Back to directory

A2A Directory

A community-maintained directory of resources for Google's Agent2Agent (A2A) protocol, including documentation, official and community samples, tools, and compatible services.

A2A Directory

A2A Directory collects resources for Agent2Agent (A2A), an open protocol from Google that lets AI agents communicate and collaborate over HTTP, JSON-RPC, and Server-Sent Events, aiming to break down silos between separately built agent systems. It links to the official A2A documentation, JSON and Agent Card specifications, and to community-written guides comparing A2A with MCP, implementing A2A in TypeScript and Python, and integrating it with other agent frameworks.

It lists official Python sample agents built on different frameworks, such as a Google ADK expense-report-filing agent and an AG2-plus-MCP agent, alongside community implementations, community samples, A2A-compatible services, and services that combine A2A with the x402 payment protocol. It also points to the official A2A GitHub organization and demo video for readers getting started, and to a community-maintained list of A2A implementations.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.