
Memos Memory Guide
This is essentially a reference manual for Claude to understand how MemOS works under the hood. It explains the auto-recall system that injects memories at the start of each turn, then walks through when to manually call memory_search, memory_get, memory_share, and the rest of the tool suite. The guidance on two sharing planes (local agent vs team) is helpful for avoiding confusion. If you're building workflows where Claude needs to search past conversations, pull task summaries, or share context across agents, this keeps the model from guessing at the API semantics. It's verbose but thorough, covering both the happy path and edge cases like when auto-recall returns nothing.
- skills.sh installs
- 302
- GitHub stars
- 12.3K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add memtensor/memos --skill memos-memory-guide --agent claude-codeInstalls into .claude/skills of the current project.
Files
MemOS Local Memory — Agent Guide
This skill describes how to use the MemOS memory tools so you can reliably search and use the user's long-term conversation history, query team-shared data, share tasks, and discover or pull reusable skills.
Two sharing planes exist and must not be confused:
- Local agent sharing: visible to agents in the same OpenClaw workspace only.
- Team sharing: visible to teammates through the configured team server.
How memory is provided each turn
- Automatic recall (hook): At the start of each turn, the system runs a memory search using the user's current message and injects relevant past memories into your context. You do not need to call any tool for that.
- When that is not enough: If the user's message is very long, vague, or the automatic search returns no memories, you should generate your own short, focused query and call
memory_searchyourself. - Memory isolation: Each agent can only see its own local private memories and local
publicmemories. Team-shared data only appears when you search withscope="group"orscope="all".
Tools — what they do and when to call
memory_search
Sponsors
Details
- Repository
- github.com/memtensor/memos
- Categories
- Documentation, Release Management
- First seen
- Jun 3, 2026