Agent2Agent Protocol (A2A)

https://a2a-protocol.org/

Google-led open protocol for agent-to-agent collaboration (announced 2025-04-09) — agent cards, RPCs, server-sent events. Launched with 50+ technology partners including Atlassian, MongoDB, Salesforce, ServiceNow.

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 20 cited facts, 7 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Tier
T2
Created
2025-04-09 third-party fix
Latest release
v1.0.1 (2026-05-28) repo fix
License
Apache-2.0 third-party fix
Pricing
free (OSS) repo fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
open-source third-party fix
Platform vs product
platform vendor fix
Protocols
a2a repo fix

When to use

Optimised for: searched not found

Anti-fit: searched not found

Pros & cons

Pros

searched not found

Cons

searched not found

Claims & capabilities

Announced 2025-04-09 with support from 50+ technology partners (e.g. Atlassian, Box, Cohere, LangChain, MongoDB, PayPal, Salesforce, SAP, ServiceNow, Workday) plus service providers such as Accenture, Deloitte, KPMG.

Technical surface

API surface
searched not found
Backend storage
not applicable — not a memory product
Deployment
Self-hosted only — open protocol spec + SDKs
Embedding model
not applicable — not a memory product
Multi-tenancy
searched not found
MCP
searched not found
A2A
yes — this is the A2A protocol specification itself
OpenTelemetry
searched not found

Similar systems

Other agent frameworks (no first-party memory layer) in the catalog, ranked by inbound references.

  • Model Context Protocol (MCP spec) T1

    Anthropic-introduced open protocol (Nov 2024) for connecting LLMs to data sources and tools. Donated by Anthropic to the Linux Foundation's Agentic AI Foundation (announced 2025-12-09); now governed as Model Context Protocol, a Series of LF Projects, LLC. Supported across Claude, ChatGPT, VS Code, Cursor and many other clients.

  • LangChain (framework) T1

    Dominant Python/JS framework for LLM apps — tool calling, agents, retrievers, runnables. Memory is one component (LangMem cross-listed); the framework itself is the product.

  • Vercel AI SDK T1

    Vercel's TypeScript LLM SDK — streaming, tool calls, structured outputs, agents. Dominant framework for Next.js LLM apps.

  • LlamaIndex (framework) T1

    Data framework for LLM apps — connectors, indices, query engines, agents, workflows. Memory is one of many subsystems (LlamaIndex Memory cross-listed).

  • OpenAI Agents SDK T1

    OpenAI's official Python framework for agents — handoffs, guardrails, tracing built in. Successor to OpenAI Swarm (experimental); officially supported.

  • LangGraph (orchestration) T1

    LangChain's stateful graph runtime for agents — explicit state, persistence, time-travel debugging, human-in-the-loop. Memory is one persistence target (LangGraph Persistence cross-listed).

Sources (19 cited facts, 7 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-29
    • Homepage “https://google.github.io/A2A/” → “https://a2a-protocol.org/”
    #305
  2. 2026-10-26
    • Latest release first recorded as “v1.0.1 (2026-05-28)” source
    • Pricing first recorded as “free (OSS)” source
    • Funding / ownership first recorded as “n/a — open-source project under the Linux Foundation, contributed by Google” source
    • Deployment first recorded as “Self-hosted only — open protocol spec + SDKs” source
    • A2A support first recorded as “yes — this is the A2A protocol specification itself” source
    #258

Related systems

Referenced by (11)

  • Agent Router (formerly Envoy AI Gateway) integrates with — Agent Router docs have an Agent2Agent (A2A) traffic capability page. (verified 2026-10-29)
  • agentgateway integrates with — agentgateway standalone docs have an A2A agent proxying page. (verified 2026-10-29)
  • AutoGen / AG2 integrates with — AG2 docs have an A2A section for serving and calling agents over the A2A protocol. (verified 2026-10-29)
  • Braintrust integrates with — Braintrust docs have a Agent2Agent Protocol (A2A) integration page. (verified 2026-10-29)
  • CrewAI integrates with — CrewAI docs have an A2A agent delegation guide. (verified 2026-10-29)
  • Galileo integrates with — Galileo's third-party integrations docs list Agent2Agent Protocol (A2A) as a supported integration. (verified 2026-10-29)
  • IBM ContextForge MCP Gateway integrates with — IBM ContextForge docs have a A2A (Agent-to-Agent) integration page. (verified 2026-10-29)
  • Keycard integrates with — Keycard docs have an Agent-to-Agent SDK page using the A2A protocol. (verified 2026-10-29)
  • LiteLLM integrates with — LiteLLM docs describe an Agent Gateway for invoking agents over the A2A protocol. (verified 2026-10-29)
  • Strands Agents (AWS) integrates with — Strands Agents vended tools include an A2A Client tool for remote A2A-protocol agents. (verified 2026-10-29)
  • Vercel AI SDK integrates with — AI SDK docs have an A2A community provider page. (verified 2026-10-29)