Skip to content
mcp/harbor
LangChain

peon mem for LangChain

io.github.vineetv2/peon-mem

Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.

client:LangChain transport:stdio runtime:npm

Install peon mem in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "peon-mem": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "peon-mem"],
        }
})

tools = await client.get_tools()

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

peon mem in other clients

peon mem MCP server