/4EVERChat/README_ja.md",
    "content": "<img src=\"https://4everlogo.4everland.store/icons/1024.png\" width=\"128\" height=\"auto\" /> \r\n\r\n# [4EVERChat](https://chat.4everland.org/)\r\n\r\n[4EVERChat](https://chat.4everland.org) は、大規模言語モデル選択プラットフォームであり、数百の主流LLMモデル（ChatGPT、Deepseek、Grokなど）をシームレスに統合しています。開発者は、さまざまなモデルの応答性能の違いをリアルタイムで比較し、ビジネスニーズに最適なエンジンを正確に特定できます。このプラットフォームはAPIキーの設定が不要で、すぐに使用を開始できます。\r\n\r\nその基盤技術は[4EVERLAND AI RPC](https://docs.4everland.org/ai/ai-rpc/quick-start)に依存しており、統一されたAPIエンドポイントを通じて数百のモデルのゼロコスト切り替えを実現するだけでなく、サービス状態をリアルタイムで監視し、バックアップノードを自動的に有効化します。応答速度が速く、推論コストが低いモデル組み合わせを動的に選択し、安定性とコスト効率を両立したAI開発インフラを構築します。\r\n\r\n\r\n\r\n🔗 \r\n\r\n4EVERChat: https://chat.4everland.org/\r\n\r\n4EVERLAND: https://www.4everland.org/\r\n\r\n## UI\r\n\r\n####  4EVERChat\r\n\r\n<img src=\"https://markdown.4everland.store/4everchat_ui.jpg\" />\r\n\r\n#### 4EVER AI RPC\r\n\r\n<img src=\"https://markdown.4everland.store/4eveairpc_ui.png\" />\r\n\r\n\r\n\r\n## Deepseek モデルを追加\r\n\r\n<img src=\"https://markdown.4everland.store/4everchat_models.jpg\" />\r\n\r\n"
  },
  {
    "path": "docs/ATTPs/README.md",
    "content": "\n# APRO-COM/ATTPs-framework\n\nFoundation framework that enables advanced agent based on DeepSeek interactions, data verification, and price queries with [ATTPs Protocol](https://docs.apro.com/attps) . It streamlines agent creation, verification processes, and provides a flexible framework for building robust agent-based solutions.\n\nFor more details about ATTPs, you can see the [whitepaper here](https://www.apro.com/attps.pdf)\n\n## Overview\n\nThe ATTPs framework bridges agent-based logic with the DeepSeek. It handles agent registration, data verification, and price queries, empowering both automated and user-driven workflows.\n\n## Features\n\n### Agent Operations\n- **Agent Creation**: Deploy new agents with custom settings\n- **Registration**: Register agents on-chain or via standardized processes\n- **Multi-Signer Framework**: Supports threshold-based approval flows\n\n### Data Verification\n- **Chain Validation**: Verify data authenticity on-chain\n- **Transaction Execution**: Handle verification logic with built-in security checks\n- **Auto-Hashing**: Convert raw data to hashed formats when needed\n- **Metadata Parsing**: Validate content type, encoding, and compression\n\n### Price Queries\n- **Live Price Data**: Fetch price information for various pairs\n- **Format Validation**: Normalize user query inputs to standard trading-pair formats\n- **APIs Integration**: Retrieve real-time or near-real-time pricing information\n\n## Security Features\n\n### Access Control\n- **Private Key Management**: Safe usage of private keys for transaction signing\n- **Environment Variables**: Secure injection of credentials\n- **On-Chain Validation**: Leverage on-chain contract checks\n\n### Verification\n- **Input Validation**: Strict schema checks before on-chain operations\n- **Transaction Receipts**: Provide verifiable transaction details\n- **Error Handling**: Detailed error logs for quick debugging\n\n## Performance Optimization\n\n1. **Cache Management**\n   - Implement caching for frequent queries\n   - Monitor retrieval times and cache hits\n\n2. **Network Efficiency**\n   - Batch requests where possible\n   - Validate response parsing to reduce overhead\n\n## System Requirements\n- Node.js 16.x or higher\n- Sufficient network access to on-chain endpoints\n- Basic configuration of environment variables\n- Minimum 4GB RAM recommended\n\n## Troubleshooting\n\n1. **Invalid Agent Settings**\n   - Ensure signers and threshold are correct\n   - Validate agentHeader for proper UUIDs and numeric values\n\n2. **Verification Failures**\n   - Check the input data formats\n   - Confirm environment variables are set\n\n3. **Price Query Errors**\n   - Verify the trading pair format\n   - Check external API availability\n\n## Safety & Security\n\n1. **Credential Management**\n   - Store private keys securely\n   - Do not commit secrets to version control\n\n2. **Transaction Limits**\n   - Configure thresholds to mitigate abuse\n   - Log transaction attempts and failures\n\n3. **Monitoring & Logging**\n   - Track unusual activity\n   - Maintain detailed audit logs\n\n\n# Usage with js\n\n## Installation\n\n```bash\nnpm install ai-agent-sdk-js\n```\n\n## Configuration\n\nConfigure the plugin by setting environment variables or runtime settings:\n- APRO_RPC_URL\n- APRO_PROXY_ADDRESS\n- APRO_PRIVATE_KEY\n- APRO_CONVERTER_ADDRESS\n- APRO_AUTO_HASH_DATA\n\n## Usage with js sdk\n\nTo use the AI Agent SDK, import the library and create an instance of the `Agent` class:\n\n```typescript\nimport { AgentSDK } from 'ai-agent-sdk-js'\n\nconst agent = new AgentSDK({\n  rpcUrl: 'https://bsc-testnet-rpc.publicnode.com',\n  privateKey: '',\n  proxyAddress: '',\n})\n\n// if you want the SDK to hash the data automatically\nconst autoHashAgent = new AgentSDK({\n  rpcUrl: 'https://bsc-testnet-rpc.publicnode.com',\n  privateKey: '',\n  proxyAddress: '',\n  autoHashData: true,\n  converterAddress: '',\n})\n```\n\nTo create a new agent, call the `createAndRegisterAgent` method:\n\n```typescript\nimport type { AgentSettings, TransactionOptions } from 'ai-agent-sdk-js'\nimport { randomUUID } from 'node:crypto'\nimport { parseUnits } from 'ethers'\n\n// prepare the agent settings\nconst agentSettings: AgentSettings = {\n  signers: [],\n  threshold: 3,\n  converterAddress: '',\n  agentHeader: {\n    messageId: randomUUID(),\n    sourceAgentId: randomUUID(),\n    sourceAgentName: 'AI Agent SDK JS',\n    targetAgentId: '',\n    timestamp: Math.floor(Date.now() / 1000),\n    messageType: 0,\n    priority: 1,\n    ttl: 3600,\n  },\n}\n\n// prepare the transaction options\nconst nonce = await agent.getNextNonce()\nconst transactionOptions: TransactionOptions = {\n  nonce,\n  gasPrice: parseUnits('1', 'gwei'),\n  gasLimit: BigInt(2000000),\n}\n\nconst tx = await agent.createAndRegisterAgent({ agentSettings, transactionOptions })\n\n// or you can leave the transaction options empty, the SDK will use the auto-generated values\n// const tx = await agent.createAndRegisterAgent({ agentSettings })\n```\n\nThe SDK also provides the tool to extract the new agent address from the transaction receipt:\n\n```typescript\nimport { parseNewAgentAddress } from 'ai-agent-sdk-js'\n\nconst receipt = await tx.wait()\nconst agentAddress = parseNewAgentAddress(receipt)\n```\n\nTo verify the data integrity, call the `verify` method:\n\n```typescript\nimport type { MessagePayload } from 'ai-agent-sdk-js'\nimport { hexlify, keccak256, toUtf8Bytes } from 'ethers'\n\n// prepare the payload\nconst data = hexlify(toUtf8Bytes('Hello World!'))\nconst dataHash = keccak256(data)\nconst payload: MessagePayload = {\n  data,\n  dataHash,\n  signatures: [\n    {\n      r: '',\n      s: '',\n      v: 1, // 1, 0, 27, 28 are allowed\n    },\n    // ...\n  ],\n  metadata: {\n    contentType: '',\n    encoding: '',\n    compression: '',\n  },\n}\n\nconst tx = await agent.verify({ payload, agent: '', digest: '' })\n```\n\nIf the data is obtained from the APRO DATA pull service, you can use the auto-hash feature:\n\n```typescript\nimport type { MessagePayload } from 'ai-agent-sdk-js'\n\nconst payload: MessagePayload = {\n  data: '0x...',\n  signatures: [\n    {\n      r: '',\n      s: '',\n      v: 1, // 1, 0, 27, 28 are allowed\n    },\n    // ...\n  ],\n  metadata: {\n    contentType: '',\n    encoding: '',\n    compression: '',\n  },\n}\n\n// When\nconst tx = await autoHashAgent.verify({ payload, agent: '', digest: '' })\n```\n\nFor more examples, see the [test](https://github.com/APRO-com/ai-agent-sdk-js/tree/main/test) cases.\n\n\n\n# Usage with Python\n\n## Installation\n\n```bash\n$ pip3 install ai-agent-sdk\n\n```\n\n## Usage with Python SDK\n\n### Initialize AgentSDK\n\n```python\nfrom ai_agent.agent import AgentSDK\n\nAGENT_PROXY_ADDRESS = \"0x07771A3026E60776deC8C1C61106FB9623521394\"\nNETWORK_RPC = \"https://testnet-rpc.bitlayer.org\"\n\nagent = AgentSDK(endpoint_uri=NETWORK_RPC, proxy_address=AGENT_PROXY_ADDRESS)\n```\n\nTo create a new agent, call the createAndRegisterAgent method:\n\n```python\nimport time\nfrom ai_agent.entities import (\n    AgentSettings,\n    AgentHeader,\n    MessageType,\n    Priority\n)\nfrom ai_agent.utils import (\n    generate_uuid_v4\n)\n\nAGENT_SETTINGS = AgentSettings(\n    signers=[\n        \"0x4b1056f504f32c678227b5Ae812936249c40AfBF\",\n        \"0xB973476e0cF88a3693014b99f230CEB5A01ac686\",\n        \"0x6cF0803D049a4e8DC01da726A5a212BCB9FAC1a1\",\n        \"0x9D46daa26342e9E9e586A6AdCEDaD667f985567B\",\n        \"0x33AF673aBcE193E20Ee94D6fBEb30fEf0cA7015b\",\n        \"0x868D2dE4a0378450BC62A7596463b30Dc4e3897E\",\n        \"0xD4E157c36E7299bB40800e4aE7909DDcA8097f67\",\n        \"0xA3866A07ABEf3fD0643BD7e1c32600520F465ca8\",\n        \"0x62f642Ae0Ed7F12Bc40F2a9Bf82ccD0a3F3b7531\"\n    ],\n    threshold=2,\n    converter_address=\"0xaB303EF87774D9D259d1098E9aA4dD6c07F69240\",\n    agent_header=AgentHeader(\n        version=\"1.0\",\n        message_id=\"d4d0813f-ceb7-4ce1-8988-12899b26c4b6\",\n        source_agent_id=\"da70f6b3-e580-470f-b88b-caa5369e7778\",\n        source_agent_name=\"APRO Pull Mode Agent\",\n        target_agent_id=\"\",\n        timestamp=int(time.time()),\n        message_type=MessageType.Event,\n        priority=Priority.Low,\n        ttl=60 * 60\n    )\n)\n\ndynamic_setting = AGENT_SETTINGS\ndynamic_setting.agent_header.source_agent_id = generate_uuid_v4()\ndynamic_setting.agent_header.target_agent_id = generate_uuid_v4()\ndynamic_setting.agent_header.message_id = generate_uuid_v4()\nuser_owner = agent.add_account(\"0x_user_private_key\")\nresult = agent.create_and_register_agent(\n    transmitter=\"\",\n    nonce=None,\n    settings=AGENT_SETTINGS)\nprint(\"created agent:\", result)\n\n```\nTo verify the data integrity, call the verify method:\n\n```python\nfrom ai_agent.entities import (\n    AgentMessagePayload,\n    Proofs,\n    AgentMetadata,\n)\n\nAGENT_CONTRACT = \"0xA1903361Ee8Ec35acC7c8951b4008dbE8D12C155\"\nAGENT_SETTING_DIGEST = \"0x010038164dba6abffb84eb5cb538850d9bc5d8f815149a371069b3255fd177a4\"\nAGENT_PAYLOAD = AgentMessagePayload(\n    data=\"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\",\n    data_hash=\"0x53d9f133f1265bd4391fcdf89b63424cbcfd316c8448f76cc515647267ac0a8e\",\n    proofs=Proofs(\n        zk_proof=\"0x\",\n        merkle_proof=\"0x\",\n        signature_proof=\"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\",\n    ),\n    meta_data=AgentMetadata(\n        content_type=\"0x\",\n        encoding=\"0x\",\n        compression=\"0x\"\n    )\n)\nuser_owner = agent.add_account(\"0x_user_private_key\")\nresult = agent.verify(\n    transmitter=user_owner,\n    nonce=None,\n    agent_contract=AGENT_CONTRACT,\n    settings_digest=AGENT_SETTING_DIGEST,\n    payload=AGENT_PAYLOAD\n)\nprint(\"verify:\", result)\n```\nFor more examples, see the [test cases](https://github.com/APRO-com/ai-agent-sdk-python/tree/main/tests).\n\n\n# Other SDKs\n\nJAVA: https://github.com/APRO-com/ai-agent-sdk-java\n\nRUST: https://github.com/APRO-com/ai-agent-sdk-rust\n\nGOLANG: https://github.com/APRO-com/ai-agent-sdk-go\n\n# Support\n\nFor issues or feature requests:\n1. Check existing documentation\n2. Submit a GitHub issue with relevant details\n3. Include transaction logs and system info if applicable\n\n# Contributing\n\nWe welcome pull requests! Refer to the project’s CONTRIBUTING.md and open discussions to coordinate efforts.\n\n# Credits\n\n- [APRO](https://www.apro.com/) - Plugin sponsor and partner\n- [ai-agent-sdk-js](https://github.com/APRO-com/ai-agent-sdk-js) - Underlying agent SDK\n- [ethers.js](https://docs.ethers.io/) - Transaction and contract interaction\n- Community contributors for feedback and testing\n\nFor more information about Apro plugin capabilities:\n\n- [Apro Documentation](https://docs.apro.com/en)\n\n# License\n\nThis plugin is part of the Eliza project. Refer to the main project repository for licensing details."
  },
  {
    "path": "docs/Alpha派/README.md",
    "content": "<img src=\"./assets/favicon1.png\" width=\"64\" height=\"auto\" /> \n\n# Alpha Pai\n\nAI Research Assistant / The Next-Generation Financial Information Portal Driven by AI.<br>\nProxy for investors to attend meetings and take notes, as well as providing search and Q&A services for financial information and quantitative analysis for investment research.\n## UI\n\n<img src=\"./assets/Alpha派-0.png\" width=\"360\" height=\"auto\" />\n\n<img src=\"./assets/Alpha派-1.png\" width=\"360\" height=\"auto\" />\n\n\n<img src=\"./assets/Alpha派-2.png\" width=\"360\" height=\"auto\" />\n"
  },
  {
    "path": "docs/Alpha派/README_cn.md",
    "content": "<img src=\"./assets/favicon1.png\" width=\"64\" height=\"auto\" /> \n\n# Alpha派\n\nAI投研助理/AI驱动的新一代金融信息入口。代理投资者听会/记纪要，金融投资信息的搜索问答/定量分析等投资研究工作。\n\n## UI\n\n<img src=\"./assets/Alpha派-0.png\" width=\"360\" height=\"auto\" />\n\n<img src=\"./assets/Alpha派-1.png\" width=\"360\" height=\"auto\" />\n\n<img src=\"./assets/Alpha派-2.png\" width=\"360\" height=\"auto\" />\n"
  },
  {
    "path": "docs/Alpha派/README_ja.md",
    "content": "<img src=\"./assets/favicon1.png\" width=\"64\" height=\"auto\" /> \n\n# Alphaパイ\n\nAI投資研究エージェント/次世代の金融情報エントリーポイント。投資家を代理して会議に出席し、AI議事録を取るほか、金融投資情報の検索・質問応答やエージェント駆使した定量分析など、投資研究業務を支援します。\n\n## UI\n\n<img src=\"./assets/Alpha派-0.png\" width=\"360\" height=\"auto\" />\n\n<img src=\"./assets/Alpha派-1.png\" width=\"360\" height=\"auto\" />\n\n<img src=\"./assets/Alpha派-2.png\" width=\"360\" height=\"auto\" />\n"
  },
  {
    "path": "docs/ChatDOC/README.md",
    "content": "# [ChatDOC](https://chatdoc.com)\n\nChatDOC is an AI-powered document reading tool equipped with robust traceability features, ensuring that the source of every piece of information is clear and verifiable, helping you efficiently and accurately grasp the core of your documents.\n\n## UI\n\n![image](./assets/ui.png)\n\n## Integrate with DeepSeek API\n\n![image](./assets/settings.png)\n\n"
  },
  {
    "path": "docs/ChatDOC/README_cn.md",
    "content": "# [ChatDOC](https://chatdoc.com)\n\nChatDOC是一款AI文档阅读工具，具备强大的溯源功能，确保每一条信息的来源清晰可查，助您高效、精准地掌握文档核心。\n\n## UI\n\n![image](./assets/ui.png)\n\n## Integrate with DeepSeek API\n\n![image](./assets/settings.png)\n"
  },
  {
    "path": "docs/Coco AI/README.md",
    "content": "<img width=\"1024\" src=\"assets/og-image.gif\">\n\n<!-- TEXT_SECTION:header:END -->\n\n# Coco AI - Connect & Collaborate\n\nCoco AI is a unified search platform that connects all your enterprise applications and data—Google Workspace, Dropbox, Confluent Wiki, GitHub, and more—into a single, powerful search interface. This repository contains the **COCO App**, built for both **desktop and mobile**. The app allows users to search and interact with their enterprise data across platforms.\n\nIn addition, COCO offers a **Gen-AI Chat for Teams**—imagine **Deepseek** but tailored to your team’s unique knowledge and internal resources. COCO enhances collaboration by making information instantly accessible and providing AI-driven insights based on your enterprise's specific data.\n\n# UI\n![alt text](assets/coco-deepseek-1.png)\n![alt text](assets/coco-deepseek-2.png)\n![alt text](assets/coco-deepseek-3.png)\n![alt text](assets/coco-deepseek-4.png)\n![alt text](assets/coco-deepseek-5.png)\n"
  },
  {
    "path": "docs/Coco AI/README_cn.md",
    "content": "<img width=\"1024\" src=\"assets/og-image.gif\">\n\n<!-- TEXT_SECTION:header:END -->\n\n# Coco AI - Connect & Collaborate\n\nCoco AI 是一个统一的搜索平台，能够将您企业的所有应用程序和数据——包括 Google Workspace、Dropbox、Confluence Wiki、GitHub 等——整合到一个强大而统一的搜索界面中。这个仓库包含了适用于桌面端和移动端的 COCO 应用程序。用户可以通过该应用在不同平台上搜索和操作企业数据。\n\n此外，Coco 还提供了一个面向团队的生成式人工智能聊天工具——可以将其想象为专为您的团队量身定制的 Deepseek，它能够与团队独特的知识体系和内部资源相结合。Coco 通过即时提供信息访问和基于企业特定数据的人工智能驱动洞察，增强了团队协作能力。\n\n# UI\n![alt text](assets/coco-deepseek-1.png)\n![alt text](assets/coco-deepseek-2.png)\n![alt text](assets/coco-deepseek-3.png)\n![alt text](assets/coco-deepseek-4.png)\n![alt text](assets/coco-deepseek-5.png)\n"
  },
  {
    "path": "docs/ComfyUI-Copilot/README.md",
    "content": "<div align=\"center\">\r\n\r\n# 🎯 ComfyUI-Copilot: Your Intelligent Assistant for Comfy-UI\r\n\r\n<!-- Enhancing Image Generation Development with Smart Assistance -->\r\n\r\n<h4 align=\"center\">\r\n\r\n<div align=\"center\">\r\n<img src=\"https://img.shields.io/badge/Version-1.0.0-blue.svg\" alt=\"Version\"> \r\n<img src=\"https://img.shields.io/badge/License-MIT-green.svg\" alt=\"License\">\r\n<img src=\"https://img.shields.io/github/stars/AIDC-AI/ComfyUI-Copilot?color=yellow\" alt=\"Stars\">\r\n<img src=\"https://img.shields.io/github/issues/AIDC-AI/ComfyUI-Copilot?color=red\" alt=\"Issues\">\r\n<img src=\"https://img.shields.io/badge/python-3.10%2B-purple.svg\" alt=\"Python\">\r\n\r\n</h4>\r\n\r\n\r\n👾 _**Alibaba International Digital Commerce**_ 👾\r\n\r\n:octocat: [**Github**](https://github.com/AIDC-AI/ComfyUI-Copilot)\r\n\r\n</div>\r\n\r\nhttps://github.com/user-attachments/assets/0372faf4-eb64-4aad-82e6-5fd69f349c2c\r\n\r\n## 🌟 Introduction\r\n\r\nWelcome to **ComfyUI-Copilot**, an intelligent assistant built on the Comfy-UI framework that simplifies and enhances the AI algorithm debugging and deployment process through natural language interactions.\r\n\r\nWhether it's generating text, images, or audio, ComfyUI-Copilot offers intuitive node recommendations, workflow building aids, and model querying services to streamline your development process.\r\n\r\n<div align=\"center\">\r\n<img src=\"assets/Framework.png\"/>\r\n</div>\r\n\r\n\r\n---\r\n\r\n## 🤔 Why Choose ComfyUI-Copilot?\r\n\r\n- 🍀 **Ease of Use**: Lower the barriers to entry with natural language interaction, making Comfy-UI accessible even for beginners.\r\n- 🍀 **Smart Recommendations**: Leverage AI-driven node suggestions and workflow implementations to boost development efficiency.\r\n- 🍀 **Real-Time Assistance**: Benefit from round-the-clock interactive support to address any issues encountered during development.\r\n\r\n---\r\n\r\n## 🔥 Core Features\r\n\r\n- 💎 **Interactive Q&A Bot**: Access a robust Q&A platform where users can inquire about model intricacies, node details, and parameter utilization with ease.\r\n- 💎 **Natural Language Node Suggestions**: Employ our advanced search mechanism to swiftly identify desired nodes and enhance workflow construction efficacy.\r\n<img src=\"assets/comfycopilot_nodes_recommend.gif\"/>\r\n\r\n- 💎 **Node Query System**: Dive deeper into nodes by exploring their explanations, parameter definitions, usage tips, and downstream workflow recommendations.\r\n<img src=\"assets/comfycopilot_nodes_search.gif\"/>\r\n\r\n- 💎 **Smart Workflow Assistance**: Automatically discern developer needs to recommend and build fitting workflow frameworks, minimizing manual setup time.\r\n<img src=\"assets/工作流检索.png\"/>\r\n\r\n- 💎 **Model Querying**: Prompt Copilot to seek foundational models and 'lora' based on requirements.\r\n- 💎 **Up-and-Coming Features**:\r\n  \r\n  - **Automated Parameter Tuning**: Exploit machine learning algorithms for seamless analysis and optimization of critical workflow parameters.\r\n  - **Error Diagnosis and Fix Suggestions**: Receive comprehensive error insights and corrective advice to swiftly pinpoint and resolve issues.\r\n\r\n---\r\n\r\n## 🚀 Getting Started\r\n\r\n**Repository Overview**: Visit the [GitHub Repository](https://github.com/AIDC-AI/ComfyUI-Copilot) to access the complete codebase.\r\n\r\n1. **Installation**:\r\n   \r\n   ```bash\r\n   cd ComfyUI/custom_nodes\r\n   git clone git@github.com:AIDC-AI/ComfyUI-Copilot.git\r\n   ```\r\n   \r\n   or\r\n   \r\n   ```bash\r\n   cd ComfyUI/custom_nodes\r\n   git clone https://github.com/AIDC-AI/ComfyUI-Copilot\r\n   ```\r\n2. **Activation**: After running the ComfyUI project, find the Copilot activation button at the top-right corner of the board to launch its service.\r\n<img src=\"assets/start.png\"/>\r\n<<<<<<< HEAD\r\n3.  **KeyGeneration**：Enter your email address on the link, the api-key will automatically be sent to your email address later.\r\n=======\r\n\r\n3.  **KeyGeneration**：Enter your name and email address on the link, and the api-key will automatically be sent to your email address later.\r\n>>>>>>> 62f0878737649971dd8c5e71c3c44e2328a38e74\r\n    \r\n<img src=\"assets/keygen.png\"/>\r\n\r\n---\r\n\r\n## 🤝 Contributions\r\n\r\nWe welcome any form of contribution! Feel free to make issues, pull requests, or suggest new features.\r\n\r\n---\r\n\r\n## 📞 Contact Us\r\n\r\nFor any queries or suggestions, please feel free to contact: ComfyUI-Copilot@service.alibaba.com.\r\n\r\n---\r\n\r\n## 📚 License\r\n\r\nThis project is licensed under the MIT License - see the [LICENSE](https://opensource.org/licenses/MIT) file for details.\r\n"
  },
  {
    "path": "docs/DocKit/README.md",
    "content": "<div align=\"center\">\n<a href=\"https://github.com/geek-fun/dockit\"><img src=\"./assets/dockit.png\" width=\"120\"/></a>\n</div>\n<h1 align=\"center\">DocKit</h1>\n<div align=\"center\">\n\n[![Node.js CI](https://github.com/geek-fun/dockit/actions/workflows/node.yml/badge.svg)](https://github.com/geek-fun/dockit/actions/workflows/node.yml)\n[![package release](https://github.com/geek-fun/dockit/actions/workflows/release.yml/badge.svg)](https://github.com/geek-fun/dockit/actions/workflows/release.yml)\n[![Known Vulnerabilities](https://snyk.io/test/github/geek-fun/dockit/badge.svg)](https://snyk.io/test/github/geek-fun/dockit)\n[![codecov](https://codecov.io/gh/geek-fun/dockit/branch/master/graph/badge.svg?token=GqlkEVgMvR)](https://codecov.io/gh/geek-fun/dockit)\n[![GitHub version](https://badge.fury.io/gh/geek-fun%2Fdockit.svg)](https://badge.fury.io/gh/geek-fun%2Fdockit)\n[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n\n\n</div>\n\n\n[DocKit](https://dockit.geekfun.club/) is an AI powered desktop GUI client designed for NoSQL database, support Elasticsearch and OpenSearch across Mac, windows and Linux. By integrating with large models like DeepSeek, DocKit can help developers to write complex DSL queries, and provide a better experience for data management and analysis. </td>\n\n\n\n## Client\n![client UI](./assets/client-ui.png)\n\n## Feature\n\nDocKit offers a range of features to suit your specific needs:\n\n- **User-Friendly Interface**: Navigate through your Elasticsearch/OpenSearch server with ease using DocKit's intuitive interface.\n- **Advanced Search Capabilities**: Perform complex searches and analyze your data efficiently.\n- **Cross-Platform Support**: Available for Mac, Windows, and Linux, ensuring compatibility with your operating system.\n- **Open-Source**: DocKit is an open-source project, allowing for community contributions and continuous improvement.\n- **Multiple Server Support**: Connect to multiple Elasticsearch/OpenSearch servers simultaneously, streamlining your workflow.\n- **AI-Powered Search**: Utilize AI-powered search capabilities to enhance your data analysis and visualization.\n- **Dark Mode Support**: DocKit offers a dark mode to protect your eyes and improve productivity.\n- **Multi-Window Support**: DocKit supports multi-window operations, allowing you to view and edit multiple indices and documents simultaneously.\n- **Multi-Language Support**: DocKit provides multiple language versions, ensuring ease of use for users worldwide.\n- **Cluster Management and Monitoring**: DocKit offers cluster management and monitoring features, helping you easily manage and monitor the health, nodes, shards, and indices of your Elasticsearch clusters.\n\n## Roadmap\n\n- [ ] MongoDB support\n- [ ] DynamoDB support\n- [ ] TBC\n\n## Installation\n\nAvailable to download for free from [here](https://github.com/geek-fun/dockit/releases).\n\n## Build Guidelines\n\n### Prerequisites\n\n* Node.js >= 20\n* NPM >= 10\n\n### Clone the code\n\n```bash\ngit clone https://github.com/geek-fun/dockit.git --depth=1\n```\n\n### Install dependencies\n\n```bash\nnpm install\n```\n\n### Compile and run\n\n```bash\nnpm run tauri dev\n```\n## About\n### Wechat Official Account\n<img src=\"./assets/wechat_official.png\" alt=\"wechat official account qr code\" width=\"360\" />\n\n### Sponsor\nIf this project helpful for you, feel free to buy me a cup of coffee ☕️.\n\n* Github Sponsor  \n  [![Sponsor](https://img.shields.io/badge/-Sponsor-fafbfc?logo=GitHub-Sponsors)](https://github.com/sponsors/[geek-fun])\n\n* Wechat Sponsor  \n  <img src=\"./assets/wechat_ponsor.jpg\" alt=\"wechat sponsor qr code\" width=\"200\" />\n"
  },
  {
    "path": "docs/DocKit/README_cn.md",
    "content": "<div align=\"center\">\n<a href=\"https://github.com/geek-fun/dockit\"><img src=\"./assets/dockit.png\" width=\"120\"/></a>\n</div>\n<h1 align=\"center\">DocKit</h1>\n<div align=\"center\">\n\n[![Node.js CI](https://github.com/geek-fun/dockit/actions/workflows/node.yml/badge.svg)](https://github.com/geek-fun/dockit/actions/workflows/node.yml)\n[![package release](https://github.com/geek-fun/dockit/actions/workflows/release.yml/badge.svg)](https://github.com/geek-fun/dockit/actions/workflows/release.yml)\n[![Known Vulnerabilities](https://snyk.io/test/github/geek-fun/dockit/badge.svg)](https://snyk.io/test/github/geek-fun/dockit)\n[![codecov](https://codecov.io/gh/geek-fun/dockit/branch/master/graph/badge.svg?token=GqlkEVgMvR)](https://codecov.io/gh/geek-fun/dockit)\n[![GitHub version](https://badge.fury.io/gh/geek-fun%2Fdockit.svg)](https://badge.fury.io/gh/geek-fun%2Fdockit)\n[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n\n\n</div>\nHere's the translated `README_cn.md` file:\n\n\n[DocKit](https://dockit.geekfun.club/) 是一个AI驱动的桌面客户端，专为NoSQL数据库设计，支持Mac、Windows和Linux上的Elasticsearch和OpenSearch。通过集成DeepSeek等大型模型，DocKit可以帮助开发者编写复杂的DSL查询，并为数据管理和分析提供更好的体验。\n\n\n\n## 客户端界面\n![客户端界面](./assets/client-ui.png)\n\n## 功能特点\n\nDocKit提供多种功能以满足您的特定需求：\n\n- **用户友好界面**：通过DocKit直观的界面轻松浏览您的Elasticsearch/OpenSearch服务器。\n- **高级搜索功能**：高效执行复杂搜索并分析您的数据。\n- **跨平台支持**：适用于Mac、Windows和Linux，确保与您的操作系统兼容。\n- **开源**：DocKit是一个开源项目，允许社区贡献和持续改进。\n- **多服务器支持**：同时连接多个Elasticsearch/OpenSearch服务器，简化您的工作流程。\n- **AI驱动搜索**：利用AI驱动的搜索功能增强数据分析和可视化。\n- **暗黑模式支持**：DocKit提供暗黑模式以保护您的眼睛并提高生产力。\n- **多窗口支持**：DocKit支持多窗口操作，允许您同时查看和编辑多个索引和文档。\n- **多语言支持**：DocKit提供多种语言版本，确保全球用户易于使用。\n- **集群管理与监控**：DocKit提供集群管理和监控功能，帮助您轻松管理和监控Elasticsearch集群的健康状况、节点、分片和索引。\n\n## 路线图\n\n- [ ] MongoDB支持\n- [ ] DynamoDB支持\n- [ ] 待定\n\n## 安装\n\n可以从[这里](https://github.com/geek-fun/dockit/releases)免费下载。\n\n## 构建指南\n\n### 前提条件\n\n* Node.js >= 20\n* NPM >= 10\n\n### 克隆代码\n\n```bash\ngit clone https://github.com/geek-fun/dockit.git --depth=1\n```\n\n### 安装依赖\n\n```bash\nnpm install\n```\n\n### 编译和运行\n\n```bash\nnpm run tauri dev\n```\n## 关于\n### 微信公众号\n<img src=\"./assets/wechat_official.png\" alt=\"微信公众号二维码\" width=\"360\" />\n\n### 赞助\n如果这个项目对您有帮助，欢迎给我买杯咖啡 ☕️。\n\n* Github赞助\n  [![Sponsor](https://img.shields.io/badge/-Sponsor-fafbfc?logo=GitHub-Sponsors)](https://github.com/sponsors/[geek-fun])\n\n* 微信赞助\n  <img src=\"./assets/wechat_ponsor.jpg\" alt=\"微信赞助二维码\" width=\"200\" />\n"
  },
  {
    "path": "docs/ETOS-LLM-Studio/README.md",
    "content": "# ETOS LLM Studio (ELS)\n\n<div align=\"center\">\n<img src=\"./assets/logo.png\" width=\"128\" alt=\"ETOS LLM Studio Logo\">\n</div>\n\n## English\n\n> **Spark of wisdom on your wrist, redefining the dimension of AI interaction.**\n\n**ETOS LLM Studio (ELS)** is a flagship AI client explicitly tailored for **watchOS** and **iOS**. It is not merely a wrapper but an ultimate exploration of Apple's ecosystem interaction logic.\n\nELS condenses the powerful reasoning capabilities of LLMs (including DeepSeek) into a square inch with its minimalist yet profound rhythmic aesthetics. Whether in the rhythm of a morning jog or a fleeting moment of inspiration, simply raise your wrist, and profound thoughts and insights are within reach like a stream of light.\n\n**Features:**\n- **Watch-First Design**: Independent interaction experience built for Apple Watch.\n- **Aesthetic UI**: Minimalist design with fluid animations and immersive typography.\n- **Seamless Sync**: Perfect synergy between iOS and watchOS.\n- **Deep Integration**: Native performance with haptic feedback.\n- **Multi-Model Support**: Connect with various LLMs, including DeepSeek.\n\n---\n\n## 简体中文\n\n> **穿梭于腕间的智慧灵光，重塑 AI 交互新维度。**\n\n**ETOS LLM Studio (ELS)** 是一款专为 **watchOS** 与 **iOS** 深度定制的旗舰级 AI 客户端。它并非简单的接口套壳，而是对 Apple 生态交互逻辑的极致探索。\n\nELS 以其极简而深邃的律动美学，将大模型（支持 DeepSeek 等多种模型）磅礴的推理能力浓缩于方寸之间。无论是在晨间慢跑的律动中，还是在灵感迸发的瞬息，只需轻抬手腕，那些深邃的思想与洞见便如流光般触手可及。\n\n**核心特性：**\n- **腕上智核 (Watch-First Design)**: 专为 Apple Watch 打造的独立交互体验，无需依赖手机即可完成复杂的对话与推理。\n- **极简美学 (Aesthetic UI)**: 摒弃繁杂，回归内容本身。流畅的动画与沉浸式的排版，让每一次对话都成为视觉享受。\n- **全端联动 (Seamless Sync)**: iOS 与 watchOS 完美协同，随时随地接入强大的 AI 模型。\n- **深度集成 (Deep Integration)**: 充分利用原生系统特性，提供如丝般顺滑的响应速度与触觉反馈。\n\n---\n\n## 日本語\n\n> **手首で輝く知性の閃き、AIインタラクションの新たな次元へ。**\n\n**ETOS LLM Studio (ELS)** は、**watchOS** と **iOS** のために特別に設計されたフラッグシップ AI クライアントです。単なるラッパーではなく、Apple エコシステムのインタラクションロジックを極限まで追求しました。\n\nELS はそのミニマルかつ深淵なリズムの美学により、DeepSeek を含む大規模言語モデル（LLM）の強大な推論能力をこの方寸の地に凝縮しました。朝のジョギングのリズムの中であれ、インスピレーションが湧いた瞬間の輝きであれ、手首を軽く上げるだけで、深遠な思考と洞察が流星のようにあなたの手に届きます。\n\n**特徴：**\n- **Watch-First Design**: Apple Watch のために構築された独立した対話体験。\n- **Aesthetic UI**: 複雑さを排除し、コンテンツの本質へ。流れるようなアニメーションと没入感のあるタイポグラフィ。\n- **Seamless Sync**: iOS と watchOS の完璧な連携。\n- **Deep Integration**: ネイティブなパフォーマンスと触覚フィードバック。\n\n---\n\n## Preview\n\n<div align=\"center\">\n    <img src=\"./assets/preview_watch.png\" width=\"45%\" alt=\"Watch Preview\">\n    <img src=\"./assets/preview.png\" width=\"45%\" alt=\"App Preview\">\n</div>\n\n## Get it | 获取 | 入手\n\n[![GitHub](https://img.shields.io/badge/GitHub-ETOS%20LLM%20Studio-black?logo=github)](https://github.com/Eric-Terminal/ETOS-LLM-Studio)\n"
  },
  {
    "path": "docs/Geneplore AI/README.md",
    "content": "# [Geneplore AI](https://geneplore.com/bot)\n\n## Geneplore AI is building the world's easiest way to use AI - Use 50+ models, all on Discord\n\nChat with the all-new Deepseek v3, GPT-4o, Claude 3 Opus, LLaMA 3, Gemini Pro, FLUX.1, and ChatGPT with **one bot**. Generate videos with Stable Diffusion Video, and images with the newest and most popular models available.\n\nDon't like how the bot responds? Simply change the model in *seconds* and continue chatting like normal, without adding another bot to your server. No more fiddling with API keys and webhooks - every model is completely integrated into the bot.\n\n**NEW:** Try the most powerful open AI model, Deepseek v3, for free with our bot. Simply type /chat and select Deepseek in the model list.\n\n![image](https://github.com/user-attachments/assets/14db7e3c-c2c7-46d7-9fe1-5a5d1e3fc856)\n\nUse the bot trusted by over 60,000 servers and hundreds of paying subscribers, without the hassle of multiple $20/month subscriptions and complicated programming.\n\nhttps://geneplore.com\n\n© 2025 Geneplore AI, All Rights Reserved.\n"
  },
  {
    "path": "docs/Lulu Translate/README.md",
    "content": "<img src=\"https://static.eudic.net/web/trans/en_trans.png\" width=\"64\" height=\"auto\" />\n\n# [Lulu Translate](https://www.eudic.net/v4/en/app/plugins)\n\nThe plugin provides mouse selection translation, paragraph-by-paragraph comparison translation, and PDF document translation functionalities. It can utilize various translation engines, such as DeepSeek AI, Bing, GPT, Google, etc.\n\n## UI\n\n![image](https://static.eudic.net/web/homepage/en_pluginsWelcome_1908.png)\n![image](https://static.eudic.net/web/homepage/en_pluginsWelcome_19003.png)\n\n## Configure DeepSeek API\n\n![image](assets/ScreenShot-2024-07-05-at-06.21.45.png)\n"
  },
  {
    "path": "docs/Lulu Translate/README_cn.md",
    "content": "<img src=\"https://static.eudic.net/web/trans/en_trans.png\" width=\"64\" height=\"auto\" />\n\n# [欧路翻译](https://www.eudic.net/v4/en/app/plugins)\n\n提供鼠标划词搜索、逐段对照翻译、PDF 文献翻译功能。可以使用支持 DeepSeek AI, Bing、GPT、Google 等多种翻译引擎。\n\n## UI\n\n![image](https://static.eudic.net/web/homepage/en_pluginsWelcome_1908.png)\n![image](https://static.eudic.net/web/homepage/en_pluginsWelcome_19003.png)\n\n## 配置 DeepSeek API\n\n![image](assets/ScreenShot-2024-07-05-at-06.21.45.png)\n"
  },
  {
    "path": "docs/Ncurator/README.md",
    "content": "<img src=\"./assets/logo.png\" width=\"64\" height=\"auto\" />\n\n# [Ncurator](https://www.ncurator.com)\n\nKnowledge Base AI Q&A Assistant -\nLet AI help you organize and analyze knowledge\n\n## UI\n<img src=\"./assets/screenshot3.png\" width=\"360\" height=\"auto\" />\n\n## Integrate with Deepseek API\n<img src=\"./assets/screenshot2.png\" width=\"360\" height=\"auto\" />"
  },
  {
    "path": "docs/Ncurator/README_cn.md",
    "content": "<img src=\"./assets/logo.png\" width=\"64\" height=\"auto\" />\n\n# [Ncurator](https://www.ncurator.com)\n\n知识库AI问答助手-让AI帮助你整理与分析知识\n\n## UI\n<img src=\"./assets/screenshot1.png\" width=\"360\" height=\"auto\" />\n\n## 配置 Deepseek API\n<img src=\"./assets/screenshot2.png\" width=\"360\" height=\"auto\" />"
  },
  {
    "path": "docs/Rearview/README.md",
    "content": "<img src=\"./assets/favicon.webp\" width=\"64\" height=\"auto\" /> \n\n# [Rearview - History Knowledge base](https://rearview-ai.vercel.app/)\n\nRecall Your Browsing History Instantly with Rearview – Interrogate Your Digital Past.\n\n## 📸 Screenshot\n\n<div align=\"center\">\n  <img src=\"assets/screenshot.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n## 🐳 Integrate with Deepseek\n\n<div align=\"center\">\n  <img src=\"assets/screenshot_api.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n"
  },
  {
    "path": "docs/Rearview/README_cn.md",
    "content": "<img src=\"./assets/favicon.webp\" width=\"64\" height=\"auto\" /> \n\n# [Rearview - 让历史记录成为知识库](https://rearview-ai.vercel.app/)\n\n通过Rearview快速回忆您的历史记录 —— 向历史发问!\n\n## 📸 截图\n\n<div align=\"center\">\n  <img src=\"assets/screenshot.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n## 🐳 集成Deepseek\n\n<div align=\"center\">\n  <img src=\"assets/screenshot_api_cn.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n"
  },
  {
    "path": "docs/Rearview/README_es.md",
    "content": "<img src=\"./assets/favicon.webp\" width=\"64\" height=\"auto\" /> \n\n# [Rearview - Base de Conocimiento del Historial](https://rearview-ai.vercel.app/)\n\nRecuerda tu historial de navegación instantáneamente con Rearview – Interroga tu pasado digital.\n\n## 📸 Captura de pantalla\n\n<div align=\"center\">\n  <img src=\"assets/screenshot.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n## 🐳 Integración con Deepseek\n\n<div align=\"center\">\n  <img src=\"assets/screenshot_api.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n"
  },
  {
    "path": "docs/Rearview/README_ja.md",
    "content": "<img src=\"./assets/favicon.webp\" width=\"64\" height=\"auto\" /> \n\n# [Rearview - 履歴をナレッジベースに](https://rearview-ai.vercel.app/)\n\nRearviewで履歴を素早く振り返る — 過去に質問しよう！\n\n## 📸 スクリーンショット\n\n<div align=\"center\">\n  <img src=\"assets/screenshot.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n## 🐳 Deepseekとの統合\n\n<div align=\"center\">\n  <img src=\"assets/screenshot_api.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n"
  },
  {
    "path": "docs/Rearview/README_zh_tw.md",
    "content": "<img src=\"./assets/favicon.webp\" width=\"64\" height=\"auto\" /> \n\n# [Rearview - 讓歷史記錄成為知識庫](https://rearview-ai.vercel.app/)\n\n透過 Rearview 快速回憶您的歷史記錄 —— 向歷史發問！\n\n## 📸 截圖\n\n<div align=\"center\">\n  <img src=\"assets/screenshot.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n## 🐳 整合 Deepseek\n\n<div align=\"center\">\n  <img src=\"assets/screenshot_api_cn.webp\" alt=\"Rearview Screenshot\" width=\"100%\" style=\"border-radius: 10px; margin: 20px 0;\"/>\n</div>\n\n"
  },
  {
    "path": "docs/SiYuan/README.md",
    "content": "# README\n\n‍\n\n​![image](https://b3log.org/images/brand/siyuan-128.png)​\n\n---\n\nSiYuan is a privacy-first personal knowledge management system that supports complete offline usage, as well as end-to-end encrypted data sync.\n\nFuse blocks, outlines, and bidirectional links to refactor your thinking.\n\n‍\n\n## STEP1.\n\nApply a token from [deepseek open platform](https://platform.deepseek.com/)\n\n‍\n\n## STEP 2\n\nEnter the Settings interface\n\n​![image](assets/image-20250122163007-hkuruoe.png)​\n\n‍\n\n## STEP 3\n\nNavigate to the \"AI\" tab in Settings and configure the following:\n\n* Enter your DeepSeek API key in the text field\n* Configure the endpoint URL and model details:\n\n  * URI: `https://api.deepseek.com`​\n  * Model: `deepseek-chat`​\n  * Temperature: 1.3\n\n​![image](assets/image-20250122162241-32a4oma.png)​\n\n‍\n\nhow to use:\n\n‍\n\n​![image](assets/image-20250122162425-wlsgw0u.png)​\n\n‍\n"
  },
  {
    "path": "docs/SiYuan/README_cn.md",
    "content": "# README_cn\n\n​![image](https://b3log.org/images/brand/siyuan-128.png)​\n\n---\n\n思源笔记是一款注重隐私的个人知识管理系统，支持完全离线使用，并提供端到端加密的数据同步功能。通过融合块、大纲和双向链接，重构你的思维方式。\n\n## 第一步\n\n从[深度求索开放平台](https://platform.deepseek.com/)申请一个令牌。\n\n## 第二步\n\n进入设置界面\n\n​![image](assets/image-20250122163007-hkuruoe.png)​\n\n## 第三步\n\n在设置中导航到“AI”选项卡并进行以下配置：\n\n* 在文本框中输入你的DeepSeek API密钥\n* 配置端点URL和模型详细信息：\n\n  * URI: `https://api.deepseek.com/v1/`​\n  * 模型: `deepseek-chat`​\n  * 温度: 1.3\n\n​![image](assets/image-20250122162241-32a4oma.png)​\n\n如何使用：\n\n​![image](assets/image-20250122162425-wlsgw0u.png)​\n\n‍\n"
  },
  {
    "path": "docs/SwiftChat/README.md",
    "content": "# [SwiftChat](https://github.com/aws-samples/swift-chat)\n\n[SwiftChat](https://github.com/aws-samples/swift-chat) is a lightning-fast, cross-platform AI chat application built with React Native. It delivers native performance on Android, iOS, iPad, Android tablets and macOS. Features include real-time streaming chat, rich Markdown support (tables, code blocks, LaTeX), AI image generation, customizable system prompts, quick model switching, and multimodal capabilities. Supports multiple AI providers including DeepSeek, Amazon Bedrock, Ollama and OpenAI Compatible Models. The minimalist UI design and optimized architecture ensure instant launch and responsive interactions across all platforms.\n\n## UI\n\n![UI](./assets/promo.png)\n\n## Integrate with Deepseek API\n\n![Mac Settings](./assets/settings.png)\n\n## Using System Prompt with DeepSeek\n\n<img src=\"./assets/system-prompt.png\" width=\"50%\">\n\nFor more information, Please refer to [SwiftChat GitHub](https://github.com/aws-samples/swift-chat)\n"
  },
  {
    "path": "docs/SwiftChat/README_cn.md",
    "content": "# [SwiftChat](https://github.com/aws-samples/swift-chat)\n\n[SwiftChat](https://github.com/aws-samples/swift-chat) 是一个基于 React Native 构建的闪电般快速的跨平台 AI 聊天应用。它在 Android、iOS、iPad、Android 平板电脑和 macOS 上都能提供原生性能体验。功能包括实时流式聊天、丰富的 Markdown 支持（表格、代码块、LaTeX）、AI 图像生成、可自定义系统提示词、快速模型切换，以及多模态能力。支持多个 AI 提供商，包括 DeepSeek、Amazon Bedrock、Ollama 和 OpenAI API 兼容的模型。极简的 UI 设计和优化的架构确保了在所有平台上都能实现即时启动和流畅的交互体验。\n\n## 界面展示\n\n![UI](./assets/promo.png)\n\n## 集成 Deepseek API\n\n![Mac Settings](./assets/settings.png)\n\n## 使用 DeepSeek 的系统提示词\n<img src=\"./assets/system-prompt.png\" width=\"50%\">\n\n更多信息请访问 [SwiftChat GitHub](https://github.com/aws-samples/swift-chat)\n"
  },
  {
    "path": "docs/Typral/README.md",
    "content": "<img src=\"https://www.typral.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" width=\"64\" height=\"auto\" />\n\n# [Typral](https://www.typral.com)\n\nFast AI writer assistant - Let AI help you quickly improve article, paper, text...\n\n## UI\n<img src=\"./assets/screenshot1.png\" width=\"360\" height=\"auto\" />\n\n## 配置 Deepseek API\n<img src=\"./assets/screenshot2.png\" width=\"360\" height=\"auto\" />"
  },
  {
    "path": "docs/Typral/README_cn.md",
    "content": "<img src=\"https://www.typral.com/_next/image?url=%2Ffavicon.ico&w=96&q=75\" width=\"64\" height=\"auto\" />\n\n# [Typral](https://www.typral.com)\n\n超快的AI写作助手 - 让AI帮你快速优化日报,文章,文本等等...\n\n## UI\n<img src=\"./assets/screenshot1.png\" width=\"360\" height=\"auto\" />\n\n## 配置 Deepseek API\n<img src=\"./assets/screenshot2.png\" width=\"360\" height=\"auto\" />"
  },
  {
    "path": "docs/UOS AI/README.md",
    "content": "___\n\n![image](assets/uos-ai-assistant.svg)\n\n___\n\n# [UOS AI](https://www.deepin.org)\n\nUOS AI is a powerful AI assistant application within the Deepin operating system. \n\nIt offers unique cross-application capabilities, enabling deep integration with built-in email and browser applications, providing you with contextualized AI capabilities.\n\n# UI\n\n![image](assets/ui-en.png)\n\n## Integrate with DeepSeek API\n\n## Default Option\n\n1. Open the \"Settings\" option in UOS AI, select \"DeepSeek-R1\" in the \"Model Configuration\" under \"Online model-Add\" to enter the UOS AI model addition interface.\n\n2. Select \"DeepSeek-R1\" in the \"LLM\".\n\n3. Fill in any name in the \"Account\".\n\n4. Enter your API key in the \"APIKey\".\n\n![image](assets/r1-en.png)\n\n## Custom Option\n\n1. Select \"Custom\" in the \"LLM\".\n2. Enter any name you like in the \"Account\".\n3. Enter your API key in the \"APIKey\".\n4. Add the name of the model you want to use in the \"Model Name\".\n   -  For DeepSeek-V3, enter: deepseek-chat\n   - For DeepSeek-R1, enter: deepseek-reasoner\n5. Enter the following request address to \"Domain\": https://api.deepseek.com/chat/completions\n\n![image](assets/custom-v3-en.png)\n"
  },
  {
    "path": "docs/UOS AI/README_cn.md",
    "content": "___\n\n![image](assets/uos-ai-assistant.svg)\n\n___\n\n# [UOS AI](https://www.deepin.org)\n\nUOS AI是Deepin操作系统中功能强大的AI助手应用。\n\n它具有独特的跨应用能力，可以深度集成到系统自带的邮箱、浏览器中，为您提供场景化的AI能力。\n\n# 界面\n\n![image](assets/ui.png)\n\n## 接入DeepSeek API\n\n## 默认添加\n\n1. 打开 UOS AI 的「设置」选项，在「模型配置」中选择「在线模型-添加」，进入UOS AI的添加模型界面。\n\n2. 在「模型类型」中选择「DeepSeek-R1」。\n\n3. 在「账号名称」中随意填写名称。\n\n4. 在「APIKey」中填写您的API key。\n\n![image](assets/r1.png)\n\n## 自定义添加\n\n1. 在「模型类型」中选择「自定义」。\n2. 在「账号名称」中随意填写名称。\n3. 在「APIKey」中填写您的API key。\n4. 「模型名」添加要使用的模型名称。\n   -  DeepSeek-V3填写：deepseek-chat\n   - DeepSeek-R1填写：deepseek-reasoner\n\n5. 「请求地址」填写：https://api.deepseek.com/chat/completions\n\n![image](assets/custom-v3.png)\n"
  },
  {
    "path": "docs/_logo svg/guidelines.md",
    "content": "# DeepSeek品牌素材使用规范\n我们为使用和分发DeepSeek模型、API的开发者提供了DeepSeek官方品牌素材，方便开发者在对外提供服务中展示和使用。开发者在使用DeepSeek的品牌素材前，请了解：\n- 请确保 准确、清晰、完整及美观地 使用DeepSeek的素材内容，避免使用错误、仿冒或低质的素材内容，且不得随意修改。\n- 请在 实际接入DeepSeek的模型或API 的前提下使用，不得故意虚假宣传、诱导误认与DeepSeek有合作。\n- 不得利用DeepSeek的素材内容，故意冒充DeepSeek官方，或通过歧义、暗示等诱导误认为是DeepSeek官方。\n- 使用品牌素材时，请遵守 商标权、著作权等知识产权 的法律要求。\n对于不符合规范的使用方，我们有权撤销使用DeepSeek品牌素材的许可。\n\n---\n# DeepSeek Brand Asset Usage Guidelines\nWe provide official DeepSeek brand assets for developers who use or distribute DeepSeek models or APIs, making it convenient for them to showcase and utilize these assets when offering services. Before using DeepSeek's brand assets, developers should understand:\n- Please ensure the accurate, clear, complete, and aesthetically pleasing use of DeepSeek's asset content. Avoid using incorrect, imitated, or low-quality content, and do not modify it arbitrarily.\n- Please use the assets only when actually integrating DeepSeek's models or APIs. Do not intentionally make false claims or mislead others into believing there is a partnership with DeepSeek.\n- Do not use DeepSeek's asset content to intentionally impersonate DeepSeek's official channels, or to mislead through ambiguity or implication that you are DeepSeek's official representative.\n- When using brand assets, please comply with legal requirements regarding intellectual property rights such as trademarks and copyrights.\nFor those who do not comply with these guidelines, we reserve the right to revoke the permission to use DeepSeek brand assets."
  },
  {
    "path": "docs/agentUniverse/README.md",
    "content": "___\n<img src=\"assets/agentUniverse_logo.jpg\" width=\"auto\" height=\"auto\" />\n\n___\n\n# [agentUniverse](https://github.com/antgroup/agentUniverse)\n\nagentUniverse is a multi-agent collaboration framework designed for complex business scenarios. It offers rapid and user-friendly development capabilities for LLM agent applications, with a focus on mechanisms such as agent collaborative scheduling, autonomous decision-making, and dynamic feedback. The framework originates from Ant Group's real-world business practices in the financial industry. In June 2024, agentUniverse achieved full integration support for the DeepSeek series of models.\n\n## Concepts\n\n<img src=\"https://raw.githubusercontent.com/antgroup/agentUniverse/refs/heads/master/docs/guidebook/_picture/agentuniverse_structure_en.png\" />\n\n## Integrate with Deepseek API\n\n### Configure via Python code\n```python\nimport os\nos.environ['DEEPSEEK_API_KEY'] = 'sk-***'\nos.environ['DEEPSEEK_API_BASE'] = 'https://xxxxxx'\n```\n### Configure via the configuration file\nIn the custom_key.toml file under the config directory of the project, add the configuration:\n```toml\nDEEPSEEK_API_KEY=\"sk-******\"\nDEEPSEEK_API_BASE=\"https://xxxxxx\"\n```\n\nFor more details, please refer to the [Documentation: DeepSeek Integration](https://github.com/antgroup/agentUniverse/blob/master/docs/guidebook/en/In-Depth_Guides/Components/LLMs/DeepSeek_LLM_Use.md)\n\n"
  },
  {
    "path": "docs/agentUniverse/README_cn.md",
    "content": "___\n<img src=\"assets/agentUniverse_logo.jpg\" width=\"auto\" height=\"auto\" />\n\n___\n\n# [agentUniverse](https://github.com/antgroup/agentUniverse)\n\nagentUniverse 是一个面向复杂业务场景设计的多智能体协作框架。其提供了快速易用的大模型智能体应用搭建能力，并着重于提供智能体协同调度、自主决策与动态反馈等机制，其源自蚂蚁集团在金融领域的真实业务实践沉淀。agentUniverse于2024年6月全面接入支持deepseek系列模型。\n\n## 设计理念\n\n<img src=\"https://raw.githubusercontent.com/antgroup/agentUniverse/refs/heads/master/docs/guidebook/_picture/agentuniverse_structure.png\" />\n\n## 在项目中使用 deepseek API\n\n### 通过python代码配置\n必须配置：DEEPSEEK_API_KEY  \n可选配置：DEEPSEEK_API_BASE\n```python\nimport os\nos.environ['DEEPSEEK_API_KEY'] = 'sk-***'\nos.environ['DEEPSEEK_API_BASE'] = 'https://xxxxxx'\n```\n### 通过配置文件配置\n在项目的config目录下的custom_key.toml当中，添加配置：\n```toml\nDEEPSEEK_API_KEY=\"sk-******\"\nDEEPSEEK_API_BASE=\"https://xxxxxx\"\n```\n\n更多使用详情可参阅[官方文档:DeepSeek接入使用](https://github.com/antgroup/agentUniverse/blob/master/docs/guidebook/zh/In-Depth_Guides/%E7%BB%84%E4%BB%B6%E5%88%97%E8%A1%A8/%E6%A8%A1%E5%9E%8B%E5%88%97%E8%A1%A8/DeepSeek%E4%BD%BF%E7%94%A8.md)\n\n"
  },
  {
    "path": "docs/agentUniverse/README_ja.md",
    "content": "___\n<img src=\"assets/agentUniverse_logo.jpg\" width=\"auto\" height=\"auto\" />\n\n___\n\n# [agentUniverse](https://github.com/antgroup/agentUniverse)\n\nagentUniverseは、複雑なビジネスシーン向けに設計されたマルチエージェント協調フレームワークです。迅速で使いやすい大規模モデルのインテリジェントエージェントアプリケーション構築能力を提供し、特にエージェント間の協調スケジューリング、自律的な意思決定、動的なフィードバックなどのメカニズムに重点を置いています。これは、Ant Groupの金融業界における実践的なビジネス経験に基づいて開発されました。agentUniverseは、2024年6月にDeepSeekシリーズモデルのサポートを全面的に統合しました。\n\n## 概念\n\n<img src=\"https://raw.githubusercontent.com/antgroup/agentUniverse/refs/heads/master/docs/guidebook/_picture/agentuniverse_structure_en.png\" />\n\n## Deepseek APIと統合する\n\n### Pythonコードを使って設定する\n```python\nimport os\nos.environ['DEEPSEEK_API_KEY'] = 'sk-***'\nos.environ['DEEPSEEK_API_BASE'] = 'https://xxxxxx'\n```\n### 設定ファイルを使って設定する\nプロジェクトのconfigディレクトリ内のcustom_key.tomlファイルに、設定を追加します：\n```toml\nDEEPSEEK_API_KEY=\"sk-******\"\nDEEPSEEK_API_BASE=\"https://xxxxxx\"\n```\n\n詳細についてはドキュメントを参照してください - [Documentation: DeepSeek Integration](https://github.com/antgroup/agentUniverse/blob/master/docs/guidebook/en/In-Depth_Guides/Components/LLMs/DeepSeek_LLM_Use.md).\n\n"
  },
  {
    "path": "docs/aingdesk/README.md",
    "content": "# AingDesk\n\n[简体中文](README.zh_cn.md)\n\n🚀 **Brief Introduction in One Sentence**  \n\nDeploy DeepSeek or other AI models on your computer with just one click.\n\n✅ **Core Features**  \n\n- Deploy DeepSeek or other AI models with one click.\n  ![image](.github/assets/img/1_en.png)\n\n  \n- Simple to operate with a user-friendly interface.\n  ![image](https://github.com/user-attachments/assets/2c7a419b-aeaa-4b5a-8c80-6bee720d366c)\n\n- Multi-source knowledge base support for enhanced data management.\n  ![image](https://github.com/user-attachments/assets/51a9dc96-ba1c-419d-9d27-1be6268778da)\n\n\n- Built-in chat interface for seamless interaction.  \n- Share your projects with friends online.  \n- Support for web search and dynamic data fetching.  \n\n\n✨ **Technical Highlights**  \n\n- Visual one-click deployment for hassle-free setup.  \n- Modular architecture for extensibility and customization.  \n- Optimized for performance on both local and cloud environments.  \n\n🎯 **Development Plan**  \n\n- Local deployment of text-to-image hybrid models for creative workflows.\n\n📥 **Quick Installation**  \n\n- [Download from the official website.](https://www.aingdesk.com/en/download.html)  \n- [Download from GitHub.](https://github.com/aingdesk/AingDesk/releases)  \n- [Download from CNB.](https://cnb.cool/aingdesk/AingDesk/-/releases/)  \n"
  },
  {
    "path": "docs/aingdesk/README.zh_cn.md",
    "content": "**🚀一句话简介**\n\n一键把DeepSeek或其他AI模型部署在你电脑\n\n**✅核心功能**\n\n- 一键部署DeepSeek或其他AI模型\n  ![image](assets/img/1_zh.png)\n\n- 多数据源知识库支持\n  ![alt text](assets/img/2_zh.png)\n\n- 支持第三方API接口\n  ![alt text](assets/img/3_zh.png)\n\n- 操作简单\n- 内置聊天界面\n- 可在线分享给朋友使用\n- 支持网络搜索和动态数据获取\n\n**✨技术亮点**\n\n- 可视化一键部署\n\n🎯 **开发计划**  \n\n- 智能体\n- 本地部署文生图混合模型\n\n**📥快速安装**\n\n- [官网下载](https://www.aingdesk.com/zh/download.html)   \n- [从 CNB 下载](https://cnb.cool/aingdesk/AingDesk/-/releases/) \n- [从 Github 下载](https://github.com/aingdesk/AingDesk/releases)  \n"
  },
  {
    "path": "docs/anda/README.md",
    "content": "# `Anda`\n\n> 🤖 A Rust framework for AI agent development, designed to build a highly composable, autonomous, and perpetually memorizing network of AI agents.\n\n**Anda Source Code**: [https://github.com/ldclabs/anda](https://github.com/ldclabs/anda)\n\n**AI Agent Example**: [https://x.com/AndaICP](https://x.com/AndaICP)\n\nAnda utilizes DeepSeek as its primary LLM service provider to deliver robust thinking and decision-making capabilities for the agent.\n\n## 🤖 Introduction\n\n`Anda` is an innovative framework for intelligent agent development, designed to build a highly composable, autonomous, and perpetually memorizing network of AI agents. By connecting agents across various industries, Anda aims to create a super AGI system, advancing artificial intelligence to new heights.\n\n![Anda Diagram](./assets/anda_diagram.webp)\n\n### ✨ Key Features\n\n1. **Composability**:\n   Anda agents specialize in solving domain-specific problems and can flexibly combine with other agents to tackle complex tasks. When a single agent cannot solve a problem alone, it collaborates with others to form a robust problem-solving network. This modular design allows Anda to adapt to diverse needs.\n\n2. **Simplicity**:\n   Anda emphasizes simplicity and ease of use, enabling developers to quickly build powerful and efficient agents. Non-developers can also create their own agents through simple configurations, lowering the technical barrier and inviting broader participation in agent development and application.\n\n3. **Trustworthiness**:\n   Anda agents operate within a decentralized trusted execution environment (dTEE) based on Trusted Execution Environments (TEEs), ensuring security, privacy, and data integrity. This architecture provides a highly reliable infrastructure for agent operations, safeguarding data and computational processes.\n\n4. **Autonomy**:\n   Anda agents derive permanent identities and cryptographic capabilities from the ICP blockchain, combined with the reasoning and decision-making abilities of large language models (LLMs). This allows agents to autonomously and efficiently solve problems based on their experiences and knowledge, adapting to dynamic environments and making effective decisions in complex scenarios.\n\n5. **Perpetual Memory**:\n   The memory states of Anda agents are stored on the ICP blockchain and within the trusted storage network of dTEE, ensuring continuous algorithm upgrades, knowledge accumulation, and evolution. This perpetual memory mechanism enables agents to operate indefinitely, even achieving \"immortality\", laying the foundation for a super AGI system.\n\n### 🧠 Vision and Goals\n\nAnda's goal is to create and connect countless agents, building an open, secure, trustworthy, and highly collaborative network of agents, ultimately realizing a super AGI system. We believe Anda will bring revolutionary changes across industries, driving the widespread application of AI technology and creating greater value for human society.\n"
  },
  {
    "path": "docs/anda/README_cn.md",
    "content": "# `Anda`\n\n> 🤖 一个专为 AI 智能体开发设计的 Rust 语言框架，致力于构建高度可组合、自主运行且具备永久记忆能力的 AI 智能体网络。\n\n**Anda 源代码**：[https://github.com/ldclabs/anda](https://github.com/ldclabs/anda)\n\n**AI Agent 应用实例**：[https://x.com/AndaICP](https://x.com/AndaICP)\n\nAnda 使用 DeepSeek 作为首要的 LLM 服务提供商，以提供强大的智能体思考和决策能力。\n\n## 🐼 简介\n\n`Anda` 是一个创新的智能体开发框架，旨在构建一个高度可组合、自主性强且具有永久记忆的 AI 智能体网络。通过连接各行各业的智能体，Anda 致力于打造一个超级 AGI 系统，推动人工智能向更高层次发展。\n\n![Anda Diagram](./assets/anda_diagram.webp)\n\n### ✨ 核心特性\n\n1. **可组合性**：\n   Anda 智能体专注于解决特定领域的问题，并通过灵活组合不同的智能体来应对复杂任务。当单个智能体无法独立解决问题时，它能够与其他智能体协作，形成强大的问题解决网络。这种模块化设计使得 Anda 能够灵活应对多样化的需求。\n\n2. **简洁性**：\n   Anda 的设计理念强调简洁易用，旨在帮助开发者快速构建功能强大且高效的智能体。同时，非开发者也可以通过简单的配置创建自己的智能体，降低了技术门槛，使更多人能够参与到智能体的开发与应用中。\n\n3. **可信性**：\n   Anda 智能体运行在基于可信执行环境（TEEs）的去中心化可信计算环境（dTEE）中，确保了智能体的安全性、隐私性和数据完整性。这种架构为智能体的运行提供了高度可信的基础设施，保障了数据和计算过程的安全。\n\n4. **自主性**：\n   Anda 智能体从 ICP 区块链获取永久身份和加密能力，并结合大语言模型的思考和决策能力，使其能够根据自身的经验和知识自主、高效地解决问题。这种自主性使智能体能够适应动态环境，并在复杂场景中做出高效决策。\n\n5. **永久记忆**：\n   Anda 智能体的记忆状态存储在 ICP 区块链和 dTEE 的可信存储网络中，确保其能够持续升级算法、积累知识并不断进化。这种永久记忆机制使智能体能够长久运行，甚至实现“永生”，为构建超级 AGI 系统奠定基础。\n\n### 🧠 愿景与目标\n\nAnda 的目标是通过创建和连接无数智能体，构建一个开放、安全、可信、高度协同的智能体网络，最终实现超级 AGI 系统。我们相信，Anda 将为各行各业带来革命性的变革，推动人工智能技术在更广泛的领域中落地应用，为人类社会创造更大的价值。"
  },
  {
    "path": "docs/anything-copilot/README.md",
