Google has bestowed ownership of its Agent2Agent (A2A) protocol to the Linux Foundation, a move announced at Open Source Summit North America that aims to establish industry-wide standards for AI agent interoperability.

AWS, Cisco, and Microsoft join the likes of Salesforce, SAP, and ServiceNow in backing the project alongside protocol developers Google to create frameworks for agent interoperability.

The Linux Foundation will manage the open-governance framework for A2A, covering topics such as trustworthy agent identity, delegated agent authority, governance policy, and agent security.

“We are happy to be the new home of the Agent2Agent Protocol project,” said Jim Zemlin, executive director of the Linux Foundation.

“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.”

What is the Agent2Agent Protocol?

First unveiled back in April, A2A is an open protocol designed to allow AI agents to securely communicate with one another.

The Google-backed concept builds on Model Context Protocol (MCP), developed by Claude creators Anthropic, which provides helpful tools and context to agents.

Essentially, A2A allows developers of agentic AI systems to connect their creations with any other agent built using the protocol, allowing end users to combine agents from a variety of vendors.

Much like how software-defined networking separated network control from individual hardware devices, A2A creates an abstraction layer for agent-to-agent communication that could reshape how enterprises design and optimize their hybrid and multi-cloud environments.

With network operators looking to deploy multiple AI agents across different cloud environments and on-prem systems, the A2A protocol is designed to address challenges around secure inter-agent communication, authentication, and service discovery – problems that network architects have been grappling with in traditional distributed systems for years.

Rao Surapaneni, VP and general manager of business application platforms at Google Cloud, said: “The Agent2Agent protocol establishes a vital open standard for communication, enabling the industry to build truly interoperable AI agents across diverse platforms and systems.

“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.”

Prior to the launch of the Linux-supported project, the likes of Langchain, PayPal, ServiceNow, and Wipro were among those supporting Google’s A2A protocol.