Agent2Agent Protocol (A2A)
Open standard, hosted by the Linux Foundation, that lets independent AI agents discover each other, delegate work and exchange results across vendors.
Tags
Description
Agents advertise capabilities via an Agent Card and collaborate on stateful Tasks without exposing internal state, memory or tools. Per the docs' llms.txt, the normative source is the Protobuf definition, the spec text is v1.0.0 while the latest release is v1.0.1 (2026-05-28; spec bug fixes such as preferring application/a2a+json in the HTTP binding), and bindings exist for JSON-RPC 2.0 over HTTP (with SSE), gRPC and HTTP/REST. The repo moved from google/A2A to a2aproject/A2A.
Agent access
Related
- Model Context Protocol (MCP): Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.
- Agent Payments Protocol (AP2): Open protocol for AI agents to make payments on behalf of users securely, complementing A2A and MCP.
Guides & comparisons
- Make your site and API discoverable by agents (Guide): Publish the files agents look for: an RFC 9727 API catalog, an AI Catalog, an MCP Server Card, an Agent Skills index and llms.txt. Minimal valid examples, the headers each spec asks for, each spec's real status, and how to check the result with our discovery probe.
- Discover a site's agent interfaces (Skill): A probe-then-pick workflow for finding the best machine interface a website offers (MCP, A2A, OpenAPI, Agent Skills, llms.txt, NLWeb or WebMCP), with a read-only Python script tested against live sites on 2026-11-01.
Sources
- https://a2a-protocol.org/llms.txt
- https://github.com/a2aproject/A2A
- https://github.com/a2aproject/A2A/releases/tag/v1.0.1
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)