
M3 Memory
Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.
- GitHub stars
- 30
- tools
- 5
- transport
- STDIO
- last updated
- Oct 26, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
memory_writeSave a fact, decision, preference or configuration.
Save a fact, decision, preference or configuration.
No parameter schema in public metadata yet.
memory_searchHybrid keyword (BM25) and semantic (vector) search.
Hybrid keyword (BM25) and semantic (vector) search.
No parameter schema in public metadata yet.
memory_supersedeClose an old fact and record its replacement, keeping the history.
Close an old fact and record its replacement, keeping the history.
No parameter schema in public metadata yet.
memory_getFetch one memory by its id.
Fetch one memory by its id.
No parameter schema in public metadata yet.
memory_suggestSearch with an explicit score breakdown for every result (through `m3_call`; it does not load at startup).
Search with an explicit score breakdown for every result (through `m3_call`; it does not load at startup).
No parameter schema in public metadata yet.
Sponsors
Readme
🧠 m3 Memory
Give your AI a memory that lasts.
Your AI assistant is helpful until you start a new conversation and it has forgotten what you were working on. m3 fixes that.
Your assistants remember your projects, preferences, decisions and past work, even after you close the app, start a new session or switch to a different agent. By default everything stays on your own computer, and it works offline. m3 itself needs no cloud account or API key; your AI assistant may have its own requirements.
Details
- Repository
- github.com/skynetcmd/m3-memory
- Website
- github.com/skynetcmd/m3-memory
- Categories
- AI & LLM Tools, Search & Web Crawling
- Package
m3-memory- Transport
- STDIO
- Registry
- MCP registry, active