A2A Moves to the Linux Foundation
Google has donated A2A to the Linux Foundation, with seven competing vendors jointly backing the project. We examine the facts, technical scope, and remaining gaps, and explain why neutral governance matters for agent interoperability across organizational boundaries.
Agents Do Not Interoperate by Default
Almost every major software vendor now ships an agent platform. Copilot Studio, Agentforce, Google's Agent Development Kit, and dozens of open-source frameworks use their own message formats, task lifecycles, and authentication schemes. Delegating work across two platforms therefore requires custom integration code. With n platforms, the estate can grow to n² point-to-point adapters. The enterprise integration problem of the 2000s is returning — this time with agents.
Shared protocols reduce that quadratic cost. Since November 2024, Anthropic's Model Context Protocol (MCP) has standardized how agents reach tools and data. Communication between agents, especially across organizational boundaries, remained the missing layer. Google published A2A in April 2025 for precisely that purpose. Yet as long as one vendor controlled the protocol, governance risk continued to slow adoption. The June 23 transfer addresses that risk.
The Announcement in Facts
At Open Source Summit North America in Denver, the Linux Foundation announced the Agent2Agent project on June 23, 2025. Google transfers the A2A protocol specification, the accompanying SDKs, and developer tooling to the new entity. The founding participants are Amazon Web Services, Cisco, Google, Microsoft, Salesforce, SAP, and ServiceNow. More than 100 companies support the protocol; AWS and Cisco are its newest validators. The code now lives under the a2aproject organization on GitHub.
Jim Zemlin, Executive Director of the Linux Foundation, framed the move as securing "long-term neutrality, collaboration and governance". The wording is standard for foundation announcements. The signal is not: five of the seven founding participants operate competing agent platforms. They are now committed to one wire format.
Project scope goes beyond the specification text. The transfer covers the SDKs, npm packages, sample implementations, and developer tooling that Google built since April. Under Linux Foundation rules, the project gets open technical governance: maintainers, public contribution paths, and vendor-neutral decision processes.
From Vendor Launch to Foundation Project
The timeline is unusually compressed for a standards effort. Google announced A2A on April 9, 2025 at Cloud Next, with more than 50 partners — Microsoft and AWS notably absent. Microsoft joined the working group on May 7 and committed A2A support for Azure AI Foundry and Copilot Studio. AWS and Cisco arrived with the foundation move. Eleven weeks passed between public launch and donation.
The speed is deliberate. Agent platforms are already being deployed, and every month without a common protocol creates more proprietary integrations that must later be removed. Google said in April that a production-ready version was planned for later in the year. Moving governance out before 1.0 reverses the usual order and reduces the risk of fragmentation early.
| Date | Event |
|---|---|
| 25 Nov 2024 | Anthropic releases the Model Context Protocol (MCP) |
| 9 Apr 2025 | Google announces A2A at Cloud Next with 50+ partners |
| 7 May 2025 | Microsoft joins the A2A working group; support planned for Azure AI Foundry and Copilot Studio |
| 23 Jun 2025 | Linux Foundation launches the Agent2Agent project with seven founding participants |
What the Protocol Specifies
The current specification is version 0.2. A2A uses JSON-RPC 2.0 over HTTPS as its transport. Every A2A server publishes an Agent Card: a JSON document describing identity, capabilities, skills, service endpoint, and authentication requirements. Clients use the card for discovery and to negotiate how to interact. Authentication reuses established schemes — OAuth 2.0, API keys, OpenID Connect — declared per agent rather than reinvented by the protocol.
Interaction is task-oriented. A client sends a message; the server creates a task with a defined lifecycle: submitted, working, input-required, completed, failed, or canceled. Outputs are typed artifacts. For incremental results, servers stream status and artifact updates over Server-Sent Events. For long-running work — hours or days — push notifications deliver updates to a client webhook. Messages carry typed parts, so agents can negotiate formats beyond plain text.
Why Neutral Governance Matters
A wire protocol is infrastructure, and no company builds cross-organizational workflows on a format that a competitor can change unilaterally. Foundation ownership shifts that control: the specification, trademarks, and repositories sit with a neutral nonprofit, while changes follow open governance rather than a vendor roadmap. Intellectual property management and long-term stewardship are therefore not side issues; they are explicit goals of the transfer.
Clear precedents show why this matters. Google donated Kubernetes to the newly formed CNCF in 2015; that neutrality helped it become the default orchestration layer without tying competitors strategically to Google. OpenTelemetry followed the same path for observability, and A2A now takes it for agent communication. AWS contributing to a Google-initiated protocol is visible evidence that neutrality changed the calculus.
What A2A Does Not Solve
A2A defines the conversation between agents, not the agents. It does not specify orchestration logic, reasoning quality, model selection, or how a task is actually executed. It does not replace MCP: MCP connects an agent vertically to tools and data, A2A connects agents horizontally as peers. Both layers are needed, and both sides state this explicitly.
The technical gaps nevertheless remain. An Agent Card may declare cross-organizational identity federation, but it does not establish trust between two companies; that is still deployment work. There is no global discovery registry and no shared semantics for liability, billing, or auditing delegated tasks. