Honcho for LangChain
io.github.plastic-labs/honcho
Memory that reasons: continual learning for stateful agents. Better context, fewer tokens.
client:LangChain
transport:streamable-http
Install Honcho in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"honcho": {
"transport": "streamable_http",
"url": "https://mcp.honcho.dev",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs