Skip to content
mcp/harbor
LangChain

M3 Memory for LangChain

io.github.skynetcmd/m3-memory

Local-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@10, hybrid search, GDPR, no cloud.

client:LangChain transport:stdio runtime:pypi

Install M3 Memory in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "m3-memory": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["m3-memory"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

M3 Memory in other clients

M3 Memory MCP server