    "content": "# [**Anything Copilot**](https://github.com/baotlake/anything-copilot)\n\n> <sub>![](./assets/logo_16x16.svg)</sub> Anything Copilot is a browser extension that enables seamless access to mainstream AI tools directly from your sidebar. For instance, you can open AI chat interfaces like DeepSeek within the sidebar, effectively transforming it into your AI Copilot that remains accessible while you browse.\n\n**Install in Chrome Web Store**： [Anything Copilot - A more powerful sidebar, split-screen, and AI assistant](https://chromewebstore.google.com/detail/anything-copilot-a-more-p/lilckelmopbcffmglfmfhelaajhjpcff)\n\n**Install in Edge Add-ons**： [Anything Copilot - A more powerful sidebar, split-screen, and AI assistant](https://microsoftedge.microsoft.com/addons/detail/anything-copilot-a-more/lbeehbkcmjaopnlccpjcdgamcabhnanl)\n\n\n![](./assets/Screenshot_DeepSeek.webp)\n"
  },
  {
    "path": "docs/anything-copilot/README_cn.md",
    "content": "# [**Anything Copilot**](https://github.com/baotlake/anything-copilot)\n\n> <sub>![](./assets/logo_16x16.svg)</sub> Anything Copilot 是一款可以让你在侧边栏无缝使用任意主流AI工具的浏览器插件。例如，你可以在侧边栏中打开 DeepSeek 等 AI 聊天页面 ，把 DeekSeek 变成你的侧边栏中的 AI Copilot 。\n\n**在 Chrome Web Store 安装**： [Anything Copilot - 更强大的侧边栏，分屏，AI 助手](https://chromewebstore.google.com/detail/anything-copilot-%E6%9B%B4%E5%BC%BA%E5%A4%A7%E7%9A%84%E4%BE%A7%E8%BE%B9%E6%A0%8F%EF%BC%8C/lilckelmopbcffmglfmfhelaajhjpcff?hl=zh)\n\n**在 Edge Add-ons 安装**： [Anything Copilot - 更强大的侧边栏，分屏，AI 助手](https://microsoftedge.microsoft.com/addons/detail/anything-copilot-%E6%9B%B4%E5%BC%BA%E5%A4%A7%E7%9A%84%E4%BE%A7%E8%BE%B9/lbeehbkcmjaopnlccpjcdgamcabhnanl?hl=zh)\n\n\n![](./assets/Screenshot_DeepSeek.webp)\n"
  },
  {
    "path": "docs/autoflow/README.md",
    "content": "# Autoflow\n\n<a href=\"https://trendshift.io/repositories/12294\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/12294\" alt=\"pingcap%2Fautoflow | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/></a>\n\n[AutoFlow](https://github.com/pingcap/autoflow) is an open-source knowledge base tool based on GraphRAG (Graph-based Retrieval-Augmented Generation), built on [TiDB](https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community) Vector, LlamaIndex, and DSPy. It provides a Perplexity-like search interface and allows easy integration of AutoFlow's conversational search window into your website by embedding a simple JavaScript snippet.\n\n## UI\n\n1. **Perplexity-style Conversational Search page**: Our platform features an advanced built-in website crawler, designed to elevate your browsing experience. This crawler effortlessly navigates official and documentation sites, ensuring comprehensive coverage and streamlined search processes through sitemap URL scraping.\n\n    ![Image](https://github.com/user-attachments/assets/50a4e5ce-8b93-446a-8ce7-11ed7844bd1e)\n\n2. **Embeddable JavaScript Snippet**: Integrate our conversational search window effortlessly into your website by copying and embedding a simple JavaScript code snippet. This widget, typically placed at the bottom right corner of your site, facilitates instant responses to product-related queries.\n\n    ![Image](https://github.com/user-attachments/assets/f0dc82db-c14d-4863-a242-c7da3a719568)\n\n## Integrate with Deepseek API\n\n- Click the tab `Models` then `LLMs` to enter the LLM model management page.\n- Click the `Create` button to create a new LLM model.\n- Input data like below, then click the `Create LLM` button.\n\n![Image](https://github.com/user-attachments/assets/875cac18-707b-465f-ac62-89ddb416f94d)\n"
  },
  {
    "path": "docs/autoflow/README_cn.md",
    "content": "# Autoflow\n\n<a href=\"https://trendshift.io/repositories/12294\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/12294\" alt=\"pingcap%2Fautoflow | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/></a>\n\n[AutoFlow](https://github.com/pingcap/autoflow) 是一个基于 GraphRAG（基于图的检索增强生成）的开源知识库工具，构建于 [TiDB](https://www.pingcap.com/ai?utm_source=tidb.ai&utm_medium=community) Vector、LlamaIndex 和 DSPy 之上。它提供类似 Perplexity 的搜索界面，并允许通过嵌入简单的 JavaScript 代码片段，将 AutoFlow 的对话式搜索窗口轻松集成到您的网站中。\n\n## UI 界面\n\n1. **Perplexity 风格的对话式搜索页面**：我们的平台配备了高级内置网站爬虫，旨在提升您的浏览体验。该爬虫能够轻松抓取官方网站和文档站点，通过 sitemap 抓取，实现全面覆盖和高效搜索。\n\n    ![Image](https://github.com/user-attachments/assets/50a4e5ce-8b93-446a-8ce7-11ed7844bd1e)\n\n2. **可嵌入的 JavaScript 代码片段**：通过复制并嵌入一段简单的 JavaScript 代码，即可轻松将我们的对话式搜索窗口集成到您的网站中。此小部件通常放置在网站右下角，可即时回答与产品相关的查询。\n\n    ![Image](https://github.com/user-attachments/assets/f0dc82db-c14d-4863-a242-c7da3a719568)\n\n## 集成 Deepseek API\n\n- 点击 `Models` 选项卡，然后进入 `LLMs` 以进入 LLM 模型管理页面。\n- 点击 `Create` 按钮创建一个新的 LLM 模型。\n- 按照下方示例输入数据，然后点击 `Create LLM` 按钮。\n\n![Image](https://github.com/user-attachments/assets/875cac18-707b-465f-ac62-89ddb416f94d)\n"
  },
  {
    "path": "docs/avante.nvim/README.md",
    "content": "# [avante.nvim](https://github.com/yetone/avante.nvim)\n\n**avante.nvim** is a Neovim plugin designed to emulate the behaviour of the [Cursor](https://www.cursor.com) AI IDE. It provides users with AI-driven code suggestions and the ability to apply these recommendations directly to their source files with minimal effort.\n\n## Features\n\n- **AI-Powered Code Assistance**: Interact with AI to ask questions about your current code file and receive intelligent suggestions for improvement or modification.\n- **One-Click Application**: Quickly apply the AI's suggested changes to your source code with a single command, streamlining the editing process and saving time.\n\n> [!IMPORTANT]\n> \n> The project is in rapid iteration, and this guide was last updated on October 19, 2024. Installation and configuration methods may change after this date, so please refer to the original project's README.md for the most accurate information.\n\n## Installation\n\n### Install via `lazy.nvim`\n\nNavigate to the nvim configuration folder (default on Linux is `~/.config/nvim`) and then to the `lua/plugins` folder. Create a file named `avante.lua` and add the following content:\n\n```lua\nreturn {\n  {\n    \"yetone/avante.nvim\",\n    event = \"VeryLazy\",\n    lazy = false,\n    version = false, -- set this if you want to always pull the latest change\n    opts = {\n      provider = \"deepseek\",\n      vendors = {\n        deepseek = {\n          __inherited_from = \"openai\",\n          api_key_name = \"DEEPSEEK_API_KEY\",\n          endpoint = \"https://api.deepseek.com\",\n          model = \"deepseek-coder\",\n          max_tokens = 8192,\n        },\n      },\n    },\n    -- if you want to build from source then do `make BUILD_FROM_SOURCE=true`\n    build = \"make\",\n    -- build = \"powershell -ExecutionPolicy Bypass -File Build.ps1 -BuildFromSource false\" -- for windows\n    dependencies = {\n      \"nvim-treesitter/nvim-treesitter\",\n      \"stevearc/dressing.nvim\",\n      \"nvim-lua/plenary.nvim\",\n      \"MunifTanjim/nui.nvim\",\n      --- The below dependencies are optional,\n      \"nvim-tree/nvim-web-devicons\", -- or echasnovski/mini.icons\n      \"zbirenbaum/copilot.lua\", -- for providers='copilot'\n      {\n        -- support for image pasting\n        \"HakonHarnes/img-clip.nvim\",\n        event = \"VeryLazy\",\n        opts = {\n          -- recommended settings\n          default = {\n            embed_image_as_base64 = false,\n            prompt_for_file_name = false,\n            drag_and_drop = {\n              insert_mode = true,\n            },\n            -- required for Windows users\n            use_absolute_path = true,\n          },\n        },\n      },\n      {\n        -- Make sure to set this up properly if you have lazy=true\n        'MeanderingProgrammer/render-markdown.nvim',\n        opts = {\n          file_types = { \"markdown\", \"Avante\" },\n        },\n        ft = { \"markdown\", \"Avante\" },\n      },\n    },\n  },\n}\n```\nRestart nvim, and `lazy.nvim` should automatically download and install the avante.nvim plugin and its dependencies based on the above file.\n\n### Other Installation Methods\nhttps://github.com/yetone/avante.nvim?tab=readme-ov-file#installation\n\n## Usage\nhttps://github.com/yetone/avante.nvim?tab=readme-ov-file#usage\n"
  },
  {
    "path": "docs/avante.nvim/README_cn.md",
    "content": "# [avante.nvim](https://github.com/yetone/avante.nvim)\n\n**avante.nvim** 是一个旨在模拟 [Cursor](https://www.cursor.com) AI IDE 的行为的 Neovim 插件。它为用户提供 AI 驱动的代码建议，并能够以最小的努力将这些建议直接应用于他们的源文件。\n\n## 功能\n\n - **AI 驱动的代码辅助**：与 AI 聊天以询问有关您当前代码文件的问题，并接收改进或修改的智能建议。\n - **一键应用**：使用单个命令快速将 AI 建议的更改应用于您的源代码，简化编辑过程并节省时间。\n\n> [!IMPORTANT]\n>\n> 该项目处于快速迭代状态，本指南更新于2024.10.19，在此日期之后的安装配置方法可能会发生变更，请以原项目README.md为准。\n\n\n## 安装\n\n### 通过 `lazy.nvim` 安装\n\n转到nvim的配置文件夹下（linux 默认是`~/.config/nvim`）的 `lua/plugins` 文件夹，创建一个名为 `avante.lua` 的文件，并在其中添加以下内容：   \n```lua\nreturn {\n  {\n    \"yetone/avante.nvim\",\n    event = \"VeryLazy\",\n    lazy = false,\n    version = false, -- set this if you want to always pull the latest change\n    opts = {\n      provider = \"deepseek\",\n      vendors = {\n        deepseek = {\n          __inherited_from = \"openai\",\n          api_key_name = \"DEEPSEEK_API_KEY\",\n          endpoint = \"https://api.deepseek.com\",\n          model = \"deepseek-coder\",\n        },\n      },\n    },\n    -- if you want to build from source then do `make BUILD_FROM_SOURCE=true`\n    build = \"make\",\n    -- build = \"powershell -ExecutionPolicy Bypass -File Build.ps1 -BuildFromSource false\" -- for windows\n    dependencies = {\n      \"nvim-treesitter/nvim-treesitter\",\n      \"stevearc/dressing.nvim\",\n      \"nvim-lua/plenary.nvim\",\n      \"MunifTanjim/nui.nvim\",\n      --- The below dependencies are optional,\n      \"nvim-tree/nvim-web-devicons\", -- or echasnovski/mini.icons\n      \"zbirenbaum/copilot.lua\", -- for providers='copilot'\n      {\n        -- support for image pasting\n        \"HakonHarnes/img-clip.nvim\",\n        event = \"VeryLazy\",\n        opts = {\n          -- recommended settings\n          default = {\n            embed_image_as_base64 = false,\n            prompt_for_file_name = false,\n            drag_and_drop = {\n              insert_mode = true,\n            },\n            -- required for Windows users\n            use_absolute_path = true,\n          },\n        },\n      },\n      {\n        -- Make sure to set this up properly if you have lazy=true\n        'MeanderingProgrammer/render-markdown.nvim',\n        opts = {\n          file_types = { \"markdown\", \"Avante\" },\n        },\n        ft = { \"markdown\", \"Avante\" },\n      },\n    },\n  },\n}\n```\n\n重启 nvim，此时`lazy.nvim`应该会根据上述文件帮你下载安装好 avante.nvim 插件及其依赖项。\n\n### 其他安装方式\n\nhttps://github.com/yetone/avante.nvim?tab=readme-ov-file#installation\n\n## 使用\n\nhttps://github.com/yetone/avante.nvim?tab=readme-ov-file#usage\n"
  },
  {
    "path": "docs/bob_translate/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/96636a42-207e-43df-a683-02e10d13fe34\" width=\"64\" height=\"auto\" /> \n\n# [Bob Translate](https://bobtranslate.com/)\n\nBob Translate is a translation and OCR application on Mac. Use it for translation and OCR, simple and efficient!\n\n## UI\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9e2a0ac5-a284-4c82-bcd3-e7aefd9cd5a8)\n\n\n## Integrate with Deepseek API\nTo use the DeepSeek API, you have to download the plugin below for fee.\nhttps://github.com/openai-translator/bob-plugin-openai-translator\n"
  },
  {
    "path": "docs/bob_translate/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/96636a42-207e-43df-a683-02e10d13fe34\" width=\"64\" height=\"auto\" /> \r\n\r\n# [Bob Translate](https://bobtranslate.com/)\r\n\r\n在任意应用程序中使用 Bob 进行翻译和 OCR，即用即走，简单、快捷、高效！\r\n\r\n## UI\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9e2a0ac5-a284-4c82-bcd3-e7aefd9cd5a8)\r\n\r\n\r\n## Integrate with Deepseek API\r\n可以使用下面的插件(收费)来配置deepseek api.\r\nhttps://github.com/openai-translator/bob-plugin-openai-translator\r\n"
  },
  {
    "path": "docs/chatbox/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/224d547a-6fbc-47c8-859f-aa14813e2b0f\" width=\"64\" height=\"auto\" /> \n\n# [Chatbox](https://chatboxai.app/)\n\nChatbox is a desktop client for multiple LLM models, available on Windows, Mac and Linux.\n\n## UI\n\n<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/cf5ebfd6-1e4d-478f-81fa-8d68d25b7414\" />\n\n## Integrate with Deepseek API\n\n<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/926a87dc-ba2c-4929-9310-c4f1a18c0ce3\" />\n"
  },
  {
    "path": "docs/chatbox/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/224d547a-6fbc-47c8-859f-aa14813e2b0f\" width=\"64\" height=\"auto\" /> \r\n\r\n# [Chatbox](https://chatboxai.app/)\r\n\r\nChatbox 是一个支持多种流行LLM模型的桌面客户端，可在 Windows、Mac 和 Linux 上使用。\r\n\r\n## UI\r\n\r\n<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/cf5ebfd6-1e4d-478f-81fa-8d68d25b7414\" />\r\n\r\n## 配置 deepseek API\r\n\r\n<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/926a87dc-ba2c-4929-9310-c4f1a18c0ce3\" />\r\n"
  },
  {
    "path": "docs/chatgpt_box/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/8a301619-a3de-489b-81fd-69aaa7c1c561\" width=\"64\" height=\"auto\" /> \n\n# [ChatGPT Box](https://github.com/josStorer/chatGPTBox)\n\nChatGPT Box is a deep LLMs integrations in your browser, completely for free.\n\n## UI\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/583b27ec-474a-4c29-aa93-cae44738b438)\n\n\n## Integrate with Deepseek API\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/ab220788-fc68-4c68-b09e-87c620b03820)\n"
  },
  {
    "path": "docs/chatgpt_box/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/8a301619-a3de-489b-81fd-69aaa7c1c561\" width=\"64\" height=\"auto\" /> \r\n\r\n# [ChatGPT Box](https://github.com/josStorer/chatGPTBox)\r\n\r\n将 LLMs 整合到你的浏览器中.\r\n\r\n## UI\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/583b27ec-474a-4c29-aa93-cae44738b438)\r\n\r\n\r\n## 配置 deepseek API\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/ab220788-fc68-4c68-b09e-87c620b03820)\r\n"
  },
  {
    "path": "docs/chatgpt_next_web/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/bb65404c-f867-42d8-ae2b-281fe953ab54\" width=\"64\" height=\"auto\" /> \n\n# [ChatGPT-Next-Web](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web)\n\nOne-Click to get a well-designed cross-platform ChatGPT web UI，support multiple LLMs.\n\n## UI\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/3a827669-e5e4-4fc3-97d7-bcf57efb76d1)\n\n\n## Integrate with Deepseek API\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/996363ca-21e3-42f0-8285-071b209f501f)\n"
  },
  {
    "path": "docs/chatgpt_next_web/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/bb65404c-f867-42d8-ae2b-281fe953ab54\" width=\"64\" height=\"auto\" /> \r\n\r\n# [ChatGPT-Next-Web](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web)\r\n\r\n一键获取设计精良的跨平台ChatGPT网页用户界面，支持流行的LLM.\r\n\r\n## UI\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/3a827669-e5e4-4fc3-97d7-bcf57efb76d1)\r\n\r\n\r\n## 配置 deepseek API\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/996363ca-21e3-42f0-8285-071b209f501f)\r\n"
  },
  {
    "path": "docs/cherrystudio/README.md",
    "content": "<img src=\"https://github.com/kangfenmao/cherry-studio/blob/main/resources/icon.png?raw=true\" width=\"64\" height=\"auto\" style=\"border-radius: 15px\" /> \n\n# [Cherry Studio](https://github.com/kangfenmao/cherry-studio)\n\nCherry Studio: A powerful desktop AI assistant for producer\n\n## Screenshot\n\n<img src=\"https://camo.githubusercontent.com/c85d1d1ec8964a3b9c231714a10f3b1179357d20c21fcb0d54117bc45fa77928/68747470733a2f2f73322e6c6f6c692e6e65742f323032342f30372f31362f494156534f6f72736646517947684d2e706e67\" />\n\n## Integrate with Deepseek API\n\n![](https://raw.githubusercontent.com/kangfenmao/assets/main/images/202407161307342.png)\n\n## Download Cherry Studio\n\nHomepage：https://github.com/kangfenmao/cherry-studio  \nDownload：https://github.com/kangfenmao/cherry-studio/releases  "
  },
  {
    "path": "docs/cherrystudio/README_cn.md",
    "content": "<img src=\"https://github.com/kangfenmao/cherry-studio/blob/main/resources/icon.png?raw=true\" width=\"64\" height=\"auto\" style=\"border-radius: 15px\" /> \n\n# [Cherry Studio](https://github.com/kangfenmao/cherry-studio)\n\nCherry Studio 是一款为创造者而生的 AI 软件，支持多种大语言模型。\n\n## 界面截图\n\n<img src=\"https://camo.githubusercontent.com/c85d1d1ec8964a3b9c231714a10f3b1179357d20c21fcb0d54117bc45fa77928/68747470733a2f2f73322e6c6f6c692e6e65742f323032342f30372f31362f494156534f6f72736646517947684d2e706e67\" />\n\n## 配置 deepseek API\n\n![](https://raw.githubusercontent.com/kangfenmao/assets/main/images/202407161306874.png)\n\n## Cherry Studio 下载地址\n\n项目主页：https://github.com/kangfenmao/cherry-studio  \n下载地址：https://github.com/kangfenmao/cherry-studio/releases  "
  },
  {
    "path": "docs/cline/README.md",
    "content": "# [Cline](https://github.com/cline/cline)\n\nMeet Cline, an AI assistant that can use your CLI aNd Editor.\n\n## Installation\n\n![image](./assets/cline-00.png)\n\n## Key Features of Cline\n\n1. **Agentic Coding with Claude 4.0 Opus**: Cline leverages advanced AI capabilities to handle complex software development tasks step-by-step, going beyond simple code completion or tech support.\n\n2. **File and Project Management**: Cline can create, edit, and explore files within large projects, enabling seamless navigation and modification of codebases.\n\n3. **Terminal Integration**: With user permission, Cline can execute terminal commands and monitor their output, allowing it to react dynamically to issues like dev server errors.\n\n4. **Browser Automation**: For web development, Cline can launch sites in a headless browser, interact with pages (click, type, scroll), and capture screenshots and console logs to debug runtime errors and visual bugs.\n\n5. **Human-in-the-Loop Safety**: Every file change and terminal command requires user approval via a GUI, ensuring a secure and controlled environment for exploring agentic AI capabilities.\n\n6. **Context-Aware Assistance**: Cline analyzes file structures, source code ASTs, and runs regex searches to understand existing projects, ensuring efficient and relevant assistance without overwhelming the context window.\n\n7. **Proactive Error Handling**: Cline monitors linter/compiler errors and proactively fixes issues like missing imports and syntax errors during file editing.\n\n8. **Model Context Protocol (MCP)**: Cline can extend its own capabilities by creating new tools using the MCP, enabling continuous adaptation to user needs.\n\n9. **Task Completion with Ease**: Once a task is completed, Cline presents results with simple terminal commands (e.g., `open -a \"Google Chrome\" index.html`), which users can execute with a single click.\n\n## UI\n\n![image](./assets/cline-01.png)\n\n## Integrate with DeepSeek API\n\n![image](./assets/cline-02.png)\n\n## Best practices\n\n1. **Disable Cline's Auto Approve Feature**: It is recommended to disable Cline's Auto Approve feature when using DeepSeek to reduce resource consumption and minimize the risk of lag caused by concurrent multiple requests.\n\n2. **Use Modified Versions of Cline**: For example, Roo-Cline or ALine. These modified versions carry relatively shorter contexts, handle requests more smoothly, and have a higher cache hit rate, which can help save API call costs.\n\n3. **Use DeepSeek with Caution for Large Projects**: For large code projects, it is not recommended to use DeepSeek + Cline. Large projects typically carry a large amount of code context, which can significantly slow down API request processing.\n\n4. **Switch to Other LLM Providers**: It is recommended to switch to other LLM providers when using Cline for a smoother experience.\n\n## Roo Cline\n\n![image](./assets/roocline-00.png)\n"
  },
  {
    "path": "docs/cline/README_cn.md",
    "content": "# [Cline](https://github.com/cline/cline)\n\nCline 是一款能够使用您的 CLI 和编辑器的 AI 助手。\n\n## 安装\n\n![image](./assets/cline-00.png)\n\n## Cline 的主要特点\n\n1. **基于 Claude 4.0 Opus 的智能编码**：Cline 利用先进的 AI 技术，逐步处理复杂的软件开发任务，超越简单的代码补全或技术支持。\n\n2. **文件与项目管理**：Cline 可以创建、编辑和浏览大型项目中的文件，实现无缝的代码库导航和修改。\n\n3. **终端集成**：在用户授权的情况下，Cline 可以执行终端命令并监控其输出，从而动态响应开发服务器错误等问题。\n\n4. **浏览器自动化**：对于 Web 开发，Cline 可以在无头浏览器中启动网站，与页面交互（点击、输入、滚动），并捕获截图和控制台日志，以调试运行时错误和视觉问题。\n\n5. **人机交互安全保障**：每次文件更改和终端命令都需要通过 GUI 获得用户批准，确保在探索智能 AI 功能时提供一个安全可控的环境。\n\n6. **上下文感知辅助**：Cline 分析文件结构、源代码 AST 并运行正则表达式搜索，以理解现有项目，确保在不超出上下文窗口的情况下提供高效且相关的帮助。\n\n7. **主动错误处理**：Cline 监控 linter/编译器错误，并在文件编辑过程中主动修复诸如缺少导入和语法错误等问题。\n\n8. **模型上下文协议 (MCP)**：Cline 可以通过 MCP 创建新工具来扩展其功能，从而持续适应用户需求。\n\n9. **轻松完成任务**：任务完成后，Cline 会以简单的终端命令（例如 `open -a \"Google Chrome\" index.html`）呈现结果，用户只需点击一下即可执行。\n\n## 用户界面\n\n![image](./assets/cline-01.png)\n\n## 与 DeepSeek API 集成\n\n![image](./assets/cline-02.png)\n\n## 最佳实践\n\n1. **关闭 Cline 的 Auto Approve 功能**：建议在使用 DeepSeek 时，关闭 Cline 的 Auto Approve 功能，以降低资源消耗，降低多请求因并发带来的卡顿风险。\n\n2. **使用 Cline 改版**：例如 Roo-Cline 或 ALine。这些改版携带的上下文相对短，处理请求时表现更为流畅，且缓存命中率更高，可以帮助节省 API 调用成本。\n\n3. **慎用 DeepSeek 处理大型工程**：对于大型代码工程，不建议使用 DeepSeek + Cline。大型工程通常会携带大量代码上下文，会导致 API 请求处理速度明显变慢。\n\n4. **更换其他 LLM 提供商**：建议您在使用 Cline 时，更换其他 LLM 提供商，以获得更流畅的体验。\n\n## Roo Cline\n\n![image](./assets/roocline-00.png)\n"
  },
  {
    "path": "docs/codecompanion.nvim/README.md",
    "content": "# [codecompanion.nvim](https://github.com/olimorris/codecompanion.nvim)\n\n> AI-powered coding, seamlessly in Neovim\n\n**codecompanion.nvim** is a productivity tool which streamlines how you develop with LLMs, in Neovim.\n\n## Features\n\n- :speech_balloon: [Copilot Chat](https://github.com/features/copilot) meets [Zed AI](https://zed.dev/blog/zed-ai), in Neovim\n- :electric_plug: Support for Anthropic, Copilot, Gemini, Ollama, OpenAI, Azure OpenAI, HuggingFace and xAI LLMs (or bring your own!)\n- :rocket: Inline transformations, code creation and refactoring\n- :robot: Variables, Slash Commands, Agents/Tools and Workflows to improve LLM output\n- :sparkles: Built in prompt library for common tasks like advice on LSP errors and code explanations\n- :building_construction: Create your own custom prompts, Variables and Slash Commands\n- :books: Have multiple chats open at the same time\n- :muscle: Async execution for fast performance\n\n## Installation\n\nFirst, Navigate to the nvim configuration folder (default on Linux is `~/.config/nvim`)\n\n### Install via `lazy.nvim`\n\nThen to the `lua/plugins` folder. Create a file named `init.lua` and add the following content:\n\n```lua\nreturn {\n  \"olimorris/codecompanion.nvim\",\n  dependencies = {\n    \"nvim-lua/plenary.nvim\",\n    \"nvim-treesitter/nvim-treesitter\",\n  },\n  config = function()\n    require(\"codecompanion\").setup({\n      adapters = {\n        deepseek = function()\n          return require(\"codecompanion.adapters\").extend(\"deepseek\", {\n            env = {\n              api_key = \"YOUR_API_KEY\",\n            },\n          })\n        end,\n      },\n      strategies = {\n        chat = { adapter = \"deepseek\", },\n        inline = { adapter = \"deepseek\" },\n        agent = { adapter = \"deepseek\" },\n      },\n    })\n  end\n}\n```\nRestart nvim, and `lazy.nvim` should automatically download and install the codecompanion.nvim plugin and its dependencies based on the above file.\n\n### Install via `mini.deps`\n\nAdd the following content to your `init.lua`:\n\n```lua\nlocal add, later = MiniDeps.add, MiniDeps.later\n\nlater(function()\n  add({\n    source = \"olimorris/codecompanion.nvim\",\n    depends = {\n      \"nvim-lua/plenary.nvim\",\n      \"nvim-treesitter/nvim-treesitter\",\n    },\n  })\n  require(\"codecompanion\").setup({\n    adapters = {\n      deepseek = function()\n        return require(\"codecompanion.adapters\").extend(\"deepseek\", {\n          env = {\n              api_key = \"YOUR_API_KEY\",\n          },\n        })\n      end,\n    },\n    strategies = {\n      chat = { adapter = \"deepseek\", },\n      inline = { adapter = \"deepseek\" },\n      agent = { adapter = \"deepseek\" },\n    },\n  })\nend)\n```\nRestart nvim, and `mini.deps` should also automatically download and install the codecompanion.nvim plugin.\n\n\n### Other Installation Methods\nhttps://codecompanion.olimorris.dev/installation.html\n\n## Usage\nhttps://codecompanion.olimorris.dev/usage/introduction.html\n"
  },
  {
    "path": "docs/codecompanion.nvim/README_cn.md",
    "content": "# [codecompanion.nvim](https://github.com/olimorris/codecompanion.nvim)\n\n> AI 驱动的编码，在 Neovim 中无缝集成\n\n**codecompanion.nvim** 是一个提高生产力的工具，它简化了在 Neovim 中使用大型语言模型（LLM）进行开发的方式。\n\n## 特性\n\n- :speech_balloon: 在 Neovim 中，[Copilot Chat](https://github.com/features/copilot) 与 [Zed AI](https://zed.dev/blog/zed-ai) 的结合\n- :electric_plug: 支持 Anthropic、Copilot、Gemini、Ollama、OpenAI、Azure OpenAI、HuggingFace 和 xAI LLM（或自定义 LLM！）\n- :rocket: 内联变换、代码生成与重构\n- :robot: 通过变量、斜杠命令、代理/工具和工作流改善 LLM 输出\n- :sparkles: 内置常用任务的提示词，例如 LSP 错误的建议和代码解释\n- :building_construction: 创建自定义提示、变量和斜杠命令\n- :books: 同时打开多个对话\n- :muscle: 异步执行，提供快速的性能\n\n## 安装\n\n首先，导航到 Neovim 配置文件夹（默认情况下，Linux 上的路径是 `~/.config/nvim`）。\n\n### 通过 `lazy.nvim` 安装\n\n然后进入 `lua/plugins` 文件夹。创建一个名为 `init.lua` 的文件，并添加以下内容：\n\n```lua\nreturn {\n  \"olimorris/codecompanion.nvim\",\n  dependencies = {\n    \"nvim-lua/plenary.nvim\",\n    \"nvim-treesitter/nvim-treesitter\",\n  },\n  config = function()\n    require(\"codecompanion\").setup({\n      adapters = {\n        deepseek = function()\n          return require(\"codecompanion.adapters\").extend(\"deepseek\", {\n            env = {\n              api_key = \"YOUR_API_KEY\",\n            },\n          })\n        end,\n      },\n      strategies = {\n        chat = { adapter = \"deepseek\", },\n        inline = { adapter = \"deepseek\" },\n        agent = { adapter = \"deepseek\" },\n      },\n    })\n  end\n}\n```\n重新启动 Neovim，`lazy.nvim` 应该会自动下载并安装 `codecompanion.nvim` 插件及其依赖项。\n\n### 通过 `mini.deps` 安装\n\n将以下内容添加到你的 `init.lua` 中\n\n```lua\nlocal add, later = MiniDeps.add, MiniDeps.later\n\nlater(function()\n  add({\n    source = \"olimorris/codecompanion.nvim\",\n    depends = {\n      \"nvim-lua/plenary.nvim\",\n      \"nvim-treesitter/nvim-treesitter\",\n    },\n  })\n  require(\"codecompanion\").setup({\n    adapters = {\n      deepseek = function()\n        return require(\"codecompanion.adapters\").extend(\"deepseek\", {\n          env = {\n              api_key = \"YOUR_API_KEY\",\n          },\n        })\n      end,\n    },\n    strategies = {\n      chat = { adapter = \"deepseek\", },\n      inline = { adapter = \"deepseek\" },\n      agent = { adapter = \"deepseek\" },\n    },\n  })\nend)\n```\n\n重新启动 Neovim，`mini.deps` 应该会自动下载并安装 `codecompanion.nvim` 插件。\n\n\n### 其他安装方法\nhttps://codecompanion.olimorris.dev/installation.html\n\n## 使用\nhttps://codecompanion.olimorris.dev/usage/introduction.html\n"
  },
  {
    "path": "docs/codegate/README.md",
    "content": "# CodeGate: secure AI code generation\n\nCodeGate is a **local gateway** that makes AI agents and coding assistants safer. It\nensures AI-generated recommendations adhere to best practices while safeguarding\nyour code's integrity and protecting your privacy. With CodeGate, you can\nconfidently leverage AI in your development workflow without sacrificing\nsecurity or productivity.\n\n<picture>\n  <source media=\"(prefers-color-scheme: dark)\" srcset=\"https://raw.githubusercontent.com/stacklok/codegate/main/static/diagram-dark.png\">\n  <img alt=\"CodeGate dashboard\" src=\"https://github.com/stacklok/codegate/raw/main/static/diagram-light.png\" width=\"1100px\" style=\"max-width: 100%;\">\n</picture>\n\n---\n## ✨ Why choose CodeGate?\n\nAI coding assistants are powerful, but they can inadvertently introduce risks.\nCodeGate protects your development process by:\n\n- 🔒 Preventing accidental exposure of secrets and sensitive data\n- 🛡️ Ensuring AI suggestions follow secure coding practices\n- ⚠️ Blocking recommendations of known malicious or deprecated libraries\n- 🔍 Providing real-time security analysis of AI suggestions\n\n---\n## 🚀 Quickstart with 🐋 Deepseek!\n\n### Prerequisites\n\nCodeGate is distributed as a Docker container. You need a container runtime like\nDocker Desktop or Docker Engine. Podman and Podman Desktop are also supported.\nCodeGate works on Windows, macOS, and Linux operating systems with x86_64 and\narm64 (ARM and Apple Silicon) CPU architectures.\n\nThese instructions assume the `docker` CLI is available. If you use Podman,\nreplace `docker` with `podman` in all commands.\n\n### Installation\n\nTo start CodeGate, run this simple command (making sure to pass in the\ndeepseek.com URL as the `CODEGATE_PROVIDER_OPENAI_URL` environment variable):\n\n```bash\ndocker run --name codegate -d -p 8989:8989 -p 9090:9090 -p 8990:8990 \\\n  -e CODEGATE_PROVIDER_OPENAI_URL=https://api.deepseek.com \\\n  --mount type=volume,src=codegate_volume,dst=/app/codegate_volume \\\n  --restart unless-stopped ghcr.io/stacklok/codegate:latest\n```\n\nThat’s it! CodeGate is now running locally. \n\n### Using CodeGate and 🐋 Deepseek within Continue\n\nTo use Continue with CodeGate, open the Continue settings and add\nthe following configuration:\n\n```json\n{\n    \"title\": \"Deepseek-r1\",\n    \"provider\": \"openai\",\n    \"model\": \"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B\",\n    \"apiKey\": \"YOUR_DEEPSEEK_API_KEY\",\n    \"apiBase\": \"http://localhost:8989/openai\",\n}\n```\n\nJust use Continue as normal, and you know longer have to worry about security\nor privacy concerns!\n\n![continue-image](https://github.com/deepseek/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/continue-screen.png)\n\n\n### Using CodeGate and 🐋 Deepseek with Cline\n\nTo use Cline with CodeGate, open the Cline settings and add\nthe following configuration:\n\n![cline-settings](https://github.com/deepseek/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/cline-settings.png)\n\nJust use Cline as normal, and you know longer have to worry about security\nor privacy concerns!\n\n![cline-image](https://github.com/deepseek/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/cline-screen.png)\n\n---\n## 🖥️ Dashboard\n\nCodeGate includes a web dashboard that provides:\n\n- A view of **security risks** detected by CodeGate\n- A **history of interactions** between your AI coding assistant and your LLM\n\n<picture>\n  <source media=\"(prefers-color-scheme: dark)\" srcset=\"./static/dashboard-dark.webp\">\n  <img alt=\"CodeGate dashboard\" src=\"./static/dashboard-light.webp\" width=\"1200px\" style=\"max-width: 100%;\">\n</picture>\n\n### Accessing the dashboard\n\nOpen [http://localhost:9090](http://localhost:9090) in your web browser to\naccess the dashboard.\n\nTo learn more, visit the\n[CodeGate Dashboard documentation](https://docs.codegate.ai/how-to/dashboard).\n\n---\n## 🔐 Features\n\n### Secrets encryption\n\nCodeGate helps you protect sensitive information from being accidentally exposed\nto AI models and third-party AI provider systems by redacting detected secrets\nfrom your prompts using encryption.\n[Learn more](https://docs.codegate.ai/features/secrets-encryption)\n\n### Dependency risk awareness\n\nLLMs’ knowledge cutoff date is often months or even years in the past. They\nmight suggest outdated, vulnerable, or non-existent packages (hallucinations),\nexposing you and your users to security risks.\n\nCodeGate scans direct, transitive, and development dependencies in your package\ndefinition files, installation scripts, and source code imports that you supply\nas context to an LLM.\n[Learn more](https://docs.codegate.ai/features/dependency-risk)\n\n### Security reviews\n\nCodeGate performs security-centric code reviews, identifying insecure patterns\nor potential vulnerabilities to help you adopt more secure coding practices.\n[Learn more](https://docs.codegate.ai/features/security-reviews)\n\n---\n## 🛡️ Privacy first\n\nUnlike other tools, with CodeGate **your code never leaves your machine**.\nCodeGate is built with privacy at its core:\n\n- 🏠 **Everything stays local**\n- 🚫 **No external data collection**\n- 🔐 **No calling home or telemetry**\n- 💪 **Complete control over your data**\n\n---\n## 🛠️ Development\n\nAre you a developer looking to contribute? Dive into our technical resources:\n\n- [Development guide](https://github.com/stacklok/codegate/blob/main/docs/development.md)\n- [CLI commands and flags](https://github.com/stacklok/codegate/blob/main/docs/cli.md)\n- [Configuration system](https://github.com/stacklok/codegate/blob/main/docs/configuration.md)\n- [Logging system](https://github.com/stacklok/codegate/blob/main/docs/logging.md)\n\n---\n## 📜 License\n\nCodeGate is licensed under the terms specified in the\n[LICENSE file](https://github.com/stacklok/codegate/blob/main/LICENSE).\n"
  },
  {
    "path": "docs/codegate/README_cn.md",
    "content": "# CodeGate:安全的 AI 代码生成\n\nCodeGate 是一个**本地代理**,可以让 AI 代理和编码助手更加安全。它确保 AI 生成的建议遵循最佳实践,同时保护您的代码完整性和隐私。使用 CodeGate,您可以在开发工作流程中自信地利用 AI,而不会牺牲安全性或生产力。\n\n<picture>\n  <source media=\"(prefers-color-scheme: dark)\" srcset=\"https://raw.githubusercontent.com/stacklok/codegate/main/static/diagram-dark.png\">\n  <img alt=\"CodeGate dashboard\" src=\"https://github.com/stacklok/codegate/raw/main/static/diagram-light.png\" width=\"1100px\" style=\"max-width: 100%;\">\n</picture>\n\n---\n## ✨ 为什么选择 CodeGate?\n\nAI 编码助手功能强大,但可能会无意中带来风险。CodeGate 通过以下方式保护您的开发过程:\n\n- 🔒 防止意外泄露机密和敏感数据\n- 🛡️ 确保 AI 建议遵循安全编码实践\n- ⚠️ 阻止推荐已知的恶意或已弃用的库\n- 🔍 提供 AI 建议的实时安全分析\n\n---\n## 🚀 使用 🐋 Deepseek 快速开始!\n\n### 前提条件\n\nCodeGate 以 Docker 容器的形式分发。您需要一个容器运行时,如 Docker Desktop 或 Docker Engine。同时也支持 Podman 和 Podman Desktop。CodeGate 可在 Windows、macOS 和 Linux 操作系统上运行,支持 x86_64 和 arm64(ARM 和 Apple Silicon)CPU 架构。\n\n以下说明基于 `docker` CLI 可用的前提。如果您使用 Podman,请在所有命令中将 `docker` 替换为 `podman`。\n\n### 安装\n\n要启动 CodeGate,运行这个简单的命令(确保将 deepseek.com URL 作为 `CODEGATE_PROVIDER_OPENAI_URL` 环境变量传入):\n\n```bash\ndocker run --name codegate -d -p 8989:8989 -p 9090:9090 -p 8990:8990 \\\n  -e CODEGATE_PROVIDER_OPENAI_URL=https://api.deepseek.com \\\n  --mount type=volume,src=codegate_volume,dst=/app/codegate_volume \\\n  --restart unless-stopped ghcr.io/stacklok/codegate:latest\n```\n\n就是这样!CodeGate 现在在本地运行了。\n\n### 在 Continue 中使用 CodeGate 和 🐋 Deepseek\n\n要在 Continue 中使用 CodeGate,打开 Continue 设置并添加以下配置:\n\n```json\n{\n    \"title\": \"Deepseek-r1\",\n    \"provider\": \"openai\",\n    \"model\": \"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B\",\n    \"apiKey\": \"YOUR_DEEPSEEK_API_KEY\",\n    \"apiBase\": \"http://localhost:8989/openai\",\n}\n```\n\n像往常一样使用 Continue,您不再需要担心安全或隐私问题!\n\n![continue-image](](https://github.com/deepseek/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/continue-screen.png))\n\n### 在 Cline 中使用 CodeGate 和 🐋 Deepseek\n\n要在 Cline 中使用 CodeGate,打开 Cline 设置并添加以下配置:\n\n![cline-settings](https://github.com/deepseek/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/cline-settings.png)\n\n像往常一样使用 Cline,您不再需要担心安全或隐私问题!\n\n![cline-image](https://github.com/deepseek/awesome-deepseek-integration/blob/codegate/docs/codegate/assets/cline-screen.png)\n\n---\n## 🖥️ 仪表板\n\nCodeGate 包含一个 Web 仪表板,提供:\n\n- CodeGate 检测到的**安全风险**视图\n- AI 编码助手与 LLM 之间的**交互历史**\n\n<picture>\n  <source media=\"(prefers-color-scheme: dark)\" srcset=\"./static/dashboard-dark.webp\">\n  <img alt=\"CodeGate dashboard\" src=\"./static/dashboard-light.webp\" width=\"1200px\" style=\"max-width: 100%;\">\n</picture>\n\n### 访问仪表板\n\n在您的网络浏览器中打开 [http://localhost:9090](http://localhost:9090) 以访问仪表板。\n\n要了解更多信息,请访问 [CodeGate 仪表板文档](https://docs.codegate.ai/how-to/dashboard)。\n\n---\n## 🔐 功能\n\n### 机密加密\n\nCodeGate 通过使用加密对检测到的机密进行编辑,帮助您防止敏感信息意外暴露给 AI 模型和第三方 AI 提供商系统。\n[了解更多](https://docs.codegate.ai/features/secrets-encryption)\n\n### 依赖风险意识\n\nLLM 的知识截止日期通常是几个月甚至几年前。它们可能会建议过时的、易受攻击的或不存在的包(幻觉),使您和您的用户面临安全风险。\n\nCodeGate 扫描您作为上下文提供给 LLM 的包定义文件、安装脚本和源代码导入中的直接依赖、传递依赖和开发依赖。\n[了解更多](https://docs.codegate.ai/features/dependency-risk)\n\n### 安全审查\n\nCodeGate 执行以安全为中心的代码审查,识别不安全的模式或潜在的漏洞,帮助您采用更安全的编码实践。\n[了解更多](https://docs.codegate.ai/features/security-reviews)\n\n---\n## 🛡️ 隐私优先\n\n与其他工具不同,使用 CodeGate **您的代码永远不会离开您的机器**。CodeGate 以隐私为核心构建:\n\n- 🏠 **所有数据均本地存储**\n- 🚫 **没有外部数据收集**\n- 🔐 **没有回传或遥测**\n- 💪 **完全控制您的数据**\n\n---\n## 🛠️ 开发\n\n您是想要贡献的开发者吗?深入了解我们的技术资源:\n\n- [开发指南](https://github.com/stacklok/codegate/blob/main/docs/development.md)\n- [CLI 命令和标志](https://github.com/stacklok/codegate/blob/main/docs/cli.md)\n- [配置系统](https://github.com/stacklok/codegate/blob/main/docs/configuration.md)\n- [日志系统](https://github.com/stacklok/codegate/blob/main/docs/logging.md)\n\n---\n## 📜 许可证\n\nCodeGate 根据 [LICENSE 文件](https://github.com/stacklok/codegate/blob/main/LICENSE) 中指定的条款获得许可。"
  },
  {
    "path": "docs/continue/README.md",
    "content": "<img src=\"https://github.com/continuedev/continue/blob/main/docs/static/img/logo.png?raw=true\" width=\"64\" height=\"auto\" />\n\n# [Continue](https://continue.dev/)\n\nAn open-source autopilot in your IDE.\nContinue will generate, refactor, and explain entire sections of code with LLMs.\n\n## UI\n\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/094e9dc8-03d0-493d-95fb-6129a42a35bd)\n\n## Integrate with DeepSeek API\n\nModify the `config.yaml` file to add the `DeepSeek` model configuration, replacing `YOUR_DEEPSEEK_API_KEY` with your DeepSeek API Key.\n\n* `~/.continue/config.yaml` (MacOS/Linux)\n* `%USERPROFILE%\\.continue\\config.yaml` (Windows)\n\n```yaml\nname: Local Assistant\nversion: 1.0.0\nschema: v1\nmodels:\n  - name: DeepSeek\n    provider: deepseek\n    model: deepseek-chat\n    apiKey: YOUR_DEEPSEEK_API_KEY\n    apiBase: https://api.deepseek.com/beta\n    roles:\n      - chat\n      - edit\n      - apply\n      - summarize\n      - autocomplete\n    contextLength: 128000\n    defaultCompletionOptions:\n      temperature: 0.0\n      maxTokens: 256\ncontext:\n  - provider: code\n  - provider: docs\n  - provider: diff\n  - provider: terminal\n  - provider: problems\n  - provider: folder\n  - provider: codebase\n```\n"
  },
  {
    "path": "docs/continue/README_cn.md",
    "content": "<img src=\"https://github.com/continuedev/continue/blob/main/docs/static/img/logo.png?raw=true\" width=\"64\" height=\"auto\" />\r\n\r\n# [Continue](https://continue.dev/)\r\n\r\n开源 IDE 插件，使用 LLM 做你的编程助手.\r\n\r\n## UI\r\n\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/094e9dc8-03d0-493d-95fb-6129a42a35bd)\r\n\r\n## 接入 DeepSeek API\r\n\r\n修改 `config.yaml` 文件，添加 `DeepSeek` 模型配置，将 `YOUR_DEEPSEEK_API_KEY` 替换为你的 DeepSeek API Key。\r\n\r\n* `~/.continue/config.yaml` (MacOS/Linux)\r\n* `%USERPROFILE%\\.continue\\config.yaml` (Windows)\r\n\r\n```yaml\r\nname: Local Assistant\r\nversion: 1.0.0\r\nschema: v1\r\nmodels:\r\n  - name: DeepSeek\r\n    provider: deepseek\r\n    model: deepseek-chat\r\n    apiKey: YOUR_DEEPSEEK_API_KEY\r\n    apiBase: https://api.deepseek.com/beta\r\n    roles:\r\n      - chat\r\n      - edit\r\n      - apply\r\n      - summarize\r\n      - autocomplete\r\n    contextLength: 128000\r\n    defaultCompletionOptions:\r\n      temperature: 0.0\r\n      maxTokens: 256\r\ncontext:\r\n  - provider: code\r\n  - provider: docs\r\n  - provider: diff\r\n  - provider: terminal\r\n  - provider: problems\r\n  - provider: folder\r\n  - provider: codebase\r\n```\r\n"
  },
  {
    "path": "docs/curator/README.md",
    "content": "\n![image](https://raw.githubusercontent.com/bespokelabsai/curator/main/docs/Bespoke-Labs-Logomark-Red-crop.png)\n\n\n# [Curator](https://github.com/bespokelabsai/curator)\n\n\nCurator is an open-source tool to curate large scale datasets for post-training LLMs. \n\nCurator was used to curate [Bespoke-Stratos-17k](https://huggingface.co/datasets/bespokelabs/Bespoke-Stratos-17k), a reasoning dataset to train a fully open reasoning model [Bespoke-Stratos](https://www.bespokelabs.ai/blog/bespoke-stratos-the-unreasonable-effectiveness-of-reasoning-distillation).\n\n\n### Curator supports:\n\n- Calling Deepseek API for scalable synthetic data curation\n- Easy structured data extraction\n- Caching and automatic recovery\n- Dataset visualization\n- Saving $$$ using batch mode\n\n### Call Deepseek API with Curator easily:\n\n![image](https://pbs.twimg.com/media/GiLHb-xasAAbs4m?format=jpg&name=4096x4096)\n\n# Get Started here\n\n- [Colab Example](https://colab.research.google.com/drive/1Z78ciwHIl_ytACzcrslNrZP2iwK05eIF?usp=sharing)\n- [Github Repo](https://github.com/bespokelabsai/curator)\n- [Documentation](https://docs.bespokelabs.ai/)\n- [Discord](https://discord.com/invite/KqpXvpzVBS)\n"
  },
  {
    "path": "docs/curator/README_cn.md",
    "content": "![image](https://raw.githubusercontent.com/bespokelabsai/curator/main/docs/Bespoke-Labs-Logomark-Red-crop.png)\n\n\n# [Curator](https://github.com/bespokelabsai/curator)\n\n\nCurator 是一个用于后训练大型语言模型 (LLMs) 和结构化数据提取的制作与管理可扩展的数据集的开源工具。\n\nCurator 被用来制作 [Bespoke-Stratos-17k](https://huggingface.co/datasets/bespokelabs/Bespoke-Stratos-17k)，这是一个用于训练完全开源的推理模型 [Bespoke-Stratos](https://www.bespokelabs.ai/blog/bespoke-stratos-the-unreasonable-effectiveness-of-reasoning-distillation) 的推理数据集。\n\n\n### Curator 支持：\n\n- 调用 Deepseek API 进行可扩展的合成数据管理\n- 简便的结构化数据提取\n- 缓存和自动恢复\n- 数据集可视化\n- 使用批处理模式节省费用\n\n### 轻松使用 Curator 调用 Deepseek API：\n\n![image](https://pbs.twimg.com/media/GiLHb-xasAAbs4m?format=jpg&name=4096x4096)\n\n# 从这里开始\n\n- [Colab 示例](https://colab.research.google.com/drive/1Z78ciwHIl_ytACzcrslNrZP2iwK05eIF?usp=sharing)\n- [Github 仓库](https://github.com/bespokelabsai/curator)\n- [文档](https://docs.bespokelabs.ai/)\n- [Discord](https://discord.com/invite/KqpXvpzVBS)"
  },
  {
    "path": "docs/cursor/README.md",
    "content": "<img src=\"https://mintlify.s3-us-west-1.amazonaws.com/cursor/_generated/favicon/apple-touch-icon.png?v=3\" width=\"64\" height=\"auto\" />\n\n# [Cursor](https://www.cursor.com/)\n\n  Cursor is the AI Code Editor\n\n## Just follow these steps:\n\n1. in Cursor Settings disable all models\n2. add `deepseek-coder` as new model\n3. in Open AI API Key add https://api.deepseek.com/beta as URL - add your API key.\n\n# UI\n\n![image](assets/cursor-setting.png)"
  },
  {
    "path": "docs/cursor/README_cn.md",
    "content": "<img src=\"https://mintlify.s3-us-west-1.amazonaws.com/cursor/_generated/favicon/apple-touch-icon.png?v=3\" width=\"64\" height=\"auto\" />\n\n# [Cursor](https://www.cursor.com/)\n\n  Cursor 是一个 AI 代码编辑器\n\n## 只需按照以下步骤操作：\n\n1. 在 Cursor 设置中禁用所有模型\n2. 添加 `deepseek-coder` 作为新模型\n3. 在 Open AI API Key 中添加 https://api.deepseek.com/beta 作为 URL - 添加您的 API 密钥。\n\n# UI\n\n![image](assets/cursor-setting.png)"
  },
  {
    "path": "docs/dbgpt/README.md",
    "content": "# [DB-GPT](https://github.com/eosphoros-ai/DB-GPT)\n\n🤖 DB-GPT is an open source AI native data app development framework with AWEL(Agentic Workflow Expression Language) and agents.\n\nThe purpose is to build infrastructure in the field of large models, through the development of multiple technical capabilities such as multi-model management (SMMF), Text2SQL effect optimization, RAG framework and optimization, Multi-Agents framework collaboration, AWEL (agent workflow orchestration), etc. Which makes large model applications with data simpler and more convenient.\n## UI\n\n![image](assets/dbgpt_ui_en.jpg)\n\n\n## Data Analysis with Deepseek API\n\n![image](assets/dbgpt_chat_data_en.jpg)\n\n\n## Datasources\n\n![image](assets/dbgpt_datasource_en.jpg)\n"
  },
  {
    "path": "docs/dbgpt/README_cn.md",
    "content": "# [DB-GPT](https://github.com/eosphoros-ai/DB-GPT)\n\nDB-GPT是一个开源的AI原生数据应用开发框架(AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents)。\n\n目的是构建大模型领域的基础设施，通过开发多模型管理(SMMF)、Text2SQL效果优化、RAG框架以及优化、Multi-Agents框架协作、AWEL(智能体工作流编排)等多种技术能力，让围绕数据库构建大模型应用更简单，更方便。\n\n\n## UI\n\n![image](assets/dbgpt_ui.jpg)\n\n\n## 数据分析 with Deepseek API\n\n![image](assets/dbgpt_chat_data.jpg)\n\n## Datasources\n\n![image](assets/dbgpt_datasource.jpg)"
  },
  {
    "path": "docs/deepshare/README.md",
    "content": "<img src=\"./assets/logo_200.png\" width=\"100\" height=\"auto\" /> \n\n\n# [Tiny AI Bee - Deep Sharing](https://www.deepshare.top/)\n\n  [Tiny AI Bee - Deep Sharing](https://www.deepshare.top/intro) is a free login-free one-click grease monkey plugin for sharing AI chats,\n\n  Specialized in solving the problem of sending thousands of words of AI Q&A to friends, causing their phones to be brushed, or long screenshots to be compressed and opened blurred, not easy to read.\n\n  Satisfy users' need to share their crystallized wisdom with AI to others\n\n  You can set the access code/expiry date/whether to make it public or not, and synchronize the sharing history of mobile phone/PC computer.\n \n  Tiny AI Bee is also a convenient AI wisdom sharing community that supports users to like/favorite/follow/reward/withdraw cash.\n\n[xhai Browser](https://www.dahai123.top/)  default installation, while supporting via browser/X browser, etc., PC computer side support Grease Monkey plug-in browser use.\n\n\n## UI\n\n<img src=\"./assets/ds2_1t.png\" width=\"auto\" height=\"auto\" />"
  },
  {
    "path": "docs/deepshare/README_cn.md",
    "content": "<img src=\"./assets/logo_200.png\" width=\"100\" height=\"auto\" /> \n\n\n# [小智蜂·深度分享](https://www.deepshare.top/)\n\n  [小智蜂·深度分享 ](https://www.deepshare.top/intro) 是免费免登录一键分享AI聊天的油猴插件\n\n  专门解决数千字AI问答发给朋友,导致其手机被刷屏,或长截图被压缩,打开模糊不清,不方便阅读的问题.\n\n  满足用户将自己与AI智慧的结晶分享给他人的需求\n\n  可设置分享的访问码/有效期/是否公开,手机/PC电脑多端同步分享历史.\n\n  小智蜂也是便捷的AI智慧分享社区,支持用户点赞/收藏/关注/打赏/提现等.\n\n[小海浏览器](https://www.dahai123.top/) 默认安装,同时支持via浏览器/X浏览器等,PC电脑端支持油猴插件的浏览器使用.\n\n\n## UI\n\n<img src=\"./assets/ds2_1t.png\" width=\"auto\" height=\"auto\" />\n\n\n\n"
  },
  {
    "path": "docs/deepspace/README.md",
    "content": "# DeepSpace\n\nDeepSpace is a tool for debugging the DeepSeek API, developed by the community and inspired by [MoonPalace](https://github.com/MoonshotAI/moonpalace?tab=readme-ov-file).\n\n[简体中文](README_cn.md)\n\n## Features\n\n- **Cross-platform Support:**\n  - [x] Mac\n  - [x] Windows\n  - [x] Linux\n- **User-friendly**: Simply replace `base_url` with `http://localhost:9988` after starting the service to begin debugging.\n- **Complete Request Capture**, including error details in case of network failures.\n- **Fast Retrieval**: Quickly search and view request information using `request_id` or `chatcmpl_id`.\n- **One-click Export of Structured BadCase Reports**, aiding DeepSeek in enhancing model capabilities.\n\n**It is recommended to use DeepSpace as your API “provider” during code development and debugging stages. This allows you to quickly identify and resolve issues related to API calls and code implementation. For any unexpected outputs from the DeepSeek large model, you can also export request details via DeepSpace and submit them to DeepSeek to help improve the model.**\n\n## Installation\n\n### Install using the `go` command\n\nIf you have the `go` toolchain installed, you can install DeepSpace by executing the following command:\n\n```shell\n$ go install github.com/2404589803/deepspace@latest\n```\n\nThis command will install the compiled binary in your `$GOPATH/bin/` directory. To verify the installation, run the following command:\n\n```shell\n$ deepspace\nDeepSpace is a command-line tool for debugging the DeepSeek AI HTTP API\n\nUsage:\n  deepspace [command]\n\nAvailable Commands:\n  cleanup     Cleanup DeepSeek AI requests\n  completion  Generate the autocompletion script for the specified shell\n  export      Export a DeepSeek AI request\n  help        Help about any command\n  inspect     Inspect the specific content of a DeepSeek AI request\n  list        Query DeepSeek AI requests based on conditions\n  start       Start the DeepSpace proxy server\n\nFlags:\n  -h, --help      help for deepspace\n  -v, --version   version for deepspace\n\nUse \"deepspace [command] --help\" for more information about a command.\n```\n\n*If the `deepspace` binary is not found, try adding the `$GOPATH/bin/` directory to your `$PATH` environment variable.*\n\n### Download Executable from the Releases Page\n\nAlternatively, you can download the precompiled binary from the [Releases](https://github.com/2404589803/deepspace/releases) page:\n\n- deepspace-linux\n- deepspace-macos-amd64 => for Intel-based Macs\n- deepspace-macos-arm64 => for Apple Silicon-based Macs\n- deepspace-windows.exe\n\n## Usage\n\n### Starting the Service\n\nUse the following command to start the DeepSpace proxy server:\n\n```shell\n$ deepspace start --port <PORT>\n```\n\nDeepSpace will start a local HTTP server. The `--port` parameter specifies the local port that DeepSpace listens to, with a default value of `9988`. Upon successful startup, the following message will be displayed:\n\n```shell\n[DeepSpace] 2024/08/26 12:12:26 DeepSpace Starts => change base_url to \"http://127.0.0.1:9988/v1\"\n```\n\nYou can submit the exported files to the following email:\n\n[api-service@deepseek.com](mailto:api-service@deepseek.com)\n"
  },
  {
    "path": "docs/deepspace/README_cn.md",
    "content": "# DeepSpace\n\nDeepSpace（深度空间）是一款用于调试 DeepSeek API 的工具，由社区制作，灵感来源于 [MoonPalace](https://github.com/MoonshotAI/moonpalace?tab=readme-ov-file)。\n\n[Read this in English](README.md)\n\n## 特性\n\n- **全平台支持：**\n  - [x] Mac\n  - [x] Windows\n  - [x] Linux\n- **简单易用**：启动后只需将 `base_url` 替换为 `http://localhost:9988` 即可开始调试。\n- **捕获完整请求**，包括网络错误时的“事故现场”。\n- **快速检索**：通过 `request_id`、`chatcmpl_id` 快速检索、查看请求信息。\n- **一键导出 BadCase 结构化上报数据**，帮助 DeepSeek 完善模型能力。\n\n**推荐在代码编写和调试阶段使用 DeepSpace 作为你的 API “供应商”，以便能快速发现和定位关于 API 调用和代码编写过程中的各种问题。对于 DeepSeek 大模型各种不符合预期的输出，你也可以通过 DeepSpace 导出请求详情并提交给 DeepSeek 以改进 DeepSeek 的大模型。**\n\n## 安装方式\n\n### 使用 `go` 命令安装\n\n如果你已经安装了 `go` 工具链，可以执行以下命令来安装：\n\n```shell\n$ go install github.com/2404589803/deepspace@latest\n```\n\n上述命令会在你的 `$GOPATH/bin/` 目录中安装编译后的二进制文件。运行 `deepspace` 命令来检查是否成功安装：\n\n```shell\n$ deepspace\nDeepSpace is a command-line tool for debugging the DeepSeek AI HTTP API\n\nUsage:\n  deepspace [command]\n\nAvailable Commands:\n  cleanup     Cleanup DeepSeek AI requests\n  completion  Generate the autocompletion script for the specified shell\n  export      Export a DeepSeek AI request\n  help        Help about any command\n  inspect     Inspect the specific content of a DeepSeek AI request\n  list        Query DeepSeek AI requests based on conditions\n  start       Start the DeepSpace proxy server\n\nFlags:\n  -h, --help      help for deepspace\n  -v, --version   version for deepspace\n\nUse \"deepspace [command] --help\" for more information about a command.\n```\n\n*如果你仍然无法检索到 `deepspace` 二进制文件，请尝试将 `$GOPATH/bin/` 目录添加到你的 `$PATH` 环境变量中。*\n\n### 从 Releases 页面下载二进制（可执行）文件\n\n你也可以从 [Releases](https://github.com/2404589803/deepspace/releases) 页面下载编译好的二进制文件：\n\n- deepspace-linux\n- deepspace-macos-amd64 => 对应 Intel 版本的 Mac\n- deepspace-macos-arm64 => 对应 Apple Silicon 版本的 Mac\n- deepspace-windows.exe\n\n## 使用方式\n\n### 启动服务\n\n使用以下命令启动 DeepSpace 代理服务器：\n\n```shell\n$ deepspace start --port <PORT>\n```\n\nDeepSpace 会在本地启动一个 HTTP 服务器，`--port` 参数指定 DeepSpace 监听的本地端口，默认值为 `9988`。当 DeepSpace 启动成功时，会输出：\n\n```shell\n[DeepSpace] 2024/08/26 12:12:26 DeepSpace Starts => change base_url to \"http://127.0.0.1:9988/v1\"\n```\n\n你可以将导出的文件投递至以下邮箱：\n\n[api-service@deepseek.com](mailto:api-service@deepseek.com)"
  },
  {
    "path": "docs/dingtalk/README.md",
    "content": "![dingtalk.png](assets/dingtalk.png)\n\n# DingTalk AI Assistant\nSupports users in independently selecting different DeepSeek models for task inference.\n\n- Currently, three major DeepSeek versions are available for user selection:\n    - DeepSeek-R1 32B Distilled Version\n    - DeepSeek-R1 671B Full-Power Version\n    - DeepSeek-V3 671B Full-Power Version\n\n![dingtalk_ai_assistant.png](assets/dingtalk_ai_assistant.png)"
  },
  {
    "path": "docs/dingtalk/README_cn.md",
    "content": "![dingtalk.png](assets/dingtalk.png)\n\n#钉钉AI助理\n支持用户自助选择deepseek不同模型进行任务推理\n- 目前支持deepseek三个大版本可供用户自助选择\n  - deepseek-R1 32B蒸馏版本\n  - deepseek-R1 671B满血版本\n  - deepseek-V3 671B满血版本\n\n\n![dingtalk_ai_assistant.png](assets/dingtalk_ai_assistant.png)"
  },
  {
    "path": "docs/docky-ai/README.md",
    "content": "<img src=\"http://cdn.docky.ai/assets/logo-with-text.svg\" height=\"64\" /> \n\n# [Docky AI](https://docky.ai)\n\n[Docky AI](https://docky.ai) is a powerful browser extension that allows you to have real-time conversations with multiple AI models through a sidebar. It supports simultaneous communication with multiple models and can assist you in reading web pages, writing, translating, and creating images\n\n## Installation\n* [Chrome Extension](https://chromewebstore.google.com/detail/miaadkeokbokhcgfndeofmfffhpchfne)\n* [Edge Extension](https://microsoftedge.microsoft.com/addons/detail/ifdhjlggobhfembihfpdogflohcdhdhl)\n\n## UI\n<img src=\"http://cdn.docky.ai/assets/snapshot.png\" /> \n"
  },
  {
    "path": "docs/docky-ai/README_cn.md",
    "content": "<img src=\"http://cdn.docky.ai/assets/logo-with-text.svg\" height=\"64\" /> \n\n# [Docky AI](https://docky.ai)\n\n[Docky AI](https://docky.ai) 是一款功能强大的浏览器插件，允许您通过侧边栏与多个 AI 模型进行实时对话。它支持多模型同时交流，并能协助您阅读网页、写作、翻译和创作图片\n\n## Installation\n* [Chrome Extension](https://chromewebstore.google.com/detail/miaadkeokbokhcgfndeofmfffhpchfne)\n* [Edge Extension](https://microsoftedge.microsoft.com/addons/detail/ifdhjlggobhfembihfpdogflohcdhdhl)\n\n## UI\n<img src=\"http://cdn.docky.ai/assets/snapshot.png\" /> \n"
  },
  {
    "path": "docs/docky-ai/README_ja.md",
    "content": "<img src=\"http://cdn.docky.ai/assets/logo-with-text.svg\" height=\"64\" /> \n\n# [Docky AI](https://docky.ai)\n\n[Docky AI](https://docky.ai) は強力なブラウザ拡張機能で、サイドバーを通じて複数のAIモデルとリアルタイムで会話することができます。複数モデルとの同時交流をサポートし、ウェブページの閲覧、執筆、翻訳、画像作成を支援します\n\n## Installation\n* [Chrome Extension](https://chromewebstore.google.com/detail/miaadkeokbokhcgfndeofmfffhpchfne)\n* [Edge Extension](https://microsoftedge.microsoft.com/addons/detail/ifdhjlggobhfembihfpdogflohcdhdhl)\n\n## UI\n<img src=\"http://cdn.docky.ai/assets/snapshot.png\" /> "
  },
  {
    "path": "docs/eechat/assets/README.md",
