MemOS 2.0: 星尘（Stardust）
-Total Tasks
-Active
-Completed
-Skipped
-Total Skills
-Active
-Draft
-Installed
-Public
-
Total Memories
-
Writes Today
-
Sessions
-
Embeddings
\u{1F4CA} Memory Writes per Day
\u26A1 Tool Response Time (per minute avg)
Model Configuration
\u{1F4CA} Model Health
\u{1F4E1} Embedding Model
\u{1F9E0} Summarizer Model
\u{1F527} Skill Evolution
Skill Dedicated Model
If not configured, the main Summarizer Model above will be used for skill generation. Configure a dedicated model here for higher quality skill output.
\u{1F4CA} Telemetry
Anonymous usage analytics to help improve the plugin. Only sends tool names, latencies, and version info. No memory content, queries, or personal data is ever sent.
\u{1F4BE} General
Requires restart to take effect
\u2713 Saved
Some changes require restarting the OpenClaw gateway to take effect.
\u{1F4E5} Import OpenClaw Memory
Migrate your existing OpenClaw built-in memories and conversation history into this plugin. The import process uses smart deduplication to avoid duplicates.
Three ways to use:
\u2460 Import memories only (fast) — Click "Start Import" to quickly migrate all memory chunks and conversations. No task/skill generation. Suitable when you just need the raw data.
\u2461 Import + generate tasks & skills (slow, serial) — After importing memories, enable "Generate Tasks" and/or "Trigger Skill Evolution" below to analyze conversations one by one. This takes longer as each session is processed by LLM sequentially.
\u2462 Import first, generate later (flexible) — Import memories now, then come back anytime to start task/skill generation. You can pause the generation at any point and resume later — it will pick up where you left off, only processing sessions that haven't been handled yet.