Back to directory

A2A Adapter

A Python SDK and CLI that exposes an existing AI agent, whether a CLI, a workflow engine or a Python framework, as an A2A protocol server in a few lines of code.

A2A Adapter

a2a-adapter wraps agent CLIs, local agents, workflow engines and Python agent frameworks behind the Agent-to-Agent protocol, handling agent-card generation, JSON-RPC, task lifecycle and streaming through the official A2A SDK so an adapter only needs to invoke the agent it wraps. It ships adapters for Claude Code, Codex, Pi, OpenClaw, n8n, LangGraph, LangChain, CrewAI, Ollama and Hermes Agent, alongside a callable adapter for wrapping an arbitrary Python function.

The CLI exposes an already-installed local agent from the current directory without writing any code, forwarding flags after a separator straight to the underlying agent's own CLI while the adapter keeps control of protocol- and session-level flags such as a sandbox or thinking-effort setting; the Python SDK instead embeds A2A support directly into an application or a custom Python framework wrapper.

It is written in Python and installed with pip.

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.