Skip to content
mcp/harbor
LangChain

ai memory for LangChain

io.github.alphaonedev/ai-memory

Persistent memory for any AI — zero token cost until recall

client:LangChain transport:stdio runtime:oci

Install ai memory in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "ai-memory": {
            "transport": "stdio",
            "command": "docker",
            "args": ["run", "-i", "--rm", "ghcr.io/alphaonedev/ai-memory:0.5.1"],
        }
})

tools = await client.get_tools()

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

ai memory in other clients

ai memory MCP server