Feature Request: Native Support for A2A Protocol (Remote Agents as Sub-Graphs)

OSS Product Help LangGraph
,
1

Motivation

LangGraph currently supports MCP adapters via langchain-mcp-adapters, which allow external tools to be integrated as @tools.

However, in many cases external systems are not just tools but full agents — capable of reasoning, maintaining state, and returning structured results.

The emerging Agent-to-Agent (A2A) protocol provides a standard for communication between such agents. Supporting A2A natively in LangGraph would allow users to seamlessly add remote agents as first-class nodes/sub-graphs.

Problem

  • Today, connecting to a remote agent requires custom handoff implementations (handoffs guide) or custom commands.

  • This is not ergonomic, and doesn’t fully capture the semantics of stateful remote agents.

  • Users should be able to declare remote agents just as easily as they do with tools.

Proposed Solution

Introduce a new concept of RemoteAgentNode (similar to ToolNode), backed by an A2A adapter/client.

Prototype Architecture

  • RemoteAgent: Represents a remote agent endpoint.

  • RemoteAgentNode: Wraps RemoteAgent for integration into LangGraph execution.

  • A2AClient: Handles transport and protocol translation.

Message Flow:
LangGraph (handoff)
↓
RemoteAgentNode.run()
↓
RemoteAgent.call()
↓
A2AClient.send()
↓
[A2A protocol transport: HTTP/WebSocket/gRPC/etc.]
↓
Remote Agent
↓
Response (state update)
↓
RemoteAgentNode returns to LangGraph

To keep scope small, the first PR could implement:

  1. RemoteAgentNode with blocking handoff only

    • Synchronously send state → wait for full response → return to LangGraph.

    • No streaming, concurrency, or advanced orchestration.

  2. Minimal A2AClient abstraction

    • Just use HTTP transport with JSON payloads (later pluggable for WebSocket/gRPC).

  3. Simple Example Notebook

    • One remote agent integrated into a LangGraph, demonstrating a blocking handoff.

This keeps the first PR low-risk, reviewable, and easy to merge.
Future PRs can then add streaming, concurrent orchestration, memory federation, etc.

Extensions

  • Streaming support: Pass remote agent’s token/thought stream back into LangGraph channels.

  • Memory federation: Allow sharing of selected history/state with remote agents.

  • Parallel orchestration: Enable multiple remote agents to run concurrently as graph branches.

2

Hey @Adithya1617 ! Have you checked out A2A endpoint in LangGraph Server - Docs by LangChain ?

3

My understanding is that A2A endpoint allows the agents to send/receive messages, it does not share the state. So the remote agent is not first-class nodes/sub-graphs as mentioned in the original feature request.

Can you comment if above understanding is correct?

Any there plans to implement the original feature request?

4

Based on my understanding there is no support for converting an existing agent created using create_agent to a2a , other than need to use agent server.

What is the scenario if i have to mount to my existing fastapi , or want to deploy on aws lambda as a serverless.

I was looking for a similar implementation such as adk-python/src/google/adk/a2a/utils/agent_to_a2a.py at 7623ff1a27c412ff9b758bb76701e2daff570741 · google/adk-python · GitHub

Thank you