Google’s Agent2Agent Protocol (A2A) is joining the Agentic AI Foundation (AAIF).

Google’s A2A is an open protocol for agent-to-agent communication. It is an open standard that defines how agents communicate across framework and vendor boundaries. An agent publishes an agent card containing a structured description of what it can do and how to reach it. Other agents read that card, discover capabilities, and delegate tasks without a human brokering the handoff. The exchange is structured, observable, and framework agnostic.

Google launched A2A in April 2025 and donated it to the Linux Foundation with founding organizations like AWS, Cisco, Google, Microsoft, Salesforce, SAP, and ServiceNow. In August 2025, IBM's Agent Communication Protocol merged into A2A showing that the field was moving toward a single shared standard rather than competing ones.

A2A v1.0, the first stable specification, shipped in March 2026. It added multi-protocol bindings and version negotiation, multi-tenancy, and signed agent cards for cryptographic identity verification.

The move puts A2A under the same roof as MCP and other open agent infrastructure projects. MCP standardizes how agents connect to tools and data. A2A standardizes how agents communicate with each other. Together, they form key pieces of the infrastructure needed for large-scale, multi-agent systems.

Anthropic created MCP. Google created A2A. Rather than building competing ecosystems, both are putting these technologies under neutral governance, making it easier for the industry to build interoperable systems and move toward an open “Internet of Agents.”

A2A has grown from an internal initiative into a standard supported by AWS, Microsoft, Salesforce, SAP, ServiceNow, PayPal and others. Much as it did with Android, Google is betting that convening the ecosystem around an open standard will accelerate adoption.