Skip to content
mcp/harbor
LangChain

dear agent for LangChain

io.github.bitmapasset/dear-agent

Your AI agent keeps your diary for you. Local-first, private, works in any agent.

client:LangChain transport:stdio runtime:npm

Install dear agent in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

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

tools = await client.get_tools()

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

dear agent in other clients

dear agent MCP server