Google’s Agent2Agent project moves to Linux Foundation

The Linux Foundation is the new home of the Agent2Agent (A2A) protocol, an open protocol developed by Google to enable agentic AI interoperability and trusted agent communication across systems and platforms.

Launched by Google in April, the A2A protocol addresses the need for agents to operate in dynamic, multi-agent environments. A2A enables autonomous agents to discover one another, exchange information securely, and collaborate across systems, which in turn allows developers to unite agents from multiple sources and platforms, improving modularity, mitigating vendor lock-in, and accelerating innovation, the Linux Foundation said in a June 23 announcement. Developers can go to the A2A repository on GitHub to learn more about the protocol and follow the progress of the project.

The A2A project is being formed with participation from Amazon Web Services, Cisco, Google, Microsoft, Salesforce, SAP, and ServiceNow, Google said in a blog post, also dated June 23. Under Linux Foundation governance, A2A will remain vendor-neutral, emphasize inclusive contributions, and continue the protocol’s focus on extensibility, security, and real-world usability, the Linux Foundation said. “By joining the Linux Foundation, A2A is ensuring the long-term neutrality, collaboration, and governance that will unlock the next era of agent-to-agent powered productivity,” said Jim Zemlin, executive director of the Linux Foundation.

“The Agent2Agent protocol establishes a vital open standard for communication, enabling the industry to build truly interoperable AI agents across diverse platforms and systems,” said Rao Surapaneni, vice president and GM of Business Applications Platform, Google Cloud. “By collaborating with the Linux Foundation and leading technology providers, we will enable more innovative and valuable AI capabilities under a trusted, open-governance framework.”