Agent2Agent protocol
In plain wordsAn open standard that lets AI agents built by different companies find each other, say what they can do and work together on tasks, much as email lets different mail systems exchange messages.
An open protocol through which independently built AI agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. — on different frameworks, run by different organizations — can find one another and hand off work. An agent advertises itself with an Agent Card, a machine-readable JSON profile giving the skills it offers, the address where it can be reached and the credentials callers must present, along with its name and description, so that a client agent can decide whether to delegate a task to it. Interaction is organized around tasks that move through a lifecycle (submitted, working, input-required, completed and so on), messages made of typed parts (text, files, structured data) and artifacts as outputs. Messages travel over HTTP — originally as JSON-RPC 2.0, with gRPC and REST bindings added later — with streaming responses and webhook push notifications for long-running jobs. A2A treats remote agents as opaque collaborators rather than as tools whose internals are exposed. Version 1.0, the first stable specification (March 2026), added signed Agent Cards for cryptographic identity, multi-protocol bindings, version negotiation and multi-tenancy.
Our procurement agent uses A2A to request a quote from the supplier's sales agent.
Origin
Announced by Google on 9 April 2025 with backing from more than 50 technology partners. Google donated it to the Linux Foundation on 23 June 2025, with AWS, Cisco, Microsoft, Salesforce, SAP and ServiceNow among the founding members; IBM's Agent Communication Protocol merged into it in August 2025, and in August 2026 it became a hosted project of the Agentic AI FoundationAgentic AI Foundation, prop. n.: A nonprofit group under the Linux Foundation that looks after shared, open technical standards for AI agents, such as the Model Context Protocol, so that no single company controls them..
Usage note
A2A and the Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI. are complementary: MCP connects an agent to tools and data, A2A connects agents to other agents. Google's Agent Payments Protocol (AP2) extends it for agentic commerceagentic commerce, n.: Shopping and payments carried out by AI agents for people — finding products, comparing offers and completing purchases — within limits the person has approved.. As of August 2026 more than 150 organizations supported A2A.
Related
- Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI.
- multi-agent systemmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves.
- agent identityagent identity, n.: The ways of proving which AI agent is acting, for whom and with what permissions — so websites, companies and other agents can tell trustworthy agents from impostors and hold someone responsible.
- Agentic AI FoundationAgentic AI Foundation, prop. n.: A nonprofit group under the Linux Foundation that looks after shared, open technical standards for AI agents, such as the Model Context Protocol, so that no single company controls them.
- agentic commerceagentic commerce, n.: Shopping and payments carried out by AI agents for people — finding products, comparing offers and completing purchases — within limits the person has approved.
- handoffhandoff, n.: The moment one AI agent passes a conversation or task to another, better-suited agent — like a call-center operator transferring you to the right department.
- Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI.
Sources
- Cruz, P. (2026). A year of open collaboration: Celebrating the anniversary of A2A. Google Open Source Blog, 16 April 2026. opensource.googleblog.com/2026/04/a-year-of-open-collaboration-celebrating-the-anniversary-of-a2a.html
- Agentic AI Foundation (2026). A2A joins AAIF's open agentic stack. AAIF blog, 17 August 2026. aaif.io/blog/a2a-joins-aaif
Mentioned in
Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI., agent skillagent skill, n.: A packaged how-to guide for an AI agent — written steps, sometimes with small programs and examples attached — that sits unread until a job of that kind comes up, when the agent opens it., agentic commerceagentic commerce, n.: Shopping and payments carried out by AI agents for people — finding products, comparing offers and completing purchases — within limits the person has approved., multi-agent systemmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves., agent identityagent identity, n.: The ways of proving which AI agent is acting, for whom and with what permissions — so websites, companies and other agents can tell trustworthy agents from impostors and hold someone responsible., Agentic AI FoundationAgentic AI Foundation, prop. n.: A nonprofit group under the Linux Foundation that looks after shared, open technical standards for AI agents, such as the Model Context Protocol, so that no single company controls them.