Give a Microsoft AutoGen agent persistent, governed memory with MemClaw over MCP.

MemClaw is MCP-native, so an AutoGen AssistantAgent can load the full memclaw_* tool surface through autogen-ext's MCP tools.

pip install "autogen-agentchat" "autogen-ext[openai,mcp]"

import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import StreamableHttpServerParams, mcp_server_tools

async def main():
  server_params = StreamableHttpServerParams(
      url="https://memclaw.net/mcp",
      # Use an agent-scoped key in production (see Per-agent keys below).
      headers={"X-API-Key": "mc_xxx"},
  )
  tools = await mcp_server_tools(server_params)   # all memclaw_* tools

  agent = AssistantAgent(
      name="assistant",
      model_client=OpenAIChatCompletionClient(model="gpt-4o"),
      tools=tools,
  )
  print(await agent.run(task="Remember our Q3 target is $4M, then recall it."))

asyncio.run(main())

Always bind a real agent_id to the credential. For anything beyond a prototype, give each agent its own agent-scoped key — see Per-agent keys — so trust gating, fleet membership, and per-agent keystones apply.

Prefer REST?

Without MCP, wrap MemClaw's POST /api/v1/memories and POST /api/v1/recall as AutoGen FunctionTools. See REST for the request shapes.

AutoGen

Prefer REST?

On this page