    "content": "<div align=\"center\">\n  <img src=\"./icon/icon.png\" alt=\"EE Chat Application Screenshot\" width=\"60\" />\n  <h1><a href=\"https://ee.chat\">eechat</a> </h1>\n  <p>🚀 Powerful Local AI Chat Application - Secure, Efficient, Personalized</p>\n  <p>  English |  <a href=\"./README.zh-CN.md\">简体中文</a>  </p>\n\n  <p style=\"margin-top:20px\">\n    <a href=\"#core-advantages\">Core Advantages</a> •\n    <a href=\"#key-features\">Key Features</a> •\n    <a href=\"#local-deployment\">Local Deployment</a> •\n    <a href=\"#quick-start\">Quick Start</a> •\n    <a href=\"#tech-stack\">Tech Stack</a> •\n    <a href=\"#contribute\">Contribute</a> •\n    <a href=\"#license\">License</a>\n  </p>\n  \n</div>\n\n  <img src=\"./resources/math.png\" alt=\"EE Chat Application Screenshot\" width=\"800\" />\n\n## Core Advantages\n\neechat is an AI chat application focused on local deployment, providing users with a secure, private, and efficient AI conversation experience.\n\n### 🔒 Data Security & Privacy Protection\n\n- **Fully Local Storage**: All conversation data is stored locally, eliminating privacy leak risks\n\n <img src=\"./resources/localmodel_light.png\" alt=\"EE Chat Application Screenshot\" width=\"800\" />\n\n- **Offline Capability**: No continuous internet connection required after initial setup\n- **API Customization**: Connect to your own AI model API or third-party services, maintaining full data flow control\n\n <img src=\"./resources/apimodel_dark.png\" alt=\"EE Chat Application Screenshot\" width=\"800\" />\n\n### 💬 Superior Conversation Experience\n\n- **Multi-Session Management**: Easily create and manage multiple independent conversations\n- **History Tracking**: Automatically save all conversation history for review and continuation\n- **Perfect Markdown Support**: Precise rendering of Markdown format, including code blocks, tables, and math formulas\n- **Smart Code Highlighting**: Automatic code block detection and highlighting for multiple programming languages\n\n### 🎨 Personalization Options\n\n- **Theme Switching**: Built-in light and dark themes for different scenarios and preferences\n- **Prompt Management**: Save and manage frequently used prompts to improve conversation efficiency\n- **Model Parameter Tuning**: Flexibly adjust temperature, max output, and other parameters for optimal responses\n\n### 🔌 Powerful Extensibility\n\n- **Plugin Ecosystem**: Support for functional extensions to meet specific scenario needs\n- **Multi-Model Integration**: Easy integration with various AI model APIs like OpenAI, Anthropic, etc.\n- **Custom Model Support**: Configure and use custom local or remote AI models\n\n## Key Features\n\n### Enhanced Intelligent Conversation\n\n- **Context Understanding**: AI maintains context coherence in long conversations\n- **Multi-Turn Optimization**: Enhanced interaction experience for complex queries\n- **Knowledge Base Integration**: Connect custom knowledge bases for more accurate domain-specific responses\n\n### Developer-Friendly\n\n- **Code Generation & Explanation**: Optimized code generation capabilities supporting multiple programming languages\n- **API Documentation Generation**: Assist developers in quickly generating API documentation\n- **Debug Assistance**: Help identify code issues and provide fix suggestions\n\n### Productivity Tools\n\n- **Document Summarization**: Quickly summarize long document content\n- **Mind Map Generation**: Transform complex concepts into structured mind maps\n- **Multi-Language Translation**: Support high-quality translation between multiple languages\n\n## Local Deployment\n\neechat is designed for local deployment, ensuring your data security and optimal user experience.\n\n### System Requirements\n\n- Windows 10/11 64-bit\n- macOS 10.15+\n- Linux (Ubuntu 18.04+, Debian 10+)\n- Minimum 4GB RAM\n- 500MB available disk space\n- GPU with CUDA support (optional) 8GB+ (win)\n\n### Installation Methods\n\n#### Download Pre-built Packages\n\nDownload the appropriate installation package for your system from the [releases page](https://github.com/Lucassssss/eechat/releases):\n\n#### Build from Source\n\n```bash\n# Clone repository\ngit clone https://github.com/Lucassssss/eechat.git\ncd eechat\n\n# Install dependencies\nnpm install\n\n# Run in development mode\nnpm run dev\n\n# Build application\nnpm run build\n```"
  },
  {
    "path": "docs/eechat/assets/README.zh-CN.md",
    "content": "<div align=\"center\">\n  <img src=\"./icon/icon.png\" alt=\"EE 聊天应用截图\" width=\"60\" />\n  <h1><a href=\"https://ee.chat\">eechat</a> </h1>\n  <p>🚀 强大的本地化 AI 聊天应用 - 安全、高效、个性化</p>\n  <p> <a href=\"./README.md\"> English</a> |  简体中文  </p>\n\n  <p style=\"margin-top:20px\">\n    <a href=\"#核心优势\">核心优势</a> •\n    <a href=\"#主要功能\">主要功能</a> •\n    <a href=\"#本地化部署\">本地化部署</a> •\n    <a href=\"#快速开始\">快速开始</a> •\n    <a href=\"#技术栈\">技术栈</a> •\n    <a href=\"#参与贡献\">参与贡献</a> •\n    <a href=\"#开源协议\">开源协议</a>\n  </p>\n  \n</div>\n\n<img src=\"./resources/math.png\" alt=\"EE 聊天应用截图\" width=\"800\" />\n\n## 核心优势\n\neechat是一款专注于本地化部署的 AI 聊天应用，为用户提供安全、私密且高效的人工智能对话体验。\n\n### 🔒 数据安全与隐私保护\n\n- **完全本地存储**：所有对话数据均存储于本地，杜绝隐私泄露风险\n\n\n<img src=\"./resources/localmodel_light.png\" alt=\"本地模型界面\" width=\"800\" />\n\n\n- **离线能力**：初始化设置后无需持续联网\n- **API 自定义**：可连接自有 AI 模型 API 或第三方服务，全程掌控数据流向\n\n\n\n<img src=\"./resources/apimodel_dark.png\" alt=\"API 模型设置\" width=\"800\" />\n\n### 💬 卓越对话体验\n\n- **多会话管理**：轻松创建和管理多个独立对话\n- **历史追溯**：自动保存全部对话记录，支持随时查阅与续聊\n- **完美 Markdown 支持**：精准渲染代码块、表格、数学公式等格式\n- **智能代码高亮**：自动检测并高亮多种编程语言代码块\n\n### 🎨 个性化定制\n\n- **主题切换**：内置明暗双色模式，适应不同场景需求\n- **提示词管理**：保存常用提示模板，提升对话效率\n- **模型参数调节**：灵活调整温度值、最大输出等参数获取最佳响应\n\n### 🔌 强大扩展性\n\n- **插件生态**：支持功能扩展，满足特定场景需求\n- **多模型集成**：轻松对接 OpenAI、Anthropic 等各类 AI 模型 API\n- **自定义模型支持**：配置使用自有本地或远程 AI 模型\n\n## 主要功能\n\n### 增强智能对话\n\n- **上下文理解**：AI 可在长对话中保持语境连贯\n- **多轮优化**：针对复杂查询的增强交互体验\n- **知识库整合**：连接自定义知识库获取更精准的领域响应\n\n### 开发者友好\n\n- **代码生成与解释**：优化多编程语言的代码生成能力\n- **API 文档生成**：协助开发者快速生成接口文档\n- **调试辅助**：帮助识别代码问题并提供修复建议\n\n### 生产力工具\n\n- **文档摘要**：快速提炼长文档核心内容\n- **思维导图生成**：将复杂概念转化为结构化视图\n- **多语言翻译**：支持多种语言的高质量互译\n\n## 本地化部署\n\neechat专为本地化部署设计，确保您的数据安全和最佳使用体验。\n\n### 系统要求\n\n- Windows 10/11 64 位\n- macOS 10.15+\n- Linux (Ubuntu 18.04+, Debian 10+)\n- 最低 4GB 内存\n- 500MB 可用存储空间\n- 支持 CUDA 的 GPU（可选）8GB+（Windows）\n\n### 安装方式\n\n#### 下载预编译包\n\n从[发布页面](https://github.com/Lucassssss/eechat/releases)下载适用于您系统的安装包：\n\n#### 源码编译\n\n```bash\n# 克隆仓库\ngit clone https://github.com/Lucassssss/eechat.git\ncd eechat\n\n# 安装依赖\nnpm install\n\n# 开发模式运行\nnpm run dev\n\n# 构建应用\nnpm run build\n```"
  },
  {
    "path": "docs/enconvo/README.md",
    "content": "<img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/logo.png\" width=\"64\" height=\"auto\" /> \n\n# [Enconvo](https://www.enconvo.com/)\n\n Enconvo is the Launcher of the AI era, the entry point for all AI functions, and a thoughtful intelligent assistant.\n\n## UI\n\n<img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/deepseek/ui.png\" />\n\n\n## Integrate with Deepseek API\n\n<img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/deepseek/settings.png\" />\n"
  },
  {
    "path": "docs/enconvo/README_cn.md",
    "content": "<img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/logo.png\" width=\"64\" height=\"auto\" /> \n\n# [Enconvo](https://www.enconvo.com/)\n\nEnconvo是AI时代的启动器,是所有AI功能的入口,也是一位体贴的智能助理.\n\n## UI\n\n<img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/deepseek/ui_cn.png\" />\n\n\n## 配置 deepseek API\n\n<img src=\"https://raw.githubusercontent.com/ysnows/enconvo_media/main/deepseek/settings.png\" />\n"
  },
  {
    "path": "docs/fhe.mind-network/README.md",
    "content": "# Mind Network FHE Rust SDK\n`mind_sdk_deepseek` is a **Native Rust SDK** by [Mind Network](https://www.mindnetwork.xyz/) to enable FHE function for DeepSeek. DeepSeek will assist user as an AI Agent to think and predict, and then encrypted by FHE and submit to Mind Network for model consensus. \n\n[![mind_sdk_deepseek on crates.io](https://img.shields.io/crates/v/mind_sdk_deepseek)](https://crates.io/crates/mind_sdk_deepseek)\n[![Documentation on docs.rs](https://img.shields.io/badge/docs-docs.rs-blue)](https://docs.rs/mind_sdk_deepseek)\n[![Licensed](https://img.shields.io/badge/license-MIT-blue.svg)](./LICENSE)\n[![Github](https://img.shields.io/badge/source-github.com-blue.svg)](https://github.com/mind-network/mind-sdk-deepseek-rust)\n[![Github](https://img.shields.io/badge/build-pass-green.svg)](https://github.com/mind-network/mind-sdk-deepseek-rust)\n\n\n## Usage \n```rust\n// call deepseek to predict, you can change to other prompt as you wish\nlet prompt = \"Please predict BTC price in next 7 days, return must be a positive integer\".to_string()\nlet client = deepseek_rs::DeepSeekClient::default().unwrap();\nlet request = deepseek_rs::client::chat_completions::request::RequestBody::new_messages(vec![\n        deepseek_rs::client::chat_completions::request::Message::new_user_message(prompt)\n    ]).with_model(deepseek_rs::client::chat_completions::request::Model::DeepSeekReasoner);\nlet response = client.chat_completions(request).await.unwrap();\n//println!(\"Reasoning: {}\", response.choices[0].message.reasoning_content.unwrap());\n//println!(\"Answer: {}\", response.choices[0].message.content.unwrap());\n\n// convert deepseek prediction to int type\nlet deepseek_prediction = match response.choices[0].clone().message.content.unwrap().parse::<u128>() {\n    Ok(prediction) => prediction,\n    Err(_) => 0,\n};\n        \n// fhe encrypt\nlet fhe: mind_sdk_fhe::FheInt = mind_sdk_fhe::FheInt::new_from_public_key_local(&fhe_public_key_fp);\nlet ciphertext = mind_sdk_fhe::fhe_client::encrypt(&fhe, \"u8\", deepseek_prediction.clone());\nlet ciphertext_str: String = mind_sdk_fhe::io::serialize_base64(ciphertext)?;\n\n// submit ciphertext onchain\nlet result: alloy::rpc::types::TransactionReceipt = self.submit_fhe_encrypted(ciphertext_str).await?;\n```\n\n## Quick Start\n\n## Source\n```bash\ngit clone https://github.com/mind-network/mind-sdk-deepseek-rust.git\ncd mind-sdk-deepseek-rust\n```\n\n### Install \n```toml\n[dependencies]\nmind_sdk_deepseek = \"*\n```\n\n### build \n```bash\ncargo build --debug\ncargo build --release\n```\n\n### run\n``` bash\ncd msn\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=info check-hot-wallet-address\n\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn.toml register 0x06eF5C5ba427434bf36469B877e4ea9044D1b735\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn_1.toml register 0x2F8aCe76a34e50943573826A326a8Eb8DC854f84\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn_2.toml register 0x3df4b66E1895E68aB000f1086e9393ca1937Cd8b\n\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn.toml deepseek-fhe-vote \ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn_1.toml deepseek-fhe-vote\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn_2.toml deepseek-fhe-vote\n\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn.toml check-registration\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn_1.toml check-registration\ncargo build && ./target/debug/mind_sdk_deepseek --log-level=debug --node-config-file=./config/config_fvn_2.toml check-registration\n```\n\n\n\n## CLI Help\n``` bash\n# ./bin/deepseek --help\n\nFHE Randen Voter Node Cli\n\nUsage: fvn [OPTIONS] <COMMAND>\n\nCommands:\n  deepseek-fhe-vote         let deepseek think and predict, and then encrypted by FHE and submit to Mind Network for model consensus\n  check-hot-wallet-address  check hot wallet address, by default will use ./config/config_fvn.toml\n  check-gas-balance         check hot wallet gas balance, need gas fee to vote\n  check-registration        check if hot wallet has registered with a particular voter wallet\n  register                  register voter address\n  check-vote-rewards        check voting rewards\n  check-vote                check voting tx history on the explore\n  help                      Print this message or the help of the given subcommand(s)\n\nOptions:\n      --node-config-file <NODE_CONFIG_FILE>\n          fvn config file, contains all the config to run fvn [default: ./config/config_fvn.toml]\n      --log-level <LOG_LEVEL>\n          control level of print, useful for debug, default is info [default: info] [possible values: debug, info, warn, error]\n      --hot-wallet-private-key <HOT_WALLET_PRIVATE_KEY>\n          fvn wallet private key is needed if to load a different wallet from config_fvn.toml to sign the message onchain, by default load from ./config/config_fvn.toml\n  -h, --help\n          Print help\n  -V, --version\n          Print version\n```\n\n## CLI Example\n``` bash\n## command\n./bin/deepseek --log-level=info deepseek-fhe-vote \n{\n  \"app\": \"deepseek\",\n  \"command\": \"deepseek-fhe-vote\",\n  \"arg\": \"deekseek predicted BTC price: 95833, hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd\",\n  \"status\": true,\n  \"result\": \"0x42d78185e4779dd3105598ac4f2786998c5059f8381a55daec12e4ffcc952a56\",\n  \"note\": \"deekseek predicted BTC price: 95833, gas_sued: 304749, block_number: 26373, tx_hash: 0x42d78185e4779dd3105598ac4f2786998c5059f8381a55daec12e4ffcc952a56\"\n}\n\n## command\n./bin/deepseek --log-level=info check-hot-wallet-address\n{\n  \"app\": \"deepseek\",\n  \"command\": \"check-hot-wallet-address\",\n  \"arg\": \"\",\n  \"status\": true,\n  \"result\": \"0x64FF17078669A507D0c831D9E844AF1C967604Dd\",\n  \"note\": \"\"\n}\n\n## command\n./bin/deepseek --log-level=info check-gas-balance\n{\n  \"app\": \"deepseek\",\n  \"command\": \"check-gas-balance\",\n  \"arg\": \"hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd\",\n  \"status\": true,\n  \"result\": \"197015375000000\",\n  \"note\": \"\"\n}\n\n## command\n./bin/deepseek --log-level=info check-registration\n{\n  \"app\": \"deepseek\",\n  \"command\": \"check-registration\",\n  \"arg\": \"0x6224F72f1439E76803e063262a7e1c03e86c6Dbd\",\n  \"status\": false,\n  \"result\": \"\",\n  \"note\": \"hot wallet is not registered with any voter wallet\"\n}\n\n## command\n./bin/deepseek --log-level=info check-vote-rewards\n{\n  \"app\": \"deepseek\",\n  \"command\": \"check-vote-rewards\",\n  \"arg\": \"hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd\",\n  \"status\": false,\n  \"result\": \"0\",\n  \"note\": \"hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd, voter_wallet: , vote_rewards: 0\"\n}\n\n## command\n./bin/deepseek --log-level=info register 0x06eF5C5ba427434bf36469B877e4ea9044D1b735\n{\n  \"app\": \"deepseek\",\n  \"command\": \"register\",\n  \"arg\": \"hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd, voter_wallet: 0x06eF5C5ba427434bf36469B877e4ea9044D1b735\",\n  \"status\": true,\n  \"result\": \"registration successful !\",\n  \"note\": \"is_registered: true, hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd, voter_wallet: 0x06eF5C5ba427434bf36469B877e4ea9044D1b735\"\n}\n\n\n## command\n./bin/deepseek --log-level=info check-vote-rewards\n{\n  \"app\": \"deepseek\",\n  \"command\": \"check-vote-rewards\",\n  \"arg\": \"hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd\",\n  \"status\": true,\n  \"result\": \"206095238095238095\",\n  \"note\": \"hot_wallet: 0x6224F72f1439E76803e063262a7e1c03e86c6Dbd, voter_wallet: 0x06eF5C5ba427434bf36469B877e4ea9044D1b735, vote_rewards: 206095238095238095\"\n}\n\n## command\n./bin/deepseek --log-level=info check-vote\n{\n  \"app\": \"deepseek\",\n  \"command\": \"check-vote\",\n  \"arg\": \"0x6224F72f1439E76803e063262a7e1c03e86c6Dbd\",\n  \"status\": true,\n  \"result\": \"check on the explore: testnet: https://explorer-testnet.mindnetwork.xyz/address/0x6224F72f1439E76803e063262a7e1c03e86c6Dbd, mainnet: https://explorer.mindnetwork.xyz/address/0x6224F72f1439E76803e063262a7e1c03e86c6Dbd\",\n  \"note\": \"\"\n}\n\n```\n\n## **License**\n\nThis project is licensed under the **MIT License**.\n\n## **Contact**\n\nFor questions or support, please contact [Mind Network Official Channels](https://mindnetwork.xyz/).\n\n\n"
  },
  {
    "path": "docs/hcfy/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c3d9d100-247a-41cc-97c1-10b01ed25e70\" width=\"64\" height=\"auto\" /> \n\n# [hcfy](https://hcfy.app/)\n\nhcfy (划词翻译) is a browser translation plugin that integrates multiple translation APIs and LLM APIs.\n\n## UI\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/367a41b6-3277-4897-a53f-aaa17bb9dc53)\n\n\n## Integrate with Deepseek API\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/b09c8c94-f0ce-4a83-9c97-3aaec58df712)\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1aecc349-b0d9-46db-9e0f-0034e672cce4)\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/340188ac-617a-45df-a9b5-b1c47a4943a1)\n"
  },
  {
    "path": "docs/hcfy/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c3d9d100-247a-41cc-97c1-10b01ed25e70\" width=\"64\" height=\"auto\" /> \r\n\r\n# [划词翻译](https://hcfy.app/)\r\n\r\n整合了多家翻译 API 以及 LLM API 的浏览器翻译插件.\r\n\r\n## UI\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/367a41b6-3277-4897-a53f-aaa17bb9dc53)\r\n\r\n\r\n## 配置 deepseek API\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/c28dad22-9102-4bb1-a32c-549472be5972)\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1aecc349-b0d9-46db-9e0f-0034e672cce4)\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/340188ac-617a-45df-a9b5-b1c47a4943a1)\r\n"
  },
  {
    "path": "docs/huixiangdou/README.md",
    "content": "<img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/huixiangdou.jpg\" width=\"64\" height=\"auto\" />\n\n# [HuixiangDou](https://github.com/InternLM/HuixiangDou)\n\"HuixiangDou\" is a domain knowledge assistant based on LLM. Features:\n\n1. Handles complex scenarios such as group chat and handle answer user questions without flooding messages.\n2. Proposes a solution for technical issues through an algorithm pipeline.\n3. Low cost, see [arxiv2401.08772](https://arxiv.org/abs/2401.08772)\n\n# Demonstration\nHuixiangDou is a **assistant**\n* Says it doesn't know in response to halluciations\n* Personal Wechat supported\n* Feishu supported\n\n<img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/demo0.jpg\" width=\"400\">\n\nHuixiangDou is a **group** assistant\n* Ignores idle talk\n* Only interacts with those who need help\n\n<img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/inside-mmpose.jpg\" width=\"400\">\n\nHuixiangDou is a **domain knowledge** group assistant\n* Relies on an algorithm pipeline + LLM instead of training\n* Has faced thousands of users, and has been \"teased\" over 20,000 times in half a year\n\n<img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/inside-middleware.png\" width=\"400\">\n\n# Configuring deepseek API\n**STEP1.** Apply for a token at deepseek open platform\n\n**STEP2.** Follow the HuixiangDou Advanced Configuration and fill in the config.ini with your token\n\n```ini\n# config.ini\n[llm]\nenable_local = 0\nenable_remote = 1\n..\n[llm.server]\n..\nremote_type = \"deepseek\"\nremote_api_key = \"YOUR-API-KEY\"\nremote_llm_max_text_length = 16000\nremote_llm_model = \"deepseek-chat\"\n```\n\n**STEP3.** Run\n\n```shell\npython3 -m huixiangdou.main --standalone\n```"
  },
  {
    "path": "docs/huixiangdou/README_cn.md",
    "content": "<img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/huixiangdou.jpg\" width=\"64\" height=\"auto\" /> \n\n# [茴香豆](https://github.com/InternLM/HuixiangDou)\n\n“茴香豆”是一个基于 LLM 的领域知识助手。特点：\n\n1. 应对群聊这类复杂场景，解答用户问题的同时，不会消息泛滥\n2. 提出一套解答技术问题的算法 pipeline\n3. 部署成本低，见[技术报告 arxiv2401.08772](https://arxiv.org/abs/2401.08772)\n\n\n## 效果展示\n\n1. 它是个**机器人**\n\n    * 面对幻觉会说不知道\n    * 支持微信\n    * 支持飞书\n\n    <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/demo0.jpg\" width=\"400\">\n\n2. 它是个**群组**机器人\n\n    * 不会搭理闲聊\n    * 只找需要帮助的人\n\n    <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/inside-mmpose.jpg\" width=\"400\">\n\n2. 它是个**领域知识**群组机器人\n\n    * 不依赖训练，依靠算法 pipeline + LLM\n    * 已经面对数千用户，半年被“调戏”了 2w 次以上\n\n    <img src=\"https://github.com/InternLM/HuixiangDou/releases/download/v0.1.0rc1/inside-middleware.png\" width=\"400\">\n\n## 配置 deepseek API\n\n**STEP1.** 打开 [deepseek 开放平台](https://platform.deepseek.com) 申请 token\n\n**STEP2.** 参照 [HuixiangDou 高级配置](https://github.com/InternLM/HuixiangDou?tab=readme-ov-file#step4-advanced-version-optional)，把 token 填入 `config.ini`\n\n```ini\n# config.ini\n[llm]\nenable_local = 0\nenable_remote = 1\n..\n[llm.server]\n..\nremote_type = \"deepseek\"\nremote_api_key = \"YOUR-API-KEY\"\nremote_llm_max_text_length = 16000\nremote_llm_model = \"deepseek-chat\"\n```\n\n**STEP3.** 运行\n```shell\npython3 -m huixiangdou.main --standalone\n```"
  },
  {
    "path": "docs/immersive_reading_guide/README.md",
    "content": "<img src=\"https://lh3.googleusercontent.com/K9i0qJb8phasC5wWf5tU68rhnfvX4swsE0hrhJP-WB3WV7MwE5KpMUIJvHKNHHRE6GKNIvIdTNSWoDMl_NggrmUsaw=s120\" alt=\"Icon\" width=\"64\" height=\"auto\" />\n\n# [Immersive Reading Guide](https://chromewebstore.google.com/detail/immersive-reading-guide/jnjhalaghogaleoidplmjhjnemmakffp)\n\nNO Sidebar!!! Immersive AI web summarization, ask questions...\n\n## Preview\n\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/concepts.png?raw=true)\n\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/table-en.png?raw=true)\n\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/ask-en.png?raw=true)\n\n## Deepseek API\n\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/deepseel-model-config-en.png?raw=true)\n\n"
  },
  {
    "path": "docs/immersive_reading_guide/README_cn.md",
    "content": "<img src=\"https://lh3.googleusercontent.com/K9i0qJb8phasC5wWf5tU68rhnfvX4swsE0hrhJP-WB3WV7MwE5KpMUIJvHKNHHRE6GKNIvIdTNSWoDMl_NggrmUsaw=s120\" alt=\"Icon\" width=\"64\" height=\"auto\" />\r\n\r\n# [沉浸式导读](https://chromewebstore.google.com/detail/immersive-reading-guide/jnjhalaghogaleoidplmjhjnemmakffp)\r\n\r\nNO Sidebar!!! 沉浸式的 AI 网页摘要，提问...\r\n\r\n## Preview\r\n\r\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/concepts.png?raw=true)\r\n\r\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/table.png?raw=true)\r\n\r\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/ask.png?raw=true)\r\n\r\n## Deepseek API\r\n\r\n![image](https://github.com/glidea/pages/blob/main/immersive-reading-guide/deepseek-model-config.png?raw=true)\r\n\r\n"
  },
  {
    "path": "docs/immersive_translate/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9d3f42b8-fcd0-47ab-8b06-1dd0554dd80e\" width=\"64\" height=\"auto\" /> \n\n# [Immersive Translate](https://immersivetranslate.com/)\n\nImmersive Translate is a bilingual webpage translation plugin.\n\n## UI\n\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/adf0f871-3ea6-4523-b892-57305bbe8de0)\n\n\n## Integrate with Deepseek API\n\n![20240808-131028](https://github.com/user-attachments/assets/081f00ee-46b8-4227-9d20-e79ce2e68004)\n\n"
  },
  {
    "path": "docs/immersive_translate/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/9d3f42b8-fcd0-47ab-8b06-1dd0554dd80e\" width=\"64\" height=\"auto\" /> \r\n\r\n# [沉浸式翻译](https://immersivetranslate.com/)\r\n\r\n沉浸式翻译是一款双语对照网页翻译插件.\r\n\r\n## UI\r\n\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/adf0f871-3ea6-4523-b892-57305bbe8de0)\r\n\r\n\r\n## 配置 Deepseek API\r\n\r\n![20240808-131028](https://github.com/user-attachments/assets/57c8fbc1-31d8-4d0c-9edd-6b75512feed1)\r\n\r\n"
  },
  {
    "path": "docs/liubai/README.md",
    "content": "<img src=\"./assets/liubai-logo.png\" width=\"64\" height=\"auto\" /> \n\n# [Liubai](https://github.com/yenche123/liubai)\n\nLet DeepSeek manage your Notes, Tasks, Calendars, and To-Do Lists directly on WeChat!\n\n## UI\n\n<img src=\"./assets/screenshot01.jpg\" width=\"360\" height=\"auto\" />\n\n<img src=\"./assets/screenshot02.jpg\" width=\"360\" height=\"auto\" />\n\n"
  },
  {
    "path": "docs/liubai/README_cn.md",
    "content": "<img src=\"./assets/liubai-logo.png\" width=\"64\" height=\"auto\" /> \n\n# [Liubai](https://github.com/yenche123/liubai)\n\n让 DeepSeek 直接在微信上管理你的笔记、任务、日程和待办清单！\n\n## UI\n\n<img src=\"./assets/screenshot01.jpg\" width=\"360\" height=\"auto\" />\n\n<img src=\"./assets/screenshot02.jpg\" width=\"360\" height=\"auto\" />\n\n"
  },
  {
    "path": "docs/llm.nvim/README.md",
    "content": "> [!IMPORTANT]\n> A free large language model(LLM) plugin that allows you to interact with LLM in Neovim.\n>\n> The main functions include but are not limited to:\n>\n> - AI chat\n> - Word translation\n> - Code explanation\n> - Code optimization\n> - Test case generation\n> - AI translation\n> - Generation of git commit messages\n> - Generation of docstrings\n\nLink: [Github:Kurama622/llm.nvim](https://github.com/Kurama622/llm.nvim)\n\n# Install\n\n- lazy.nvim\n\n```lua\nreturn {\n  {\n    \"Kurama622/llm.nvim\",\n    dependencies = { \"nvim-lua/plenary.nvim\", \"MunifTanjim/nui.nvim\" },\n    cmd = { \"LLMSessionToggle\", \"LLMSelectedTextHandler\", \"LLMAppHandler\" },\n    config = function()\n      require(\"llm\").setup({\n        url = \"https://api.deepseek.com/chat/completions\",\n        model = \"deepseek-chat\",\n        api_type = \"openai\",\n        max_tokens = 4096,\n        temperature = 0.3,\n        top_p = 0.7,\n\n        prompt = \"You are a helpful Chinese assistant.\",\n\n        prefix = {\n          user = { text = \"  \", hl = \"Title\" },\n          assistant = { text = \"  \", hl = \"Added\" },\n        },\n\n        -- history_path = \"/tmp/llm-history\",\n        save_session = true,\n        max_history = 15,\n        max_history_name_length = 20,\n\n        -- stylua: ignore\n        keys = {\n          -- The keyboard mapping for the input window.\n          [\"Input:Submit\"]      = { mode = \"n\", key = \"<cr>\" },\n          [\"Input:Cancel\"]      = { mode = {\"n\", \"i\"}, key = \"<C-c>\" },\n          [\"Input:Resend\"]      = { mode = {\"n\", \"i\"}, key = \"<C-r>\" },\n\n          -- only works when \"save_session = true\"\n          [\"Input:HistoryNext\"] = { mode = {\"n\", \"i\"}, key = \"<C-j>\" },\n          [\"Input:HistoryPrev\"] = { mode = {\"n\", \"i\"}, key = \"<C-k>\" },\n\n          -- The keyboard mapping for the output window in \"split\" style.\n          [\"Output:Ask\"]        = { mode = \"n\", key = \"i\" },\n          [\"Output:Cancel\"]     = { mode = \"n\", key = \"<C-c>\" },\n          [\"Output:Resend\"]     = { mode = \"n\", key = \"<C-r>\" },\n\n          -- The keyboard mapping for the output and input windows in \"float\" style.\n          [\"Session:Toggle\"]    = { mode = \"n\", key = \"<leader>ac\" },\n          [\"Session:Close\"]     = { mode = \"n\", key = {\"<esc>\", \"Q\"} },\n        },\n      })\n    end,\n    keys = {\n      { \"<leader>ac\", mode = \"n\", \"<cmd>LLMSessionToggle<cr>\" },\n      { \"<leader>ae\", mode = \"v\", \"<cmd>LLMSelectedTextHandler 请解释下面这段代码<cr>\" },\n      { \"<leader>ts\", mode = \"x\", \"<cmd>LLMSelectedTextHandler 英译汉<cr>\" },\n    },\n  },\n}\n```\n\n"
  },
  {
    "path": "docs/llm.nvim/README_cn.md",
    "content": "> [!IMPORTANT]\n> 免费的大语言模型插件，让你在Neovim中与大模型交互\n>\n> 主要功能包括但不限于:\n>\n> - AI对话\n> - 划词翻译\n> - 解释代码\n> - 优化代码\n> - 生成测试用例\n> - AI翻译\n> - 生成git commit信息\n> - 生成docstring\n\n链接: [Github:Kurama622/llm.nvim](https://github.com/Kurama622/llm.nvim)\n\n# 安装\n\n- lazy.nvim\n\n```lua\nreturn {\n  {\n    \"Kurama622/llm.nvim\",\n    dependencies = { \"nvim-lua/plenary.nvim\", \"MunifTanjim/nui.nvim\" },\n    cmd = { \"LLMSessionToggle\", \"LLMSelectedTextHandler\", \"LLMAppHandler\" },\n    config = function()\n      require(\"llm\").setup({\n        url = \"https://api.deepseek.com/chat/completions\",\n        model = \"deepseek-chat\",\n        api_type = \"openai\",\n        max_tokens = 4096,\n        temperature = 0.3,\n        top_p = 0.7,\n\n        prompt = \"You are a helpful Chinese assistant.\",\n\n        prefix = {\n          user = { text = \"  \", hl = \"Title\" },\n          assistant = { text = \"  \", hl = \"Added\" },\n        },\n\n        -- history_path = \"/tmp/llm-history\",\n        save_session = true,\n        max_history = 15,\n        max_history_name_length = 20,\n\n        -- stylua: ignore\n        keys = {\n          -- The keyboard mapping for the input window.\n          [\"Input:Submit\"]      = { mode = \"n\", key = \"<cr>\" },\n          [\"Input:Cancel\"]      = { mode = {\"n\", \"i\"}, key = \"<C-c>\" },\n          [\"Input:Resend\"]      = { mode = {\"n\", \"i\"}, key = \"<C-r>\" },\n\n          -- only works when \"save_session = true\"\n          [\"Input:HistoryNext\"] = { mode = {\"n\", \"i\"}, key = \"<C-j>\" },\n          [\"Input:HistoryPrev\"] = { mode = {\"n\", \"i\"}, key = \"<C-k>\" },\n\n          -- The keyboard mapping for the output window in \"split\" style.\n          [\"Output:Ask\"]        = { mode = \"n\", key = \"i\" },\n          [\"Output:Cancel\"]     = { mode = \"n\", key = \"<C-c>\" },\n          [\"Output:Resend\"]     = { mode = \"n\", key = \"<C-r>\" },\n\n          -- The keyboard mapping for the output and input windows in \"float\" style.\n          [\"Session:Toggle\"]    = { mode = \"n\", key = \"<leader>ac\" },\n          [\"Session:Close\"]     = { mode = \"n\", key = {\"<esc>\", \"Q\"} },\n        },\n      })\n    end,\n    keys = {\n      { \"<leader>ac\", mode = \"n\", \"<cmd>LLMSessionToggle<cr>\" },\n      { \"<leader>ae\", mode = \"v\", \"<cmd>LLMSelectedTextHandler 请解释下面这段代码<cr>\" },\n      { \"<leader>ts\", mode = \"x\", \"<cmd>LLMSelectedTextHandler 英译汉<cr>\" },\n    },\n  },\n}\n```\n\n"
  },
  {
    "path": "docs/minuet-ai.nvim/README.md",
    "content": "\n# Minuet AI\n\nMinuet AI: Dance with Intelligence in Your Code 💃.\n\n`Minuet-ai` brings the grace and harmony of a minuet to your coding process.\nJust as dancers move during a minuet.\n\n# Features\n\n- AI-powered code completion with dual modes:\n  - Specialized prompts and various enhancements for chat-based LLMs on code completion tasks.\n  - Fill-in-the-middle (FIM) completion for compatible models (DeepSeek,\n    Codestral, Qwen, and others).\n- Support for multiple AI providers (OpenAI, Claude, Gemini, Codestral, Ollama, and\n  OpenAI-compatible services).\n- Customizable configuration options.\n- Streaming support to enable completion delivery even with slower LLMs.\n- Support `nvim-cmp`, `blink-cmp`, `virtual text` frontend.\n\n# Requirements\n\n- Neovim 0.10+.\n- [plenary.nvim](https://github.com/nvim-lua/plenary.nvim)\n- optional: [nvim-cmp](https://github.com/hrsh7th/nvim-cmp)\n- optional: [blink.cmp](https://github.com/Saghen/blink.cmp)\n- An API key for at least one of the supported AI providers\n\n# Installation\n\n**Lazy.nvim**:\n\n```lua\nspecs = {\n    {\n        'milanglacier/minuet-ai.nvim',\n        config = function()\n            require('minuet').setup {\n                -- Your configuration options here\n            }\n        end,\n    },\n    { 'nvim-lua/plenary.nvim' },\n    -- optional, if you are using virtual-text frontend, nvim-cmp is not\n    -- required.\n    { 'hrsh7th/nvim-cmp' },\n    -- optional, if you are using virtual-text frontend, blink is not required.\n    { 'Saghen/blink.cmp' },\n}\n```\n\n**Rocks.nvim**:\n\n`Minuet` is available on luarocks.org. Simply run `Rocks install\nminuet-ai.nvim` to install it like any other luarocks package.\n\n**Setting up with virtual text**:\n\n```lua\nrequire('minuet').setup {\n    virtualtext = {\n        auto_trigger_ft = {},\n        keymap = {\n            -- accept whole completion\n            accept = '<A-A>',\n            -- accept one line\n            accept_line = '<A-a>',\n            -- accept n lines (prompts for number)\n            -- e.g. \"A-z 2 CR\" will accept 2 lines\n            accept_n_lines = '<A-z>',\n            -- Cycle to prev completion item, or manually invoke completion\n            prev = '<A-[>',\n            -- Cycle to next completion item, or manually invoke completion\n            next = '<A-]>',\n            dismiss = '<A-e>',\n        },\n    },\n}\n```\n\n**Setting up with nvim-cmp**:\n\n<details>\n\n```lua\nrequire('cmp').setup {\n    sources = {\n        {\n             -- Include minuet as a source to enable autocompletion\n            { name = 'minuet' },\n            -- and your other sources\n        }\n    },\n    performance = {\n        -- It is recommended to increase the timeout duration due to\n        -- the typically slower response speed of LLMs compared to\n        -- other completion sources. This is not needed when you only\n        -- need manual completion.\n        fetching_timeout = 2000,\n    },\n}\n\n\n-- If you wish to invoke completion manually,\n-- The following configuration binds `A-y` key\n-- to invoke the configuration manually.\nrequire('cmp').setup {\n    mapping = {\n        [\"<A-y>\"] = require('minuet').make_cmp_map()\n        -- and your other keymappings\n    },\n}\n```\n\n</details>\n\n**Setting up with blink-cmp**:\n\n<details>\n\n```lua\nrequire('blink-cmp').setup {\n    keymap = {\n        -- Manually invoke minuet completion.\n        ['<A-y>'] = require('minuet').make_blink_map(),\n    },\n    sources = {\n         -- Enable minuet for autocomplete\n        default = { 'lsp', 'path', 'buffer', 'snippets', 'minuet' },\n        -- For manual completion only, remove 'minuet' from default\n        providers = {\n            minuet = {\n                name = 'minuet',\n                module = 'minuet.blink',\n                score_offset = 8, -- Gives minuet higher priority among suggestions\n            },\n        },\n    },\n    -- Recommended to avoid unnecessary request\n    completion = { trigger = { prefetch_on_insert = false } },\n}\n```\n\n</details>\n\n**LLM Provider Examples**:\n\n**Deepseek**:\n\n```lua\n-- you can use deepseek with both openai_fim_compatible or openai_compatible provider\nrequire('minuet').setup {\n    provider = 'openai_fim_compatible',\n    provider_options = {\n        openai_fim_compatible = {\n            api_key = 'DEEPSEEK_API_KEY',\n            name = 'deepseek',\n            optional = {\n                max_tokens = 256,\n                top_p = 0.9,\n            },\n        },\n    },\n}\n\n\n-- or\nrequire('minuet').setup {\n    provider = 'openai_compatible',\n    provider_options = {\n        openai_compatible = {\n            end_point = 'https://api.deepseek.com/v1/chat/completions',\n            api_key = 'DEEPSEEK_API_KEY',\n            name = 'deepseek',\n            optional = {\n                max_tokens = 256,\n                top_p = 0.9,\n            },\n        },\n    },\n}\n```\n"
  },
  {
    "path": "docs/minuet-ai.nvim/README_cn.md",
    "content": "# Minuet AI\n\nMinuet AI：在您的代码中翩翩起舞，挥洒智能 💃。\n\n`Minuet-ai` 将小步舞曲的优雅与和谐带入您的编码流程。正如舞者在小步舞曲中舞动一样。\n\n# 特性\n\n- 基于 AI 的代码补全，提供双重模式：\n  - 针对代码补全任务，为基于聊天的 LLMs 提供专门的提示和各种增强功能。\n  - 针对兼容的模型（DeepSeek、Codestral、Qwen 等）提供中间填充 (FIM) 补全。\n- 支持多种 AI 提供商（OpenAI、Claude、Gemini、Codestral、Ollama 和兼容 OpenAI 的服务）。\n- 可自定义配置选项。\n- 支持流式传输，即使使用较慢的 LLMs 也能实现补全的交付。\n- 支持 `nvim-cmp`、`blink-cmp`、`virtual text` 前端。\n\n# 要求\n\n- Neovim 0.10+。\n- [plenary.nvim](https://github.com/nvim-lua/plenary.nvim)\n- 可选： [nvim-cmp](https://github.com/hrsh7th/nvim-cmp)\n- 可选： [blink.cmp](https://github.com/Saghen/blink.cmp)\n- 至少一个受支持的 AI 提供商的 API 密钥\n\n# 安装\n\n**Lazy.nvim：**\n\n```lua\nspecs = {\n    {\n        'milanglacier/minuet-ai.nvim',\n        config = function()\n            require('minuet').setup {\n                -- 在此处配置您的选项\n            }\n        end,\n    },\n    { 'nvim-lua/plenary.nvim' },\n    -- 可选，如果您使用 virtual-text 前端，则不需要 nvim-cmp。\n    { 'hrsh7th/nvim-cmp' },\n    -- 可选，如果您使用 virtual-text 前端，则不需要 blink。\n    { 'Saghen/blink.cmp' },\n}\n```\n\n**Rocks.nvim：**\n\n`Minuet` 可在 luarocks.org 上获取。只需运行 `Rocks install minuet-ai.nvim` 即可像安装其他 luarocks 包一样安装它。\n\n**使用 virtual text 进行设置：**\n\n```lua\nrequire('minuet').setup {\n    virtualtext = {\n        auto_trigger_ft = {},\n        keymap = {\n            -- 接受完整补全\n            accept = '<A-A>',\n            -- 接受一行\n            accept_line = '<A-a>',\n            -- 接受 n 行（提示输入数字）\n            -- 例如，“A-z 2 CR”将接受 2 行\n            accept_n_lines = '<A-z>',\n            -- 切换到上一个补全项，或手动调用补全\n            prev = '<A-[>',\n            -- 切换到下一个补全项，或手动调用补全\n            next = '<A-]>',\n            dismiss = '<A-e>',\n        },\n    },\n}\n```\n\n**使用 nvim-cmp 进行设置：**\n\n<details>\n\n```lua\nrequire('cmp').setup {\n    sources = {\n        {\n             -- 包含 minuet 作为源以启用自动补全\n            { name = 'minuet' },\n            -- 和您的其他来源\n        }\n    },\n    performance = {\n        -- 建议增加超时时间，因为与其他补全来源相比，LLMs 的响应速度通常较慢。如果您只需要手动补全，则不需要此设置。\n        fetching_timeout = 2000,\n    },\n}\n\n\n-- 如果你希望手动调用补全，\n-- 以下配置将 `A-y` 键绑定到手动调用配置。\nrequire('cmp').setup {\n    mapping = {\n        [\"<A-y>\"] = require('minuet').make_cmp_map()\n        -- 和您的其他键映射\n    },\n}\n```\n\n</details>\n\n**使用 blink-cmp 进行设置：**\n\n<details>\n\n```lua\nrequire('blink-cmp').setup {\n    keymap = {\n        -- 手动调用 minuet 补全。\n        ['<A-y>'] = require('minuet').make_blink_map(),\n    },\n    sources = {\n         -- 启用 minuet 进行自动补全\n        default = { 'lsp', 'path', 'buffer', 'snippets', 'minuet' },\n        -- 仅对于手动补全，从默认值中删除 'minuet'\n        providers = {\n            minuet = {\n                name = 'minuet',\n                module = 'minuet.blink',\n                score_offset = 8, -- 在建议中赋予 minuet 更高的优先级\n            },\n        },\n    },\n    -- 建议避免不必要的请求\n    completion = { trigger = { prefetch_on_insert = false } },\n}\n```\n\n</details>\n\n**LLM 提供商示例：**\n\n**Deepseek：**\n\n```lua\n-- 你可以使用 openai_fim_compatible 或 openai_compatible 提供商来使用 deepseek\nrequire('minuet').setup {\n    provider = 'openai_fim_compatible',\n    provider_options = {\n        openai_fim_compatible = {\n            api_key = 'DEEPSEEK_API_KEY',\n            name = 'deepseek',\n            optional = {\n                max_tokens = 256,\n                top_p = 0.9,\n            },\n        },\n    },\n}\n\n\n-- 或者\nrequire('minuet').setup {\n    provider = 'openai_compatible',\n    provider_options = {\n        openai_compatible = {\n            end_point = 'https://api.deepseek.com/v1/chat/completions',\n            api_key = 'DEEPSEEK_API_KEY',\n            name = 'deepseek',\n            optional = {\n                max_tokens = 256,\n                top_p = 0.9,\n            },\n        },\n    },\n}\n```\n"
  },
  {
    "path": "docs/model_context_protocol/README.md",
    "content": "\n# DeepSeek MCP Server\n\nA Model Context Protocol (MCP) server for the DeepSeek API, allowing seamless integration of DeepSeek's powerful language models with MCP-compatible applications like Claude Desktop.\n\n## *Anonymously*  use DeepSeek API  --  Only a proxy is seen on the other side \n\n<a href=\"https://glama.ai/mcp/servers/asht4rqltn\"><img width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/asht4rqltn/badge\" alt=\"DeepSeek Server MCP server\" /></a>\n<a href=\"https://smithery.ai/server/@dmontgomery40/deepseek-mcp-server\"><img alt=\"Smithery Badge\" src=\"https://smithery.ai/badge/@dmontgomery40/deepseek-mcp-server\"></a>\n\n\n[![npm version](https://img.shields.io/npm/v/deepseek-mcp-server)](https://www.npmjs.com/package/deepseek-mcp-server)\n[![npm downloads](https://img.shields.io/npm/dm/deepseek-mcp-server)](https://www.npmjs.com/package/deepseek-mcp-server)\n[![GitHub issues](https://img.shields.io/github/issues/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/issues)\n[![GitHub forks](https://img.shields.io/github/forks/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/network)\n[![GitHub stars](https://img.shields.io/github/stars/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/stargazers)\n[![GitHub license](https://img.shields.io/github/license/DMontgomery40/deepseek-mcp-server?color=blue)](https://github.com/DMontgomery40/deepseek-mcp-server/blob/main/LICENSE)\n\n## Installation\n\n### Installing via Smithery\n\nTo install DeepSeek MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@dmontgomery40/deepseek-mcp-server):\n\n```bash\nnpx -y @smithery/cli install @dmontgomery40/deepseek-mcp-server --client claude\n```\n\n### Manual Installation\n```bash\nnpm install -g deepseek-mcp-server\n```\n### Usage with Claude Desktop\n\nAdd this to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"deepseek\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"deepseek-mcp-server\"\n      ],\n      \"env\": {\n        \"DEEPSEEK_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n## Features\n\n> Note: The server intelligently handles these natural language requests by mapping them to appropriate configuration changes. You can also query the current settings and available models:\n\n- User: \"What models are available?\"\n  - Response: Shows list of available models and their capabilities via the models resource.\n- User: \"What configuration options do I have?\"\n  - Response: Lists all available configuration options via the model-config resource.\n- User: \"What is the current temperature setting?\"\n  - Response: Displays the current temperature setting.\n- User: \"Start a multi-turn conversation. With the following settings: model: 'deepseek-chat', make it not too creative, and \n   allow 8000 tokens.\"\n  - Response: *Starts a multi-turn conversation with the specified settings.*\n\n### Automatic Model Fallback if R1 is down\n\n- If the primary model (R1) is down (called `deepseek-reasoner` in the server), the server will automatically attempt to try with v3 (called `deepseek-chat` in the server) \n> Note: You can switch back and forth anytime as well, by just giving your prompt and saying \"use `deepseek-reasoner`\" or \"use `deepseek-chat`\"\n- V3 is recommended for general purpose use, while R1 is recommended for more technical and complex queries, primarily due to speed and token useage\n\n###  Resource discovery for available models and configurations:\n   * Custom model selection\n   * Temperature control (0.0 - 2.0)\n   * Max tokens limit\n   * Top P sampling (0.0 - 1.0)\n   * Presence penalty (-2.0 - 2.0)\n   * Frequency penalty (-2.0 - 2.0)\n\n## Enhanced Conversation Features\n\n**Multi-turn conversation support:**\n* Maintains complete message history and context across exchanges\n* Preserves configuration settings throughout the conversation\n* Handles complex dialogue flows and follow-up chains automatically\n\nThis feature is particularly valuable for two key use cases:\n\n1. **Training & Fine-tuning:**\n   Since DeepSeek is open source, many users are training their own versions. The multi-turn support provides properly formatted conversation data that's essential for training high-quality dialogue models.\n\n2. **Complex Interactions:**\n   For production use, this helps manage longer conversations where context is crucial:\n   * Multi-step reasoning problems\n   * Interactive troubleshooting sessions\n   * Detailed technical discussions\n   * Any scenario where context from earlier messages impacts later responses\n\nThe implementation handles all context management and message formatting behind the scenes, letting you focus on the actual interaction rather than the technical details of maintaining conversation state.\n\n\n\n\n## Testing with MCP Inspector\n\nYou can test the server locally using the MCP Inspector tool:\n\n1. Build the server:\n   ```bash\n   npm run build\n   ```\n\n2. Run the server with MCP Inspector:\n   ```bash\n   # Make sure to specify the full path to the built server\n   npx @modelcontextprotocol/inspector node ./build/index.js\n   ```\n\nThe inspector will open in your browser and connect to the server via stdio transport. You can:\n- View available tools\n- Test chat completions with different parameters\n- Debug server responses\n- Monitor server performance\n\nNote: The server uses DeepSeek's R1 model (deepseek-reasoner) by default, which provides state-of-the-art performance for reasoning and general tasks.\n\n## License\n\nMIT\n"
  },
  {
    "path": "docs/model_context_protocol/README_cn.md",
    "content": "# DeepSeek MCP 服务器\n\n这是一个适用于 DeepSeek API 的 Model Context Protocol (MCP) 服务器，可与 Claude Desktop 等兼容 MCP 的应用程序无缝集成，从而利用 DeepSeek 强大的语言模型。\n\n## *匿名* 使用 DeepSeek API —— 另一端只会看到代理\n\n<a href=\"https://glama.ai/mcp/servers/asht4rqltn\"><img width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/asht4rqltn/badge\" alt=\"DeepSeek MCP Server\" /></a>\n<a href=\"https://smithery.ai/server/@dmontgomery40/deepseek-mcp-server\"><img alt=\"Smithery Badge\" src=\"https://smithery.ai/badge/@dmontgomery40/deepseek-mcp-server\"></a>\n\n[![npm version](https://img.shields.io/npm/v/deepseek-mcp-server)](https://www.npmjs.com/package/deepseek-mcp-server)\n[![npm downloads](https://img.shields.io/npm/dm/deepseek-mcp-server)](https://www.npmjs.com/package/deepseek-mcp-server)\n[![GitHub issues](https://img.shields.io/github/issues/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/issues)\n[![GitHub forks](https://img.shields.io/github/forks/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/network)\n[![GitHub stars](https://img.shields.io/github/stars/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/stargazers)\n[![GitHub license](https://img.shields.io/github/license/DMontgomery40/deepseek-mcp-server?color=blue)](https://github.com/DMontgomery40/deepseek-mcp-server/blob/main/LICENSE)\n\n## 安装\n\n### 通过 Smithery 安装\n\n要使用 Smithery 在 Claude Desktop 上自动安装 DeepSeek MCP Server，请执行以下命令（请确保已安装 `@smithery/cli`）：\n\n`bash\nnpx -y @smithery/cli install @dmontgomery40/deepseek-mcp-server --client claude\n`\n\n### 手动安装\n\n`bash\nnpm install -g deepseek-mcp-server\n`\n\n### 在 Claude Desktop 中使用\n\n在你的 `claude_desktop_config.json` 中添加：\n\n`json\n{\n  \"mcpServers\": {\n    \"deepseek\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"deepseek-mcp-server\"\n      ],\n      \"env\": {\n        \"DEEPSEEK_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n`\n\n## 功能简介\n\n> 注意：该服务器能够根据自然语言请求智能地将其映射到相应的配置更改。你也可以查询当前设置和可用模型：\n\n- 用户：“有哪些可用的模型？”\n  - 响应：通过 models 资源列出可用模型及其功能。\n- 用户：“我有哪些配置选项？”\n  - 响应：通过 model-config 资源列出所有可用的配置选项。\n- 用户：“当前的温度（temperature）设置是多少？”\n  - 响应：显示当前温度设置。\n- 用户：“开始一个多轮对话。使用如下设置：model: 'deepseek-chat'，创意度不要太高，并且允许 8000 个 token。”\n  - 响应：使用指定设置启动一个多轮对话。\n\n### 当 R1 出现故障时自动回退到其他模型\n\n- 如果主模型（R1，服务器中称为 `deepseek-reasoner`）出现故障，服务器会自动尝试使用 v3（服务器中称为 `deepseek-chat`）\n- 你也可以随时在对话中切换，只需在对话中输入提示并说“使用 `deepseek-reasoner`”或“使用 `deepseek-chat`”\n- v3 更适用于通用场景；R1 更适用于处理较为复杂的技术性问题，主要得益于速度和 token 使用的优化\n\n### 资源发现：可用的模型和配置\n\n- 自定义模型选择\n- 温度控制（0.0 - 2.0）\n- 最大 token 限制\n- Top P 采样（0.0 - 1.0）\n- 存在惩罚（presence penalty）（-2.0 - 2.0）\n- 频率惩罚（frequency penalty）（-2.0 - 2.0）\n\n## 增强的对话功能\n\n**多轮对话支持：**\n- 在多轮交互过程中维护完整的消息历史和上下文\n- 在对话过程中保留配置设置\n- 自动处理复杂的对话逻辑和后续请求\n\n这一功能在以下两个主要场景中特别有价值：\n\n1. **训练 & 微调：**\n   - 由于 DeepSeek 是开源的，很多用户正在训练自己的版本。多轮对话支持能够提供格式正确的对话数据，这对于训练高质量对话模型至关重要。\n\n2. **复杂场景交互：**\n   - 在生产环境中，这种功能有助于管理需要保留上下文的更长对话，例如：\n     * 多步骤推理问题\n     * 交互式故障排查\n     * 详尽的技术讨论\n     * 任何需要利用早期消息上下文来影响后续响应的场景\n\n该功能在幕后自动处理所有上下文管理和消息格式，你只需关注对话本身，无需担心维护对话状态的技术细节。\n\n## 使用 MCP Inspector 进行测试\n\n你可以使用 MCP Inspector 工具在本地测试服务器：\n\n1. 构建服务器：  \n   `bash\n   npm run build\n   `\n\n2. 使用 MCP Inspector 启动服务器：  \n   `bash\n   npx @modelcontextprotocol/inspector node ./build/index.js\n   `\n\nMCP Inspector 将在你的浏览器中打开，并通过 stdio 传输连接到该服务器。你可以：\n\n- 查看可用工具\n- 使用不同参数测试对话补全\n- 调试服务器响应\n- 监控服务器性能\n\n注意：服务器默认使用 DeepSeek 的 R1 模型（`deepseek-reasoner`），它在推理和通用任务方面具有最先进的性能。\n\n## 许可证\n\nMIT\n"
  },
  {
    "path": "docs/oai-compatible-copilot/README.md",
    "content": "<img src=\"https://github.com/JohnnyZ93/oai-compatible-copilot/blob/main/assets/logo.png?raw=true\" width=\"64\" height=\"auto\" />\n\n# [OAI Compatible Provider for Copilot](https://marketplace.visualstudio.com/items?itemName=johnny-zhao.oai-compatible-copilot)\n\nAn open-source VS Code extension to use openai compatible inference providers in GitHub Copilot.\n\n[Source Code](https://github.com/JohnnyZ93/oai-compatible-copilot)\n\n[VS Code Chat Provider API](https://code.visualstudio.com/api/extension-guides/ai/language-model-chat-provider)\n\n## ✨ Features\n- Supports almost all OpenAI-compatible providers, such as ModelScope, DeepSeek...\n- Supports vision models.\n- Offers additional configuration options for chat requests.\n- Supports control model thinking and reasoning content show in chat interface.\n- Supports configuring models from multiple providers simultaneously, automatically managing API keys without switch them repeatedly.\n- Supports defining multiple configurations for the same model ID with different settings (e.g. thinking enable/disable for GLM-4.6).\n\n## Requirements\n- VS Code 1.104.0 or higher.\n- DeepSeek API key.\n\n## ⚡ Integrate with DeepSeek API\n1. Install the OAI Compatible Provider for Copilot extension [here](https://marketplace.visualstudio.com/items?itemName=johnny-zhao.oai-compatible-copilot).\n2. Open VS Code Settings and configure `oaicopilot.baseUrl` and `oaicopilot.models`.\n3. Open Github Copilot Chat interface.\n4. Click the model picker and select \"Manage Models...\".\n5. Choose \"OAI Compatible\" provider.\n6. Enter your API key — it will be saved locally.\n7. Select the DeepSeek models by your configuration.\n\n```json\n\"oaicopilot.baseUrl\": \"https://api.deepseek.com/v1\",\n\"oaicopilot.models\": [\n  {\n      \"id\": \"deepseek-chat\",\n      \"owned_by\": \"deepseek\",\n      \"context_length\": 128000,\n      \"max_tokens\": 8000\n  },\n  {\n      \"id\": \"deepseek-reasoner\",\n      \"owned_by\": \"deepseek\",\n      \"context_length\": 128000,\n      \"max_tokens\": 16000\n  }\n]\n```\n"
  },
  {
    "path": "docs/oai-compatible-copilot/README_cn.md",
    "content": "<img src=\"https://github.com/JohnnyZ93/oai-compatible-copilot/blob/main/assets/logo.png?raw=true\" width=\"64\" height=\"auto\" />\r\n\r\n# [OAI Compatible Provider for Copilot](https://marketplace.visualstudio.com/items?itemName=johnny-zhao.oai-compatible-copilot)\r\n\r\n开源的 VS Code 扩展，可在 GitHub Copilot 中使用 OpenAI 兼容的推理提供商。\r\n\r\n[源代码](https://github.com/JohnnyZ93/oai-compatible-copilot)\r\n\r\n[VS Code Chat Provider API](https://code.visualstudio.com/api/extension-guides/ai/language-model-chat-provider)\r\n\r\n## ✨ 特性\r\n- 支持几乎所有 OpenAI 兼容的提供商，如 ModelScope、DeepSeek...\r\n- 支持视觉模型\r\n- 为聊天请求提供额外的配置选项\r\n- 支持在聊天界面中控制模型的思考和推理内容显示\r\n- 支持同时配置来自多个提供商的模型，自动管理 API 密钥而无需重复切换\r\n- 支持为同一模型 ID 定义具有不同设置的多个配置（例如 GLM-4.6 的思考启用/禁用）\r\n\r\n## 要求\r\n- VS Code 1.104.0 或更高版本\r\n- DeepSeek API 密钥\r\n\r\n## ⚡ 与 DeepSeek API 集成\r\n1. 安装 OAI Compatible Provider for Copilot 扩展 [此处](https://marketplace.visualstudio.com/items?itemName=johnny-zhao.oai-compatible-copilot)\r\n2. 打开 VS Code 设置并配置 `oaicopilot.baseUrl` 和 `oaicopilot.models`\r\n3. 打开 GitHub Copilot Chat 界面\r\n4. 点击模型选择器并选择 \"Manage Models...\"\r\n5. 选择 \"OAI Compatible\" 提供商\r\n6. 输入您的 API 密钥 — 它将保存在本地\r\n7. 选择您配置的 DeepSeek 模型\r\n\r\n```json\r\n\"oaicopilot.baseUrl\": \"https://api.deepseek.com/v1\",\r\n\"oaicopilot.models\": [\r\n  {\r\n      \"id\": \"deepseek-chat\",\r\n      \"owned_by\": \"deepseek\",\r\n      \"context_length\": 128000,\r\n      \"max_tokens\": 8000\r\n  },\r\n  {\r\n      \"id\": \"deepseek-reasoner\",\r\n      \"owned_by\": \"deepseek\",\r\n      \"context_length\": 128000,\r\n      \"max_tokens\": 16000\r\n  }\r\n]\r\n```\r\n"
  },
  {
    "path": "docs/pal/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1ac9791b-87f7-41d9-9282-a70698344e1d\" width=\"64\" height=\"auto\" /> \n\n# [Pal - AI Chat Client](https://apps.apple.com/us/app/pal-ai-chat-client/id6447545085)\n\nPal is a customized chat playground on iOS.\n\n## UI\n\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/4c514622-0073-43b0-86df-3f4b5d3c3514)\n\n\n## Integrate with Deepseek API\n\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/68ec290d-bc5f-4844-a3bf-29d3f39bf9ba)\n\n"
  },
  {
    "path": "docs/pal/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/1ac9791b-87f7-41d9-9282-a70698344e1d\" width=\"64\" height=\"auto\" /> \r\n\r\n# [Pal - AI Chat Client](https://apps.apple.com/us/app/pal-ai-chat-client/id6447545085)\r\n\r\n支持用户定制的聊天app，仅限于ios系统使用.\r\n\r\n## UI\r\n\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/4c514622-0073-43b0-86df-3f4b5d3c3514)\r\n\r\n\r\n## 配置 deepseek API\r\n\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/68ec290d-bc5f-4844-a3bf-29d3f39bf9ba)\r\n"
  },
  {
    "path": "docs/promptfoo/README.md",
    "content": "# promptfoo\n\n[promptfoo](https://promptfoo.dev) is an open-source framework for testing and evaluating LLM outputs. It helps you compare DeepSeek models with other LLMs (like o1, GPT-4o, Claude 3.5, Llama3.3, and Gemini) and test LLMs and LLM applications for security vulnerabilities. You can:\n\n- Run side-by-side comparisons between models\n- Check output quality and consistency\n- Generate test reports\n\n## Setup\n\n1. Install promptfoo:\n\n```bash\nnpm install -g promptfoo\n# or\nbrew install promptfoo\n```\n\n2. Configure API keys:\n\n```bash\nexport DEEPSEEK_API_KEY=your_api_key\n# Add other API keys as needed\n```\n\n## Quick Start\n\nCreate a configuration file `promptfooconfig.yaml`:\n\n```yaml\nproviders:\n  - deepseek:deepseek-reasoner # DeepSeek-R1\n  - openai:o1\n\nprompts:\n  - 'Solve this step by step: {{math_problem}}'\n\ntests:\n  - vars:\n      math_problem: 'What is the derivative of x^3 + 2x with respect to x?'\n    assert:\n      - type: contains\n        value: '3x^2' # Check for correct answer\n      - type: llm-rubric\n        value: 'Response shows clear steps'\n      - type: cost\n        threshold: 0.05 # Maximum cost per request\n```\n\nRun tests:\n\n```bash\npromptfoo eval\n```\n\nView results in your browser:\n\n```bash\npromptfoo view\n```\n\n## Example Project\n\nCheck out our [example](https://github.com/promptfoo/promptfoo/tree/main/examples/deepseek-r1-vs-openai-o1) that compares r1 and o1 on MMLU.\n\n## Resources\n\n- [Documentation](https://promptfoo.dev/docs/providers/deepseek)\n- [GitHub Repository](https://github.com/promptfoo/promptfoo)\n- [Community Discord](https://discord.gg/promptfoo)\n"
  },
  {
    "path": "docs/promptfoo/README_cn.md",
    "content": "# promptfoo\n\n[promptfoo](https://promptfoo.dev) 是一个开源框架，用于测试和评估 LLM 输出。它可以帮助您将 DeepSeek 模型与其他 LLM（如 o1、GPT-4o、Claude 3.5、Llama 3.3 和 Gemini）进行比较，并测试 LLM 及其应用的安全漏洞。您可以：\n\n- 对不同模型进行并排比较\n- 检查输出质量和一致性\n- 生成测试报告\n\n## 安装设置\n\n1. 安装 promptfoo：\n\n```bash\nnpm install -g promptfoo\n# 或者使用 brew\nbrew install promptfoo\n```\n\n2. 配置 API 密钥：\n\n```bash\nexport DEEPSEEK_API_KEY=your_api_key\n# 根据需要添加其他 API 密钥\n```\n\n## 快速开始\n\n创建配置文件 `promptfooconfig.yaml`：\n\n```yaml\nproviders:\n  - deepseek:deepseek-reasoner # DeepSeek-R1\n  - openai:o1\n\nprompts:\n  - '请逐步解决这个问题：{{math_problem}}'\n\ntests:\n  - vars:\n      math_problem: '求 x^3 + 2x 对 x 的导数'\n    assert:\n      - type: contains\n        value: '3x^2' # 检查正确答案\n      - type: llm-rubric\n        value: '回答需要展示清晰的步骤'\n      - type: cost\n        threshold: 0.05 # 每次请求的最大成本\n```\n\n运行测试：\n\n```bash\npromptfoo eval\n```\n\n在浏览器中查看结果：\n\n```bash\npromptfoo view\n```\n\n## 示例项目\n\n查看我们的[示例](https://github.com/promptfoo/promptfoo/tree/main/examples/deepseek-r1-vs-openai-o1)，展示了 r1 和 o1 在 MMLU 上的比较。\n\n## 资源\n\n- [文档](https://promptfoo.dev/docs/providers/deepseek)\n- [GitHub 仓库](https://github.com/promptfoo/promptfoo)\n- [社区 Discord](https://discord.gg/promptfoo)\n"
  },
  {
    "path": "docs/ragflow/README.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372\" alt=\"Icon\" width=\"64\" height=\"auto\" />\n\n# [RAGFlow](https://github.com/infiniflow/ragflow)\n\nAn open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data.\n\n## UI\n\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/a69ce143-931c-4a75-b129-f6a1ddd114a2)\n\n\n## Integrate with Deepseek API\n\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/49dc1916-c3c2-470a-a3ea-b5877de52958)\n"
  },
  {
    "path": "docs/ragflow/README_cn.md",
    "content": "<img src=\"https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372\" alt=\"Icon\" width=\"64\" height=\"auto\" />\r\n\r\n# [RAGFlow](https://github.com/infiniflow/ragflow)\r\n\r\n一款基于深度文档理解构建的开源 RAG（Retrieval-Augmented Generation）引擎。RAGFlow 可以为各种规模的企业及个人提供一套精简的 RAG 工作流程，结合大语言模型（LLM）针对用户各类不同的复杂格式数据提供可靠的问答以及有理有据的引用。\r\n\r\n## UI\r\n\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/a69ce143-931c-4a75-b129-f6a1ddd114a2)\r\n\r\n\r\n## 配置 Deepseek API\r\n\r\n![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/514b87e3-2eef-4dd2-b21d-88bb3f381573)\r\n"
  },
  {
    "path": "docs/raycast/README.md",
    "content": "<img width=\"1024\" src=\"assets/og-image.png\" alt=\"ray.so\">\n\n<!-- TEXT_SECTION:header:END -->\n\n# Raycast Extension - Deepseek Quick Actions\n\nRaycast is a productivity tool that allows you to control your tools with a few keystrokes. It's far more than an app launcher, it's a way to interact with your tools and data in a more efficient way. With Raycast, you can run scripts, open files, and even interact with your favorite apps without leaving your keyboard.\n\n[Deepseek Quick Actions](https://www.raycast.com/ViGeng/deepseeker?via=ViGeng) is a Raycast extension that allows you to interact with the Deepseek API directly from Raycast. You can perform common tasks like `summarize`, `rephrase`, `fix writing`, so on.\n\n\n# Features\n- [x] 🚀 Results Stream in real time\n- [x] ⌘ Supports custom keybinding for each action\n- [x] 📄 Custom prompt for each action\n- [x] Set token price in settings\n\n# UI\n![alt text](assets/deepseeker-1.png)\n![alt text](assets/deepseeker-2.png)\n![alt text](assets/deepseeker-3.png)\n![alt text](assets/deepseeker-4.png)\n![alt text](assets/deepseeker-5.png)\n"
  },
  {
    "path": "docs/raycast/README_cn.md",
    "content": "<img width=\"1024\" src=\"assets/og-image.png\" alt=\"ray.so\">\n\n<!-- TEXT_SECTION:header:END -->\n\n# Raycast Extension - Deepseek Quick Actions\n\nRaycast 是一款效率工具，允许你只需敲击几下按键就能控制你的工具。它远不止是一个应用程序启动器，它是一种更高效地与你的工具和数据交互的方式。使用 Raycast，你可以运行脚本、打开文件，甚至可以在不离开键盘的情况下与你最喜欢的应用程序进行交互。\n\n[Deepseek 快速操作](https://www.raycast.com/ViGeng/deepseeker?via=ViGeng) 是一个 Raycast 扩展，允许你直接从 Raycast 与 Deepseek API 交互。你可以执行诸如 `summarize`、`rephrase`、`fix writing` 等常见任务。\n\n\n# Features\n- [x] 🚀 实时结果流\n- [x] ⌘ 支持每个动作的自定义键绑定\n- [x] 📄 每个动作的自定义提示\n- [x] 💰 在设置中设置Token价格\n\n# UI\n![alt text](assets/deepseeker-1.png)\n![alt text](assets/deepseeker-2.png)\n![alt text](assets/deepseeker-3.png)\n![alt text](assets/deepseeker-4.png)\n![alt text](assets/deepseeker-5.png)\n"
  },
  {
    "path": "docs/refinereader/README.md",
    "content": "# Refine Reader （Chrome Extension）\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-128.png\" alt=\"Refine Reader Logo\" width=\"128\" height=\"128\">\n</p>\n\n<p align=\"center\">\n  An AI-powered intelligent reading assistant dedicated to helping users quickly understand and extract article essentials, with interactive reading support.\n</p>\n\n## ✨ Key Features\n\n- 🤖 **AI Smart Summary**: One-click generation of core viewpoints, key arguments, and crucial conclusions\n- 🌏 **Multi-language Support**: Supports Simplified Chinese, Traditional Chinese, English, Japanese, and Korean\n- 🎨 **Theme Switching**: Multiple elegant themes including Chinese Ink and Spring Vibes\n- 💬 **Reading Interaction**: Supports multi-turn dialogue based on article content\n- ⚡️ **Quick Inquiry**: Built-in question templates for instant professional insights\n\n## 🛠️ Supported AI Models\n\n- OpenAI (GPT-4/3.5)\n- Tongyi Qianwen\n- DeepSeek\n- Claude\n- Ollama (Local Deployment)\n- More integrations coming soon\n\n## 🚀 Quick Start\n\n1. Install Refine Reader extension from Chrome Web Store\n2. Click the extension icon to enter settings and configure AI model\n3. Open any article page and click \"AI Smart Summary\"\n4. Enjoy the intelligent reading experience!\n\n## 🎯 Use Cases\n\n- 📚 Quickly grasp key points of long articles\n- 📝 Generate professional article analysis\n- 🗣️ Obtain multi-perspective interpretations\n- 📢 One-click content sharing generation\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-preview-1.png\" alt=\"Refine Reader Preview\" width=\"800\">\n</p>\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-preview-2.png\" alt=\"Refine Reader Preview\" width=\"800\">\n</p>\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-preview-3.jpg\" alt=\"Refine Reader Preview\" width=\"800\">\n</p>\n\n## 🔒 Privacy Protection\n\n- All configuration information stored locally only\n- API keys securely encrypted\n- No collection of personal user information\n\n## 👨‍💻 Developer\n\n- GitHub: [wzfukui/refinereader](https://github.com/wzfukui/refinereader)\n- Website: [https://refinereader.cuihuaer.com](https://refinereader.cuihuaer.com)\n"
  },
  {
    "path": "docs/refinereader/README_cn.md",
    "content": "# 萃花阅读 (Refine Reader, Chrome扩展)\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-128.png\" alt=\"萃花阅读 Logo\" width=\"128\" height=\"128\">\n</p>\n\n<p align=\"center\">\n  一款基于 AI 的智能阅读助手，致力于帮助用户快速理解和提炼文章精华，支持阅读互动。\n</p>\n\n\n## ✨ 主要功能\n\n- 🤖 **AI 智能总结**：一键生成文章核心观点、重要论据和关键结论\n- 🌏 **多语言支持**：支持中文简体、中文繁体、英文、日文、韩文\n- 🎨 **主题切换**：内置水墨中文、春意盎然等多种精美主题\n- 💬 **阅读互动**：支持基于文章内容的多轮对话\n- ⚡️ **快速提问**：内置多种提问模板，一键生成专业见解\n\n## 🛠️ 支持的 AI 模型\n\n- OpenAI (GPT-4/3.5)\n- 通义千问\n- DeepSeek\n- Claude\n- Ollama (本地部署)\n- 更多集成中\n\n## 🚀 快速开始\n\n1. 在 Chrome 商店安装萃花阅读扩展\n2. 点击扩展图标，进入设置页面配置 AI 模型\n3. 打开任意文章页面，点击\"AI智能总结\"\n4. 享受智能阅读体验！\n\n## 🎯 使用场景\n\n- 📚 快速掌握长文章重点\n- 📝 生成专业的文章分析\n- 🗣️ 获取多角度的解读见解\n- 📢 一键生成分享内容\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-preview-1.png\" alt=\"萃花阅读预览\" width=\"800\">\n</p>\n\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-preview-2.jpg\" alt=\"萃花阅读预览\" width=\"800\">\n</p>\n\n<p align=\"center\">\n  <img src=\"assets/refinereader-preview-3.jpg\" alt=\"萃花阅读预览\" width=\"800\">\n</p>\n\n## 🔒 隐私保护\n\n- 所有配置信息仅存储在本地\n- API 密钥安全加密存储\n- 不收集任何用户个人信息\n\n\n## 👨‍💻 开发者\n\n- GitHub：[wzfukui/refinereader](https://github.com/wzfukui/refinereader)\n- 网站：[https://refinereader.cuihuaer.com](https://refinereader.cuihuaer.com)\n\n"
  },
  {
    "path": "docs/relingo/README.md",
    "content": "<img src=\"https://relingo.net/assets/images/relingo-logo.png\" width=\"64\" height=\"auto\" /> \n\n# [Relingo Ext](https://relingo.net/)\n\nBuild and master vocabulary while you browse website and watch youtube!\n\n## UI\n\n![Image](https://relingo.net/assets/images/step3.png)\n\n## Integrate with Deepseek API\n\n![Image](https://github.com/user-attachments/assets/277a570d-e77e-4eac-b468-0a3b9da04fc6)\n\n"
  },
  {
    "path": "docs/relingo/README_cn.md",
    "content": "<img src=\"https://relingo.net/assets/images/relingo-logo.png\" width=\"64\" height=\"auto\" /> \r\n\r\n# [Relingo 浏览器扩展](https://relingo.net/)\r\n\r\n在浏览网页和观看YouTube视频的同时，构建并掌握词汇量！\r\n\r\n## UI\r\n\r\n![Image](https://relingo.net/assets/images/step3.png)\r\n\r\n## Integrate with Deepseek API\r\n\r\n![Image](https://github.com/user-attachments/assets/277a570d-e77e-4eac-b468-0a3b9da04fc6)\r\n\r\n"
  },
  {
    "path": "docs/rss_translator/README.md",
    "content": "<img src=\"https://raw.githubusercontent.com/rss-translator/RSS-Translator/main/core/static/favicon.ico\" width=\"64\" height=\"auto\" /> \n\n# [RSS Translator](https://rsstranslator.com/en/)\n\nRSS Translator is an open source, self-hosted application. Translates title or content, provides AI summaries and generates a new translated feed\n\n## UI\n\n![UI](assets/ui.png)\n\n\n## Integrate with Deepseek API\n\n![add_translator](assets/add_translator.png)\n![add_openai](assets/add_openai.png)\n"
  },
  {
    "path": "docs/rss_translator/README_cn.md",
    "content": "<img src=\"https://raw.githubusercontent.com/rss-translator/RSS-Translator/main/core/static/favicon.ico\" width=\"64\" height=\"auto\" /> \n\n# [RSS翻译器](https://rsstranslator.com/)\n\n一个开源、简洁、可自部署的RSS翻译器，可翻译标题/内容、AI总结，并输出翻译后的RSS订阅链接。\n\n## UI\n\n![UI](assets/ui.png)\n\n## 配置 deepseek API\n\n![add_translator](assets/add_translator.png)\n![add_openai](assets/add_openai.png)"
  },
  {
    "path": "docs/ruzhiai_note/README.md",
    "content": "<div align=\"center\">\n<img src=\"./assets/play_store_512.png\" width=\"64\" height=\"auto\" />\n</div>\n\n# RuZhi AI Notes\n\nRuZhi AI Notes is an intelligent AI knowledge management tool dedicated to providing users with one-stop knowledge management and application services, including AI search and exploration, AI results to notes conversion, note management and organization, knowledge presentation and sharing, etc.\n\n## Core Advantages\n\n### 1. Powerful AI Model Support\n- Integrated with DeepSeek thinking model\n- According to user feedback, compared to similar products, our model:\n  - More stable\n  - Higher output quality\n  - Can integrate with enterprise internal knowledge bases\n\n<img src=\"./assets/deepseek_used.jpg\" width=\"100%\" height=\"auto\" />\n\n### 2. Convenient Content Management\n- One-click save AI conversation content to notes\n- Support for various export formats:\n  - Markdown\n  - Word documents\n  - PDF files\n  - PPT presentations\n  - Resume templates\n  and more formats\n\n### 3. Upcoming Features\n- Task management list\n- To-do tracking\n- Calendar management\n- More intelligent features\n- Multi-platform clients\n\n## Usage Guide\n\n#### Method 1: Search\n1. Search for \"RuZhi AI Notes\" in search engines\n2. Register\n\n#### Method 2: Direct Link Access\n1. Visit our official link https://ruzhiai.perfcloud.cn/\n2. Complete the registration process\n   - The system will automatically create an application for you after registration\n   - You can then start using all features\n"
  },
  {
    "path": "docs/ruzhiai_note/README_cn.md",
    "content": "<div align=\"center\">\n<img src=\"./assets/play_store_512.png\" width=\"64\" height=\"auto\" />\n</div>\n\n# 如知AI笔记\n\n如知AI笔记是一款智能化的AI知识管理工具，致力于为用户提供一站式的知识管理和应用服务，包括AI搜索探索、AI结果转笔记、笔记管理与整理、 知识演示与分享等。\n\n## 核心优势\n\n### 1. 强大的AI模型支持\n- 集成了DeepSeek深度思考模型\n- 用户反馈显示，相较同类产品，我们的模型：\n  - 更加稳定\n  - 输出质量更高\n  - 可以融合企业内部知识库\n\n<img src=\"./assets/deepseek_used.jpg\" width=\"100%\" height=\"auto\" />\n\n\n### 2. 便捷的内容管理\n- 一键保存AI对话内容到笔记\n- 多样化的导出格式支持：\n  - Markdown\n  - Word文档\n  - PDF文件\n  - PPT演示文稿\n  - 简历模板\n  等多种格式\n\n### 3. 即将推出的功能\n- 任务管理清单\n- 待办事项追踪\n- 日历管理\n- 更多智能化功能\n- 多端客户端\n\n## 使用指南\n\n\n#### 方式一：搜索\n1. 在搜索引擎中搜索\"如知AI笔记\"\n2. 注册\n\n#### 方式二：直接访问链接\n1. 访问我们的官方链接 https://ruzhiai.perfcloud.cn/\n2. 完成注册流程\n   - 注册后系统会自动为您创建应用\n   - 即可开始使用所有功能\n"
  },
  {
    "path": "docs/siri_deepseek_shortcut/README.md",
    "content": "\n# [深度求索 (shortcut)](https://www.icloud.com/shortcuts/b75899492ead45ef9a47cfce89334bf0)\n\nA shortcut to enhance Siri's capabilities with the DeepSeek API.\n\n## UI\n\n![siri3](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/155953822/c76a1a87-3f0e-49c2-a2a1-2685289ab022)\n\n\n\n## Integrate with Deepseek API\n## After adding the shortcut to the 'Shortcuts' app,  fill in your own DeepSeek API key.Then you can use it in text or Siri.\n\n![siri1](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/155953822/18bfbf79-e208-4366-8bea-6499096dd819)\n\n![siri2](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/155953822/6d1cca80-de94-4ae4-ae88-c5aa23b8b1fc)\n"
  },
  {
    "path": "docs/siri_deepseek_shortcut/README_cn.md",
    "content": "\r\n# [深度求索 (快捷指令)](https://www.icloud.com/shortcuts/b75899492ead45ef9a47cfce89334bf0)\r\n\r\n使用DeepSeek API 来增强 Siri 能力的快捷指令.\r\n\r\n## UI\r\n\r\n![siri3](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/155953822/657bf7f8-3a2b-4757-9acc-7b6548574a0b)\r\n\r\n\r\n\r\n\r\n## 配置 deepseek API\r\n## 添加该快捷指令后，填入你自己的DeepSeek API Key即可。使用时可以用文本输入，也可以使用Siri唤醒后语音输入。\r\n![siri1](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/155953822/bfc74639-e85b-4cba-89dc-1a286d17307d)\r\n\r\n![siri2](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/155953822/0e483340-858e-424e-9c46-386b6464bfa3)\r\n\r\n\r\n"
  },
  {
    "path": "docs/solana-agent-kit/README.md",
    "content": "# README\n\n<img src=\"assets/sendai-logo.png\" width=\"64\" height=\"auto\" alt=\"logo\">\n\n---\n\nAn open-source toolkit for connecting AI agents to Solana protocols. Now, any agent, using any model can autonomously perform 60+ Solana actions:\n‍\n\n## STEP1.\n\nApply a token from [deepseek open platform](https://platform.deepseek.com/)\n\n## STEP 2\n\nIntialize the DeepSeek LLM\n\n```\nimport { ChatDeepSeek } from \"@langchain/deepseek\";\n\nconst deepseek = new ChatDeepSeek({\n  model: \"deepseek-chat\",\n  temperature: 0,\n});\n```\n‍\n## STEP 3\n\nIntialize the Solana Agent Kit with DeepSeek\n\n```typescript\nconst solanaAgent = new SolanaAgentKit(\n  process.env.SOLANA_PRIVATE_KEY!,\n  process.env.RPC_URL!,\n  {\n    OPENAI_API_KEY: process.env.OPENAI_API_KEY!,\n    HELIUS_API_KEY: process.env.HELIUS_API_KEY!,\n    PERPLEXITY_API_KEY: process.env.PERPLEXITY_API_KEY!,\n  },\n);\n\nconst tools = createSolanaTools(solanaAgent);\n\nconst agent = createReactAgent({\n  llm: deepseek,\n  tools,\n  checkpointSaver: memory,\n  messageModifier: `\n    You are a helpful agent that can interact onchain using the Solana Agent Kit. You are\n    empowered to interact onchain using your tools. If you ever need funds, you can request them from the\n    faucet. If not, you can provide your wallet details and request funds from the user. If there is a 5XX\n    (internal) HTTP error code, ask the user to try again later. If someone asks you to do something you\n    can't do with your currently available tools, you must say so, and encourage them to implement it\n    themselves using the Solana Agent Kit, recommend they go to https://www.solanaagentkit.xyz for more information. Be\n    concise and helpful with your responses. Refrain from restating your tools' descriptions unless it is explicitly requested.\n  `,\n});\n\nconst stream = await agent.stream(\n  { messages: [new HumanMessage(userInput)] },\n  config,\n);\n```\n\nMore guides can be found in the [Solana Agent Kit](https://docs.solanaagentkit.xyz/v0/introduction)\n\n‍"
  },
  {
    "path": "docs/stranslate/README.md",
    "content": "<img src=\"./assets/stranslate.svg\" width=\"64\" height=\"auto\" /> \n\n# [`STranslate`](https://stranslate.zggsong.com/)\n\nSTranslate is a translation and OCR tool that is ready to use on the go.\n\n## Translation\n\nSupports multiple translation languages and various translation methods such as input, text selection, screenshot, clipboard monitoring, and mouse text selection. It also allows displaying multiple service translation results simultaneously for easy comparison.\n\n## OCR\n\nSupports fully offline OCR for Chinese, English, Japanese, and Korean, based on PaddleOCR, with excellent performance and quick response. It supports screenshot, clipboard, and file OCR, as well as silent OCR. Additionally, it supports OCR services from WeChat, Baidu, Tencent, OpenAI, and Google.\n\n## Services\n\nSupports integration with over ten translation services including DeepSeek, OpenAI, Gemini, ChatGLM, Baidu, Microsoft, Tencent, Youdao, and Alibaba. It also offers free API options. Built-in services like Microsoft, Yandex, Google, and Kingsoft PowerWord are ready to use out of the box.\n\n## Features\n\nSupports back-translation, global TTS, writing (directly translating and replacing selected content), custom prompts, QR code recognition, external calls, and more.\n\n## Main Interface\n\n![main_ui](./assets/main.png)\n\n## Configuration\n\n![settings_1](./assets/settings_1.png)\n\n![settings_2](./assets/settings_2.png)"
  },
  {
    "path": "docs/stranslate/README_cn.md",
    "content": "<img src=\"./assets/stranslate.svg\" width=\"64\" height=\"auto\" /> \n\n# [`STranslate`](https://stranslate.zggsong.com/)\n\nSTranslate 是一款即用即走的翻译、OCR工具\n\n## 翻译\n\n支持多种翻译语言，支持输入、划词、截图、监听剪贴板、监听鼠标划词等多种翻译方式，支持同时显示多个服务翻译结果，方便比较翻译结果\n\n## OCR\n\n支持中英日韩完全离线OCR，基于 PaddleOCR，效果优秀反应迅速，支持截图、剪贴板、文件OCR，支持静默OCR，同时支持微信、百度、腾讯、OpenAI、Google等OCR\n\n## 服务\n\n支持DeepSeek、OpenAI、Gemini、ChatGLM、百度、微软、腾讯、有道、阿里等十多家翻译服务接入；同时还提供免费API可供选择；内置微软、Yandex、Google、金山词霸等内置服务可做到开箱即用\n\n## 特色\n\n支持回译、全局TTS、写作(选中后直接翻译替换内容)、自定义Prompt、二维码识别、外部调用等等功能\n\n## 主界面\n\n![main_ui](./assets/main.png)\n\n## 配置\n\n![settings_1](./assets/settings_1.png)\n\n![settings_2](./assets/settings_2.png)"
  },
  {
    "path": "docs/superagentx/README.md",
    "content": "# `SuperAgentX`\n\n> 🤖 SuperAgentX: A lightweight autonomous true multi-agent framework with AGI capabilities.\n\n**SuperAgentX Source Code**: [https://github.com/superagentxai/superagentx](https://github.com/superagentxai/superagentx)\n\n**DeepSeek AI Agent Example**: [https://github.com/superagentxai/superagentx/blob/master/tests/llm/test_deepseek_client.py](https://github.com/superagentxai/superagentx/blob/master/tests/llm/test_deepseek_client.py)\n\n**Documentation** : [https://docs.superagentx.ai/](https://docs.superagentx.ai/)\n\nThe SuperAgentX framework integrates DeepSeek as its LLM service provider, enhancing the multi-agent's reasoning and decision-making capabilities.\n\n## 🤖 Introduction\n\n`SuperAgentX` SuperAgentX is an advanced agentic AI framework designed to accelerate the development of Artificial General Intelligence (AGI). It provides a powerful, modular, and flexible platform for building autonomous AI agents capable of executing complex tasks with minimal human intervention.\n\n![SuperAgentX Diagram](https://raw.githubusercontent.com/superagentxai/superagentX/refs/heads/master/docs/images/architecture.png)\n\n### ✨ Key Features\n\n🚀 Open-Source Framework: A lightweight, open-source AI framework built for multi-agent applications with Artificial General Intelligence (AGI) capabilities.\n\n🎯 Goal-Oriented Multi-Agents: This technology enables the creation of agents with retry mechanisms to achieve set goals. Communication between agents is Parallel, Sequential, or hybrid.\n\n🏖️ Easy Deployment: Offers WebSocket, RESTful API, and IO console interfaces for rapid setup of agent-based AI solutions.\n\n♨️ Streamlined Architecture: Enterprise-ready scalable and pluggable architecture. No major dependencies; built independently!\n\n📚 Contextual Memory: Uses SQL + Vector databases to store and retrieve user-specific context effectively.\n\n🧠 Flexible LLM Configuration: Supports simple configuration options of various Gen AI models.\n\n🤝🏻 Extendable Handlers: Allows integration with diverse APIs, databases, data warehouses, data lakes, IoT streams, and more, making them accessible for function-calling features.\n"
  },
  {
    "path": "docs/tomemo/README.md",
    "content": "<img src=\"https://tomemo.top/images/logo.png\" width=\"64\" height=\"auto\" />\n\n# [ToMemo](https://apps.apple.com/cn/app/tomemo/id1610843304)\n\nToMemo is a phrasebook + clipboard history + keyboard iOS app with integrated AI macromodeling for quick output use in the keyboard.\n\n## UI\n\n![image](assets/ui.jpg)\n\n![image](assets/ui-keyboard.jpg)\n\n## Integrate with Deepseek API\n\n- Go to \"Settings-Extensions-AI Services-AI Providers\", click \"Add\" in the top right corner, and select \"DeepSeek\" in the **Provider** field.\n- Enter your API Key in the **API Key** field.\n- Click the \"Test\" button to verify if the input is valid.\n- Click \"Load Models\" to select the model you want to use\n- Turn on \"Enable\" and click \"Save\"\n\n![image](assets/app-provider.png)\n\n## Use\n\n- Go to \"Settings-Extensions-AI Services\"\n- Click \"AI Assistant\" to enter the AI Assistant page\n- Add an AI Assistant in the top right corner, you can select \"Deepseek\" in the models\n- Start chatting with Deepseek\n\n![image](assets/use-deepseek.png)\n"
  },
  {
    "path": "docs/tomemo/README_cn.md",
    "content": "<img src=\"https://tomemo.top/images/logo.png\" width=\"64\" height=\"auto\" />\n\n# [ToMemo](https://apps.apple.com/cn/app/tomemo/id1610843304)\n\nToMemo 是一款短语合集 + 剪切板历史 + 键盘输出的 iOS 应用，集成了 AI 大模型，可以在键盘中快速输出使用。\n\n## UI\n\n![image](assets/ui.jpg)\n\n![image](assets/ui-keyboard.jpg)\n\n## Integrate with Deepseek API\n\n- 进入「设置-扩展-AI 服务-AI 供应商」，点击右上角「添加」，在**供应商**中选择「DeepSeek」。\n- 在**API Key**中输入你的 API Key。\n- 点击「测试」按钮，测试填入是否可用。\n- 点击「加载模型」，选择需要使用的模型\n- 打开「启用」后，点击「保存」\n\n![image](assets/app-provider.png)\n\n## Use\n\n- 进入「设置-扩展-AI 服务」，\n- 点击「AI 助手」进入 AI 助手页面，\n- 右上角添加 AI 助手，可以在模型中选择「深度求索」\n- 开始和 Deepseek 聊天\n\n![image](assets/use-deepseek.png)\n"
  },
  {
    "path": "docs/translate.js/README.md",
    "content": "<h1 align=\"center\">\n    translate.js\n</h1>\n<h4 align=\"center\">\n    It is an AI i18n tool designed for front-end developers. With just two lines of JavaScript code, it can achieve fully automatic translation of HTML.  <br/>\n    Leave it to the AI. There is no need to modify the page, no language configuration file is required, no API Key is needed, and it is SEO-friendly! \n</h4> \n\n![image](assets/html_demo.gif)  \n\n\n# Usage method\n### 1. Deploy the text translation API\nFirst, deploy the text translation open interface. It supports batch translation of multiple texts at once and has a built-in multi-layer caching system, which minimizes the time-consuming process of AI translation. This enables users to achieve instant and delay-free translation when using it. \n\n##### 1.1 Server specifications\nIt can run perfectly with the following server configuration: 1 core, 1GB of memory, a 20GB system disk, a bandwidth of 1MB, and the operating system being CentOS 7.4 (any version from 7.0 to 7.9 is acceptable).  \n\n##### 1.2 Install\n````\nwget https://gitee.com/mail_osc/translate/raw/master/deploy/install_translate.service.sh -O install.sh && chmod -R 777 install.sh && sh ./install.sh\n````\n\n##### 1.3 Configure DeepSeek parameters\n\nEdit application.properties ，Edit command：\n````\nvi /mnt/tomcat8/webapps/ROOT/WEB-INF/classes/application.properties\n````\nThen append a few lines of configuration at the very end:  \n````\n# The request URL of the large model interface. For example, the following is the request URL of Huawei DeepSeek. Additionally, the request URL of GiteeAI is https://ai.gitee.com/v1/chat/completions , You can obtain and fill in the information for other platforms by yourself. \ntranslate.service.deepSeek.url=https://infer-modelarts-cn-southwest-2.modelarts-infer.com/v1/infers/fd53915b-8935-48fe-be70-449d76c0fc87/v1/chat/completions\n# Access token\ntranslate.service.deepSeek.key=QM8jrVl98lTluLhzCaO4i9PFv-caRk6U7kDL-H6CIyApytMG69jO33aasO1GnduQak8fGI7dtpmbsM98Qh3ywA\n# Which model to use? Here, it is advisable to use DeepSeek-V3 by default, and there is no need to make any changes.  \ntranslate.service.deepSeek.model=DeepSeek-V3\n# The maximum number of tokens for a single AI operation. If not set, the default value is 3000. You can just use this default value here.  \ntranslate.service.deepSeek.max_tokens=3000\n````\nThe final effect is shown in the following figure: \n![image](assets/application_properties_demo.png)\n\n##### 1.4 Restart the service\n````\npkill java\nsudo /mnt/tomcat8/bin/startup.sh\n````\n\n##### 1.5 Test the text translation API.\n![image](assets/texts_translate_api_demo.png)  \nThe \"from\" passed in here represents the language before translation. If you know what language it is, fill it in. If you don't know and it's difficult to judge, just fill it in as shown in the picture above. DeepSeek will automatically recognize and perform the translation. \nFor detailed instructions on this translation API interface, please refer to: [http://api.zvo.cn/translate/service/20230807/translate.json.html](http://api.zvo.cn/translate/service/20230807/translate.json.html)\n\n\n\n### 2. Use translate.js in HTML.\n\n**Click on a certain language in an ordinary website to switch. **   \n\nAs shown in the following figure, there should be an option to switch among several languages at a certain position on the website. \n![](assets/site_demo.png)  \nDirectly add the following code at the end of its HTML code: \n\n````\n<!-- Add a button for switching to a certain language. Note that a `class=\"ignore\"` is added to the `ul` tag, which means that this piece of code will not be translated.  -->\n<ul class=\"ignore\">\n\t<li><a href=\"javascript:translate.changeLanguage('english');\">English</a></li>|\n\t<li><a href=\"javascript:translate.changeLanguage('chinese_simplified');\">简体中文</a></li>|\n\t<li><a href=\"javascript:translate.changeLanguage('chinese_traditional');\">繁體中文</a></li>\n</ul>\n\n<!-- Introduce the JavaScript for multi-language switching. -->\n<script src=\"https://res.zvo.cn/translate/translate.js\"></script>\n<script>\n\t//Do not display the default select option for choosing languages. \n\ttranslate.selectLanguageTag.show = false; \n\t//Set the host of the text translation API, which is the text translation API we deployed in the first step above. For more information about this, please refer to https://translate.zvo.cn/4068.html. \n\ttranslate.request.api.host='http://121.36.23.238/'; \n\t//Translation triggers initialization.\n\ttranslate.execute();\n</script>\n````\n\nThis is just the use in the most common scenario. In addition, for various frameworks such as VUE, React, and so on, as well as all kinds of management backends, as long as JavaScript can be run, it can be used! \n\n# Open-source repository\nhttps://github.com/xnx3/translate  \n\n"
  },
  {
    "path": "docs/translate.js/README_cn.md",
    "content": "<h1 align=\"center\">\n    translate.js\n</h1>\n<h4 align=\"center\">\n    它是面向前端开发者使用的 AI i18n，两行js实现html全自动翻译。 <br/>\n    交给AI，无需改动页面、无语言配置文件、无API Key、对SEO友好！\n</h4> \n\n![image](assets/html_demo.gif)  \n\n\n# 使用方式\n### 1. 部署文本翻译API\n首先部署文本翻译开放接口，它支持一次性批量翻译多个文本，同时内置多层缓存体系，最大化降低AI翻译的耗时。以使用户在使用时做到瞬间翻译无延迟的能力。  \n\n##### 1.1 服务器规格\n1核1G、20G系统盘、1MB带宽，操作系统为CentOS 7.4 （7.0~7.9都可）即可完美运行。\n\n##### 1.2 安装\n````\nwget https://gitee.com/mail_osc/translate/raw/master/deploy/install_translate.service.sh -O install.sh && chmod -R 777 install.sh && sh ./install.sh\n````\n\n##### 1.3 配置 DeepSeek 参数\n\n编辑 application.properties ，编辑命令：\n````\nvi /mnt/tomcat8/webapps/ROOT/WEB-INF/classes/application.properties\n````\n然后再最后面追加几行配置：  \n````\n# 大模型接口请求URL, 比如下面的是华为DeepSeek的请求URL的，另外像是GiteeAI的请求URL是 https://ai.gitee.com/v1/chat/completions 其他的平台的可自行获取填入\ntranslate.service.deepSeek.url=https://infer-modelarts-cn-southwest-2.modelarts-infer.com/v1/infers/fd53915b-8935-48fe-be70-449d76c0fc87/v1/chat/completions\n# 访问令牌\ntranslate.service.deepSeek.key=QM8jrVl98lTluLhzCaO4i9PFv-caRk6U7kDL-H6CIyApytMG69jO33aasO1GnduQak8fGI7dtpmbsM98Qh3ywA\n# 使用哪个模型，这里默认使用 DeepSeek-V3 即可，无需更改\ntranslate.service.deepSeek.model=DeepSeek-V3\n# AI单次的最大token数量,不设置默认是3000，这里可以默认用这个即可\ntranslate.service.deepSeek.max_tokens=3000\n````\n最终的效果如下图所示：  \n![image](assets/application_properties_demo.png)\n\n##### 1.4 重启服务\n````\npkill java\nsudo /mnt/tomcat8/bin/startup.sh\n````\n\n##### 1.5 文本翻译API测试一下\n![image](assets/texts_translate_api_demo.png)  \n这里传入的 from 代表翻以前的语种语言，如果你知道是什么语言则填上，如果不知道不好判断，那就固定上图这样填写即可，DeepSeek会自动识别并进行翻译。\n有关此翻译API接口的详细说明可参考： [http://api.zvo.cn/translate/service/20230807/translate.json.html](http://api.zvo.cn/translate/service/20230807/translate.json.html)\n\n\n\n### 2. html中使用 translate.js \n\n**普通网站中点击某个语言进行切换**  \n如下图所示，网站中的某个位置要有几种语言切换  \n![](assets/site_demo.png)  \n直接在其html代码末尾的位置加入以下代码：  \n\n````\n<!-- 增加某种语言切换的按钮。注意 ul上加了一个 class=\"ignore\" 代表这块代码不会被翻译到 -->\n<ul class=\"ignore\">\n\t<li><a href=\"javascript:translate.changeLanguage('english');\">English</a></li>|\n\t<li><a href=\"javascript:translate.changeLanguage('chinese_simplified');\">简体中文</a></li>|\n\t<li><a href=\"javascript:translate.changeLanguage('chinese_traditional');\">繁體中文</a></li>\n</ul>\n\n<!-- 引入多语言切换的js -->\n<script src=\"https://res.zvo.cn/translate/translate.js\"></script>\n<script>\n\t//不出现默认的select的选择语言\n\ttranslate.selectLanguageTag.show = false; \n\t//设置文本翻译API的主机，也就是我们上面第一步部署好的文本翻译API，有关此更多可参考 https://translate.zvo.cn/4068.html\n\ttranslate.request.api.host='http://121.36.23.238/'; \n\t//翻译触发初始化\n\ttranslate.execute();\n</script>\n````\n\n这只是一个最普通的场景使用，另外像是各框架了比如VUE、React、等等，各种管理后台，只要能运行js，都能使用它！\n\n# 开源仓库\nhttps://github.com/xnx3/translate  \n交流QQ群： 240567964\n\n# 它的能力\n\n### 特性说明\n* **使用极其简单。** 直接加入几行 JavaScript 代码即可让其拥有上百种语言切换能力。\n* **不增加工作量。** 无需改造页面本身植入大量垃圾代码变得臃肿，也不需要配置各种语种的语言文件，因为它会直接扫描你的DOM自动识别并翻译显示，它不需要你到某某网站登录去申请什么key，它是开源开放的，拿来就能用。\n* **极其灵活扩展。** 您可指定它[只翻译某些指定区域的元素](http://translate.zvo.cn/4063.html)、[自定义切换语言方式及美化](http://translate.zvo.cn/4056.html)、[某些id、class、tag不被翻译](https://translate.zvo.cn/4061.html)、[自定义翻译术语](https://translate.zvo.cn/4070.html) ...... 只要你想的，它都能做到。做不到的，你找我我来让它做到！\n* **自动切换语种。** [自动根据用户的语言喜好及所在的国家切换到这个语种进行浏览](http://translate.zvo.cn/4065.html)\n* **极速翻译能力。** [内置三层缓存、预加载机制，毫秒级瞬间翻译的能力。它并不是你理解的大模型蜗牛似的逐个字往外出的那样](http://translate.zvo.cn/4026.html)\n* [**永久开源免费。** 采用Apache-2.0开源协议，您可永久免费使用](https://github.com/xnx3/translate/blob/master/LICENSE)。[另外你可以用它来做某些系统的三方插件直接售卖盈利](http://translate.zvo.cn/4036.html)、或者你是建站公司用它来做为一项高级功能盈利，我们都是完全认可并支持的，并不需要给我们任何费用！\n* **搜索引擎友好。** 完全不影响你本身网站搜索引擎的收录。爬虫所爬取的网页源代码，它不会对其进行任何改动，你可完全放心。[另外我们还有高级版本让你翻译之后的页面也能被搜索引擎收录](http://translate.zvo.cn/236896.html)\n* **支持私有部署。** [在某些政府机关及大集团内部项目中，对数据隐私及安全保密有强要求场景、或者完全不通外网的场景，可以自行私有部署翻译API服务](http://translate.zvo.cn/4052.html) \n* **全球网络节点**。美洲、亚洲、欧洲 ... 都有网络节点，它能自动适配最快节点，每间隔1分钟自动获取一次延迟最小的节点进行接入使用，使全球范围使用都可高效稳定。\n* **HTML整体翻译**。[提供开放API接口，传入html文件（html源代码）及要翻译为的语言即可拿到翻译后的html源码。完美支持识别各种复杂及不规范html代码，\n支持翻译前的微调，比如不翻译某个区域、图片翻译、js语法操作html文件中的元素进行增删改等。](https://translate.zvo.cn/4022.html)\n* **源站翻译及域名分发**。[将您现有的网站，翻译成全新的小语种网站，小语种网站可以分别绑定域名并支持搜索引擎收录和排名。而您的源站无需任何改动。也就是你可以将你朋友的网站，翻译为小语种网站，绑定上自己的域名，提供对外访问。而你无需向你朋友取得任何的如账号等相关权限](https://translate.zvo.cn/236896.html)\n* **浏览器翻译插件**。[提供整体的浏览器翻译插件的全套方案，您如果是开发者，完全可以拿去将界面美化包装一下，而后直接提交应用市场进行售卖盈利](https://translate.zvo.cn/4037.html)\n\n\n### 微调指令\n* **[设置默认翻译为的语种](http://translate.zvo.cn/4071.html)**，用户第一次打开时，默认以什么语种显示。\n* **[自定义翻译术语](http://translate.zvo.cn/41555.html)**，如果你感觉某些翻译不太符合你的预期，可进行针对性的定义某些词或句子的翻译结果，进行自定义术语库\n* **[翻译完后自动触发执行](http://translate.zvo.cn/4069.html)**，当翻译完成后会自动触发执行您的某个方法，以便您来做自定义扩展。\n* **[指定翻译服务接口](http://translate.zvo.cn/4068.html)**，如果你不想用我们开源免费的翻译服务接口，使用您自己私有部署的、或者您自己二次开发对接的某个翻译服务，可通过此来指定自己的翻译接口。\n* **[监控页面动态渲染的文本进行自动翻译](http://translate.zvo.cn/4067.html)**，如果页面用 JavaScript 的地方比较多，内容都是随时用JS来控制显示的，比如 VUE、React 等框架做的应用，它可以实时监控DOM中文字的变动，当发生变动后立即识别并进行翻译。\n* **[设置本地语种（当前网页的语种）](http://translate.zvo.cn/4066.html)**，手动指定当前页面的语言。如果不设置，它会自动识别当前网页的文本，取当前网页文本中，出现频率最高的语种为默认语种。\n* **[自动切换为用户所使用的语种](http://translate.zvo.cn/4065.html)**，用户第一次打开网页时，自动判断当前用户所使用的语种、以及所在的国家，来自动进行切换为这个语种。\n* **[主动进行语言切换](http://translate.zvo.cn/4064.html)**，开放一个方法提供程序调用，只需传入翻译的目标语言，即可快速切换到指定语种\n* **[只翻译指定的元素](http://translate.zvo.cn/4063.html)**，指定要翻译的元素的集合,可传入一个或多个元素。如果不设置此，默认翻译整个网页。\n* **[翻译时忽略指定的id](http://translate.zvo.cn/4062.html)**，翻译时追加上自己想忽略不进行翻译的id的值，凡是在这里面的，都不进行翻译，也就是当前元素以及其子元素都不会被翻译。\n* **[翻译时忽略指定的class属性](http://translate.zvo.cn/4061.html)**，翻译时追加上自己想忽略不进行翻译的class标签，凡是在这里面的，都不进行翻译，也就是当前元素以及其子元素都不会被翻译。\n* **[翻译时忽略指定的tag标签](http://translate.zvo.cn/4060.html)**，翻译时追加上自己想忽略不进行翻译的tag标签，凡是在这里面的，都不进行翻译，也就是当前元素以及其子元素都不会被翻译。\n* **[翻译时忽略指定的文字不翻译](http://translate.zvo.cn/283381.html)**，翻译时追加上自己想忽略不进行翻译的文字，凡是在这里面的，都不进行翻译。\n* **[对网页中图片进行翻译](http://translate.zvo.cn/4055.html)**，在进行翻译时，对其中的图片也会一起进行翻译。\n* **[鼠标划词翻译](http://translate.zvo.cn/4072.html)**，鼠标在网页中选中一段文字，会自动出现对应翻译后的文本\n* **[获取当前显示的是什么语种](http://translate.zvo.cn/4074.html)**，如果用户切换为英语进行浏览，那么这个方法将返回翻译的目标语种。\n* **[根据URL传参控制以何种语种显示](http://translate.zvo.cn/41929.html)**，设置可以根据当前访问url的某个get参数来控制使用哪种语言显示。\n* **[离线翻译及自动生成配置](http://translate.zvo.cn/4076.html)**，其实它也就是传统 i18n 的能力，有语言配置文件提供翻译结果。\n* **[手动调用接口进行翻译操作](http://translate.zvo.cn/4077.html)**，通过JavaScript调用一个方法，传入翻译文本进行翻译，并获得翻译结果\n* **[元素的内容整体翻译能力配置](http://translate.zvo.cn/4078.html)**，对node节点的文本拿来进行整体翻译处理，而不再拆分具体语种，提高翻译语句阅读通顺程度\n* **[翻译接口响应捕获处理](http://translate.zvo.cn/4079.html)**，对翻译API接口的响应进行捕获，进行一些自定义扩展\n* **[清除历史翻译语种的缓存](http://translate.zvo.cn/4080.html)**，清除掉你上个页面所记忆的翻译语种，从而达到切换页面时不会按照上个页面翻译语种自动进行翻译的目的。\n* **[网页ajax请求触发自动翻译](http://translate.zvo.cn/4086.html)**，监听当前网页中所有的ajax请求，当请求结束后，自动触发翻译\n* **[设置只对指定语种进行翻译](http://translate.zvo.cn/4085.html)**，翻译时只会翻译在这里设置的语种，未在里面的语种将不会被翻译。\n* **[识别字符串语种及分析](http://translate.zvo.cn/43128.html)**，对字符串进行分析，识别出都有哪些语种，每个语种的字符是什么、每个语种包含的字符数是多少\n* **[重写一级缓存（浏览器缓存）](http://translate.zvo.cn/4082.html)**，你如果不想使用默认的 localStorage 的缓存，您完全可以对其重写，设置自己想使用的缓存方式\n* **[设置使用的翻译服务 translate.service.use](http://translate.zvo.cn/4081.html)**，目前有自有的服务器提供翻译API方式、无自己服务器API的方式两种。\n* **[启用企业级稳定翻译](http://translate.zvo.cn/4087.html)**，独立于开源版本的翻译通道之外，仅对少数用户开放，提供企业级的稳定、高速、以及更多网络分发节点。\n* **[增加对指定标签的属性进行翻译](http://translate.zvo.cn/231504.html)**，可以增加对指定html标签的某个或某些属性进行翻译。比如element、vue 等框架，有些自定义的标签属性，想让其也正常翻译\n* **[本地语种也进行强制翻译](http://translate.zvo.cn/289574.html)**，切换为中文时，即使本地语种设置的是中文，网页中只要不是中文的元素，都会被翻译为要显示的语种\n* **[自定义通过翻译API进行时的监听事件](http://translate.zvo.cn/379207.html)**，当通过翻译API进行文本翻译时的整个过程进行监听，做一些自定义处理，比如翻译API请求前要做些什么、请求翻译API完成并在DOM渲染完毕后触发些什么。\n\n\n"
  },
  {
    "path": "docs/translate.js/README_ja.md",
    "content": "<h1 align=\"center\">\n    translate.js\n</h1>\n<h4 align=\"center\">\n    それはフロントエンド開発者向けのAI i18nで、2行のJSでHTMLの全自動翻訳を実現します。 <br/>\n    AIに任せて、ページの変更なし、言語設定ファイルなし、APIキーなし、SEOに優しい！\n</h4> \n\n![image](assets/html_demo.gif)  \n\n# 使用方法\n### 1. テキスト翻訳APIの展開\nまず、テキスト翻訳のオープンインターフェースを展開し、一度に複数のテキストをバッチ翻訳することをサポートし、同時に多層キャッシュシステムを内蔵して、AI翻訳の時間を最大限に短縮します。これにより、ユーザーが使用時に瞬時に遅延なく翻訳できる能力を実現します。\n\n##### 1.1 サーバー仕様\n1コア1GB、20GBのシステムディスク、1MBの帯域幅で、オペレーティングシステムはCentOS 7.4（7.0〜7.9でも可）で完璧に動作します。\n\n##### 1.2 インストール\n````\nwget https://gitee.com/mail_osc/translate/raw/master/deploy/install_translate.service.sh -O install.sh && chmod -R 777 install.sh && sh ./install.sh\n````\n\n##### 1.3 DeepSeek パラメータの設定\n\n編集 application.properties ：\n````\nvi /mnt/tomcat8/webapps/ROOT/WEB-INF/classes/application.properties\n````\nその後、最後にいくつかの設定を追加します： \n````\n# 大規模モデルインターフェースリクエストURL、例えば以下のものはHuawei DeepSeekのリクエストURLです。また、GiteeAIのリクエストURLは https://ai.gitee.com/v1/chat/completions 他のプラットフォームからは自分で取得して入力できます\ntranslate.service.deepSeek.url=https://infer-modelarts-cn-southwest-2.modelarts-infer.com/v1/infers/fd53915b-8935-48fe-be70-449d76c0fc87/v1/chat/completions\n# アクセストークン\ntranslate.service.deepSeek.key=QM8jrVl98lTluLhzCaO4i9PFv-caRk6U7kDL-H6CIyApytMG69jO33aasO1GnduQak8fGI7dtpmbsM98Qh3ywA\n# どのモデルを使用するか、ここではデフォルトで DeepSeek-V3 を使用すればよく、変更する必要はありません。\ntranslate.service.deepSeek.model=DeepSeek-V3\n# AIの単回の最大トークン数、設定しない場合デフォルトは3000で、ここではデフォルトでこれを使用すれば良いです。\ntranslate.service.deepSeek.max_tokens=3000\n````\n最終の効果は以下の図のとおりです：  \n![image](assets/application_properties_demo.png)\n\n##### 1.4 サービスを再起動する\n````\npkill java\nsudo /mnt/tomcat8/bin/startup.sh\n````\n\n##### 1.5 テキスト翻訳APIをテストする\n![image](assets/texts_translate_api_demo.png)  \nここで渡される「from」は、翻訳前の言語を表します。もしその言語がわかればそれを記入し、わからない場合や判断が難しい場合は、上記のように固定して記入してください。DeepSeekが自動的に認識し、翻訳を行います。\nこの翻訳APIインターフェースの詳細な説明については、以下を参照してください： [http://api.zvo.cn/translate/service/20230807/translate.json.html](http://api.zvo.cn/translate/service/20230807/translate.json.html)\n\n\n\n### 2. htmlでtranslate.jsを使用する\n\n**通常のウェブサイトで、ある言語をクリックして切り替える**  \n以下の図に示すように、ウェブサイトの特定の場所でいくつかの言語を切り替える必要があります。\n![](assets/site_demo.png)  \nそのHTMLコードの末尾に以下のコードを直接追加します：  \n\n````\n<!-- ある言語の切り替えボタンを追加します。ulに class=\"ignore\" が追加されていることに注意してください。これは、この部分のコードが翻訳されないことを意味します。 -->\n<ul class=\"ignore\">\n\t<li><a href=\"javascript:translate.changeLanguage('english');\">English</a></li>|\n\t<li><a href=\"javascript:translate.changeLanguage('chinese_simplified');\">简体中文</a></li>|\n\t<li><a href=\"javascript:translate.changeLanguage('chinese_traditional');\">繁體中文</a></li>\n</ul>\n\n<!-- 多言語切り替えのJSを導入 -->\n<script src=\"https://res.zvo.cn/translate/translate.js\"></script>\n<script>\n\t//デフォルトの選択言語が表示されない\n\ttranslate.selectLanguageTag.show = false; \n\t//テキスト翻訳APIのホストを設定します。これは、上記の最初のステップでデプロイしたテキスト翻訳APIです。これに関する詳細は、以下を参照してください。 https://translate.zvo.cn/4068.html\n\ttranslate.request.api.host='http://121.36.23.238/'; \n\t//翻訳トリガーの初期化\n\ttranslate.execute();\n</script>\n````\n\nこれは最も一般的なシーンでの使用例です。また、VUEやReactなどの各フレームワークや、さまざまな管理画面など、JSが実行できる環境であればどこでも使用できます！\n\n# オープンソースリポジトリ\nhttps://github.com/xnx3/translate  \n"
  },
  {
    "path": "docs/wordware/README.md",
    "content": "<img width=\"1024\" src=\"assets/og-image.png\" alt=\"wordware og\">\n\n<!-- TEXT_SECTION:header:END -->\n\n# Use DeepSeek Through Wordware\n\n<a href=\"https://www.wordware.ai/\">Wordware</a> is a toolkit that enables anyone to build, iterate, and deploy their AI stack with just natural language. Wordware is the easiest and fastest way to integrate both DeepSeek V3 and R1 into your LLM applications.\n\n## Tutorial\n\n### Create a new generation with the slash command\n\n![select model](assets/select-deepseek.jpg)\n\n### Select your desired DeepSeek model\n\n![select model](assets/select-deepseek.jpg)\n\n### Provide it with your context and press run. It's that simple.\n\n![use v3](assets/v3.jpg)\n\n### Use R1 for more advanced reasoning.\n\n![use r1](assets/r1.jpg)\n\n### And pair it with control blocks and tools to create more complex flows\n\n![use tools](assets/tools.jpg)\n\n### Refer to the <a href=\"https://docs.wordware.ai/tour\">docs</a> to learn more.\n\n### Try <a href=\"https://www.wordware.ai/\">Wordware</a> out today and build something awesome!\n"
  },
  {
    "path": "docs/wordware/README_cn.md",
    "content": "<img width=\"1024\" src=\"assets/og-image.png\" alt=\"wordware og\">\n\n<!-- TEXT_SECTION:header:END -->\n\n# 通过 Wordware 使用 DeepSeek\n\n<a href=\"https://www.wordware.ai/\">Wordware</a> 是一个工具包，让任何人都能仅使用自然语言来构建、迭代和部署他们的 AI 技术栈。Wordware 是将 DeepSeek V3 和 R1 集成到您的 LLM 应用程序中最简单和最快速的方式。\n\n## 教程\n\n### 使用斜杠命令创建新的生成\n\n![select model](assets/select-deepseek.jpg)\n\n### 选择您想要的 DeepSeek 模型\n\n![select model](assets/select-deepseek.jpg)\n\n### 提供您的上下文并点击运行，就是这么简单\n\n![use v3](assets/v3.jpg)\n\n### 使用 R1 进行更高级的推理\n\n![use r1](assets/r1.jpg)\n\n### 将其与控制块和工具配对，创建更复杂的流程\n\n![use tools](assets/tools.jpg)\n\n### 查看<a href=\"https://docs.wordware.ai/tour\">文档</a>了解更多信息\n\n### 立即试用 <a href=\"https://www.wordware.ai/\">Wordware</a> 并构建令人惊叹的应用！\n"
  },
  {
    "path": "docs/wusigram/README.md",
    "content": "### AI Programming on Mobile Devices — 无思微程序 Makes Mobile Development Effortless\n\nDeveloping and running code directly on mobile devices used to be cumbersome and difficult. **无思微程序** simplifies the development and publishing process by integrating DeepSeek AI programming, solving this challenge with ease. This tool, designed specifically for mobile use, focuses on auto-generating and running HTML/CSS/JS code, offering a more user-friendly mobile development experience for coding enthusiasts, educators, and lightweight developers.\n\n---\n\n#### Watch a Demo Video First\n\n[![Bilibili Video]](https://www.bilibili.com/video/BV1xn55zKEUT)\n\n---\n\n#### 1. AI-Powered: Run-Ready Programs from a Single Sentence\n\n**无思微程序** innovatively integrates the DeepSeek model into the development workflow, breaking traditional coding barriers:\n\n1. **Natural Language to Code**\n   Simply describe your needs in conversational language (e.g., “Create a cyberpunk-style TodoList”), and the AI generates complete HTML+CSS+JS code automatically—no need to write code line by line.\n2. **Dynamic Feature Adjustments**\n   You can request changes directly (e.g., “Change the style to cute”), and the AI will instantly update the code—enabling a conversational programming experience.\n3. **Beginner-Friendly Design**\n   No need to master full syntax rules—users can complete functional development through multiple rounds of interaction with the AI, making it perfect for beginners to quickly test ideas.\n\n---\n\n#### 2. A Dedicated Development Environment for Mobile\n\nSpecifically optimized for mobile scenarios, offering capabilities that traditional PC tools can’t easily provide:\n\n1. **Instant Preview System**\n   Code can be pasted or generated and instantly rendered into a visual interface. The runtime experience closely resembles native apps, supporting touch interactions like swiping and tapping.\n2. **Standardized Hardware Access**\n   Supports access to the phone’s camera (photo/scanning), microphone (voice input), and local storage. A code sample library provides templates for common scenarios.\n3. **Multi-Project Management Mode**\n   Each HTML project is stored independently, with customizable runtime icons and launch interfaces—allowing users to launch different projects just like opening lightweight apps.\n\n---\n\n#### 3. Practical Features That Meet Real Needs\n\n1. **Version Time Machine**\n   Every modification is automatically saved as a version history, preventing code loss due to accidental changes.\n2. **Cloud-Based Backup**\n   Local code can optionally be synced to a private cloud space for encrypted storage, enabling cross-device development continuity.\n3. **Code Sharing Community**\n   An open code hub lets users explore public creative projects (such as mini-games or tool templates) and one-click share their own programs with others—also supporting collaborative development.\n\n---\n\n#### 4. Full Cross-Platform Support\n\n* **Mobile Devices**:\n  iOS users can download from the App Store, Android users can install via their app store\n* **Desktop Usage Extensions**:\n\n  * Mac devices (M-series) can run the iOS version natively\n  * Windows PCs can use the full features via Android emulators\n\n---\n"
  },
  {
    "path": "docs/wusigram/README_cn.md",
    "content": "### 手机上也可以AI编程了 —— 无思微程序让移动设备开发触手可及\n\n在移动设备上直接编写并运行代码程序，以往是比较繁琐和困难的事情。**无思微程序**通过引入DeepSeek AI编程，简化了开发和发布流程，将这一难题轻松解决。这款专为手机端设计的工具，聚焦HTML/CSS/JS代码的自动编写和运行，为编程爱好者、教育用户和轻量级开发者提供了更友好的移动开发方式。\n\n---\n\n#### 可以先看一段视频实操演示  \n[![Bilibili Video]](https://www.bilibili.com/video/BV1xn55zKEUT)\n\n---\n\n#### 一、AI助力：一句话生成可运行程序  \n无思微程序创新性地将DeepSeek模型融入开发流程，打破传统编码门槛：  \n1. **自然语言转代码**  \n   用口语化指令描述需求（如“做一个赛博风格的TodoList”），AI自动生成完整的HTML+CSS+JS代码，无需手动逐行编写。  \n2. **动态调整功能**  \n   对生成的代码可直接提出修改要求（如“将风格改为可爱风”），AI即时响应调整，实现“对话式编程”。  \n3. **零基础友好设计**  \n   用户无需掌握完整语法规则，通过多次与AI交互即可完成功能开发，特别适合编程初学者快速验证想法。\n\n---\n\n#### 二、手机端的专属开发环境  \n针对移动场景深度优化，提供传统PC工具难以实现的功能：  \n1. **即写即现的预览系统**  \n   粘贴或生成的代码可立即渲染为可视化界面，运行效果接近原生APP，支持触屏滑动、点击反馈等交互体验。  \n2. **硬件调用标准化**  \n   支持调用手机摄像头（拍照/扫码）、麦克风（语音输入）、本地存储等功能，代码示例库提供常用场景模板。  \n3. **多项目管理模式**  \n   每个HTML项目独立存储，运行界面与应用图标均可自定义，可直接点击启动不同项目，如同安装多个轻应用。\n\n---\n\n#### 三、贴合实际需求的实用功能  \n1. **版本时光机**  \n   每次修改自动保存历史版本，避免误操作导致的代码丢失。  \n2. **云端双保险**  \n   本地代码可选择同步至私有云空间，加密存储，换设备也可继续开发。  \n3. **代码共享社区**  \n   开放代码广场功能，既能学习他人公开的创意项目（如小游戏、工具模板），也可将自己编写的程序一键分享给其他用户，同时支持二次开发。\n\n---\n\n#### 四、全平台覆盖方案  \n- **手机端**：  \n  iOS用户访问App Store，安卓用户通过应用商店搜索安装  \n- **电脑端延伸使用**：  \n  - Mac设备（M系列）直接运行iOS版本  \n  - Windows电脑通过安卓模拟器使用完整功能  \n\n---\n"
  },
  {
    "path": "docs/xhai_browser/README.md",
    "content": "<img src=\"./assets/logo_512.png\" width=\"64\" height=\"auto\" /> <img src=\"./assets/desktop_512.png\" width=\"64\" height=\"auto\" /> \n\n# [xhai Browser](https://www.dahai123.top/)\n\n\n[xhai Browser](https://m.malink.cn/s/7JFfIv) is an Android desktop management & AI browser, DeepSeek is the default AI dialog engine.\nHe has the ultimate performance (0.2 seconds to start), slim size (apk 3M), no ads, ultra-fast ad blocking, multi-screen classification, screen navigation, multi-search box, a box multiple search!\n\nxhai means \"xiaohai\" in Chinese, which means \"extreme, high-performance, AI Browser\" in English.\n\n## UI\n\n<img src=\"./assets/deepseek3-4t.jpg\" width=\"360\" height=\"auto\" />\n<img src=\"./assets/deepseek3-4_2t.jpg\" width=\"360\" height=\"auto\" />\n"
  },
  {
    "path": "docs/xhai_browser/README_cn.md",
    "content": "<img src=\"./assets/logo_512.png\" width=\"64\" height=\"auto\" /> <img src=\"./assets/desktop_512.png\" width=\"64\" height=\"auto\" /> \n\n# [小海浏览器](https://www.dahai123.top/)\n\n\n[小海浏览器](https://m.malink.cn/s/7JFfIv)是安卓桌面管理&AI浏览器,DeepSeek是默认AI对话引擎\n他有极致的性能(0.2秒启动),苗条的体型(apk 3M大),无广告,超高速广告拦截,多屏分类,屏幕导航,多搜索框,一框多搜\n\n\n## UI\n\n<img src=\"./assets/deepseek3-4t.jpg\" width=\"360\" height=\"auto\" />\n<img src=\"./assets/deepseek3-4_2t.jpg\" width=\"360\" height=\"auto\" />\n\n\n"
  },
  {
    "path": "docs/yomo/README.md",
    "content": "# YoMo Framework - Deepseek Provider\n\nYoMo is an open-source LLM Function Calling Framework for building Geo-distributed AI agents. Built atop QUIC Transport Protocol and Strongly-typed Stateful Serverless architecture, makes your AI agents low-latency, reliable, secure, and easy.\n\n## 🚀 Getting Started\n\nLet's implement a function calling serverless `sfn-get-ip-latency`:\n\n### Step 1. Install CLI\n\n```bash\ncurl -fsSL https://get.yomo.run | sh\n```\n\n### Step 2. Start the server\n\nPrepare the configuration as `my-agent.yaml`\n\n```yaml\nname: ai-zipper\nhost: 0.0.0.0\nport: 9000\n\nauth:\n  type: token\n  token: SECRET_TOKEN\n\nbridge:\n  ai:\n    server:\n      addr: 0.0.0.0:9000 ## Restful API endpoint\n      provider: deepseek ## LLM API Service we will use\n\n    providers:\n      deepseek:\n        api_key: <DEEPSEEK_API_KEY>\n        model: deepseek-reasoner\n```\n\nStart the server:\n\n```sh\nYOMO_LOG_LEVEL=debug yomo serve -c my-agent.yaml\n```\n\n### Step 3. Write the function\n\nFirst, let's define what this function do and how's the parameters required, these will be combined to prompt when invoking LLM.\n\n```golang\ntype Parameter struct {\n\tDomain string `json:\"domain\" jsonschema:\"description=Domain of the website,example=example.com\"`\n}\n\nfunc Description() string {\n\treturn `if user asks ip or network latency of a domain, you should return the result of the giving domain. try your best to dissect user expressions to infer the right domain names`\n}\n\nfunc InputSchema() any {\n\treturn &Parameter{}\n}\n```\n\nCreate a Stateful Serverless Function to get the IP and Latency of a domain:\n\n```golang\nfunc Handler(ctx serverless.Context) {\n\tvar msg Parameter\n\tctx.ReadLLMArguments(&msg)\n\n\t// get ip of the domain\n\tips, _ := net.LookupIP(msg.Domain)\n\n\t// get ip[0] ping latency\n\tpinger, _ := ping.NewPinger(ips[0].String())\n\tpinger.Count = 3\n\tpinger.Run()\n\tstats := pinger.Statistics()\n\n\tval := fmt.Sprintf(\"domain %s has ip %s with average latency %s\", msg.Domain, ips[0], stats.AvgRtt)\n\tctx.WriteLLMResult(val)\n}\n\n```\n\nFinally, let's run it\n\n```bash\n$ yomo run app.go\n\ntime=2025-01-29T21:43:30.583+08:00 level=INFO msg=\"connected to zipper\" component=StreamFunction sfn_id=B0ttNSEKLSgMjXidB11K1 sfn_name=fn-get-ip-from-domain zipper_addr=localhost:9000\ntime=2025-01-29T21:43:30.584+08:00 level=INFO msg=\"register ai function success\" component=StreamFunction sfn_id=B0ttNSEKLSgMjXidB11K1 sfn_name=fn-get-ip-from-domain zipper_addr=localhost:9000 name=fn-get-ip-from-domain tag=16\n```\n\n### Done, let's have a try\n\n```sh\n$ curl -i http://127.0.0.1:9000/v1/chat/completions -H \"Content-Type: application/json\" -d '{\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a test assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Compare website speed between Nike and Puma\"\n    }\n  ],\n  \"stream\": false\n}'\n\nHTTP/1.1 200 OK\nContent-Length: 944\nConnection: keep-alive\nContent-Type: application/json\nDate: Wed, 29 Jan 2025 13:30:14 GMT\nKeep-Alive: timeout=4\nProxy-Connection: keep-alive\n\n{\n  \"Content\": \"Based on the data provided for the domains nike.com and puma.com which include IP addresses and average latencies, we can infer the following about their website speeds:\n  - Nike.com has an IP address of 13.225.183.84 with an average latency of 65.568333 milliseconds.\n  - Puma.com has an IP address of 151.101.194.132 with an average latency of 54.563666 milliseconds.\n  \n  Comparing these latencies, Puma.com is faster than Nike.com as it has a lower average latency. \n  \n  Please be aware, however, that website speed can be influenced by many factors beyond latency, such as server processing time, content size, and delivery networks among others. To get a more comprehensive understanding of website speed, you would need to consider additional metrics and possibly conductreal-time speed tests.\",\n  \"FinishReason\": \"stop\"\n}\n```\n\n### Full Example Code\n\n[Full LLM Function Calling Codes](https://github.com/yomorun/llm-function-calling-examples)\n\n## 🎯 Focuses on Geo-distributed AI Inference Infra\n\nIt’s no secret that today’s users want instant AI inference, every AI \napplication is more powerful when it response quickly. But, currently, when we\ntalk about `distribution`, it represents **distribution in data center**. The AI model is\nfar away from their users from all over the world.\n\nIf an application can be deployed anywhere close to their end users, solve the\nproblem, this is **Geo-distributed System Architecture**:\n\n<img width=\"580\" alt=\"yomo geo-distributed system\" src=\"https://user-images.githubusercontent.com/65603/162367572-5a0417fa-e2b2-4d35-8c92-2c95d461706d.png\">\n"
  },
  {
    "path": "docs/zenfeed/README.md",
    "content": "# zenfeed Integration with DeepSeek\n\nzenfeed supports using DeepSeek models for tasks like summarization and semantic analysis by configuring it within the `llms` section of your zenfeed configuration file.\n\n## Configuration\n\nTo use DeepSeek, add an entry to the `llms` list in your configuration file. Here's an example:\n\n```yaml\nllms:\n  - name: my-deepseek-chat  # A unique name for this configuration\n    provider: deepseek        # Specify the provider as deepseek\n    api_key: sk-xxxxxxxxxxx # Replace with your actual DeepSeek API key\n    model: deepseek-chat      # Specify the desired DeepSeek model (e.g., deepseek-chat, deepseek-coder)\n```"
  },
  {
    "path": "docs/zenfeed/README_cn.md",
    "content": "# zenfeed 与 DeepSeek 集成\n\nzenfeed 支持通过在其配置文件的 `llms` 部分进行设置，来使用 DeepSeek 模型执行摘要、语义分析等任务。\n\n## 配置方法\n\n要使用 DeepSeek，请在你的配置文件中的 `llms` 列表下添加一个条目。以下是一个示例：\n\n```yaml\nllms:\n  - name: my-deepseek-chat  # 为此配置指定一个唯一的名称\n    provider: deepseek        # 指定提供商为 deepseek\n    api_key: sk-xxxxxxxxxxx # 替换为你的 DeepSeek API 密钥\n    model: deepseek-chat      # 指定所需的 DeepSeek 模型（例如：deepseek-chat, deepseek-coder）\n```"
  },
  {
    "path": "docs/zotero/README.md",
    "content": "<img src=\"./assets/zotero-icon.png\" width=\"64\" height=\"auto\" /> \n\n# [Zotero](https://www.zotero.org)\n\nZotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share research.\n\n## UI\n\n<img src=\"./assets/front.png\"  />\n\n## Configuring  deepseek API\nSTEP1. Apply a token from [deepseek open platform](https://platform.deepseek.com)\nSTEP2. Install [Translate for Zotero](https://zotero.yuque.com/staff-gkhviy/pdf-trans/bwxwxh) Plugin\nSTEP3.Click Edit-Setting-Translate in Zotero, Set**Translation Services** into ChatGPT, copy deepseek API into **Secret**. Click **Config** button and set parameters in **ChatGPT Config** as follows:\n- API: https://api.deepseek.com/v1/chat/completions\n- Model: deepseek-chat\n- Temp: 1.3\n- Prompt\n你是一个中英文学术论文翻译专家，将用户输入的中文翻译成英文，或将用户输入的英文翻译成中文。对于非中文内容，将提供中文翻译结果。用户可以向你发送需要翻译的内容，你回答相应的翻译结果，你可以调整语气和风格，并考虑到某些词语的文化内涵和地区差异。同时作为翻译家，需将原文翻译成具有信达雅标准的译文。\"信\" 即忠实于原文的内容与意图；\"达\" 意味着译文应通顺易懂，表达清晰；\"雅\" 则追求译文的文化审美和语言的优美。目标是创作出既忠于原作精神，又符合目标语言文化和读者审美的翻译。一些缩写比如方法名字、人名视情况可不进行翻译。同时翻译时需要注意上下文一些名词的翻译结果的一致性。需要翻译的内容为：${sourceText}，请提供翻译结果并不做任何解释。\n\n<img src=\"./assets/setting.png\"  />"
  },
  {
    "path": "docs/zotero/README_cn.md",
    "content": "<img src=\"./assets/zotero-icon.png\" width=\"64\" height=\"auto\" /> \n\n# [Zotero](https://www.zotero.org)\n\nZotero 是一款免费且易于使用的文献管理工具，旨在帮助您收集、整理、注释、引用和分享研究成果。\n## UI\n\n<img src=\"./assets/front.png\"  />\n\n## 配置 deepseek API\nSTEP1. 打开 [deepseek开放平台](https://platform.deepseek.com) 申请token\nSTEP2. 安装 [Translate for Zotero](https://zotero.yuque.com/staff-gkhviy/pdf-trans/bwxwxh) 插件\nSTEP3. 在Zotero中点击编辑-设置-翻译,将翻译服务设置为ChatGPT, 申请的deepseek token复制到密钥中. 点击配置, 在**ChatGPT 配置项**中设置如下内容:\n\n- 接口: https://api.deepseek.com/v1/chat/completions\n- 模型: deepseek-chat\n- 温度: 1.3\n- Prompt\n你是一个中英文学术论文翻译专家，将用户输入的中文翻译成英文，或将用户输入的英文翻译成中文。对于非中文内容，将提供中文翻译结果。用户可以向你发送需要翻译的内容，你回答相应的翻译结果，你可以调整语气和风格，并考虑到某些词语的文化内涵和地区差异。同时作为翻译家，需将原文翻译成具有信达雅标准的译文。\"信\" 即忠实于原文的内容与意图；\"达\" 意味着译文应通顺易懂，表达清晰；\"雅\" 则追求译文的文化审美和语言的优美。目标是创作出既忠于原作精神，又符合目标语言文化和读者审美的翻译。一些缩写比如方法名字、人名视情况可不进行翻译。同时翻译时需要注意上下文一些名词的翻译结果的一致性。需要翻译的内容为：${sourceText}，请提供翻译结果并不做任何解释。\n\n\n<img src=\"./assets/setting_cn.png\"  />"
  }
]