Quick Start

Get your first A2A-compatible agent running in about 5 minutes.

Step 1 — Install

pip install a2a-adapter

Step 2 — Your First Agent (3 lines of config!)

Save the following as my_agent.py (or use the repository example ):

import asyncio
from a2a_adapter import load_a2a_agent, serve_agent
from a2a.types import AgentCard
 
async def main():
    adapter = await load_a2a_agent({
        "adapter": "n8n",
        "webhook_url": "https://your-n8n.com/webhook/workflow"
    })
    serve_agent(
        agent_card=AgentCard(name="My Agent", description="..."),
        adapter=adapter
    )
 
asyncio.run(main())

Replace https://your-n8n.com/webhook/workflow with your real n8n webhook URL

Step 3 — Start the agent server

python my_agent.py

Leave this terminal running. The server will listen on port 9000 by default. You should see log output indicating the server is ready.

Step 4 — Call the agent (second terminal)

Open a second terminal. Run the A2A client so it talks to the agent on port 9000:

• If you cloned the repo in Step 3:

  cd a2a-adapter
  python examples/04_single_agent_client.py

• If you only ran my_agent.py: clone the repo (or download the client script ), then from the repo root run:

  python examples/04_single_agent_client.py

The client sends a test message to the agent at http://localhost:9000 and prints the response. If the agent is running, you’ll see the reply in this terminal.

Other frameworks (snippets)

CrewAI Crew → A2A Agent

adapter = await load_a2a_agent({
    "adapter": "crewai",
    "crew": your_crew_instance
})

LangChain Chain → A2A Agent (with Streaming)

adapter = await load_a2a_agent({
    "adapter": "langchain",
    "runnable": your_chain,
    "input_key": "input"
})

LangGraph Workflow → A2A Agent (with Streaming)

adapter = await load_a2a_agent({
    "adapter": "langgraph",
    "graph": your_compiled_graph,
    "input_key": "messages",
    "output_key": "output"
})

Custom Function → A2A Agent

async def my_agent(inputs: dict) -> str:
    return f"Processed: {inputs['message']}"
 
adapter = await load_a2a_agent({
    "adapter": "callable",
    "callable": my_agent
})

OpenClaw Agent → A2A Agent

adapter = await load_a2a_agent({
    "adapter": "openclaw",
    "thinking": "low",
    "async_mode": True
})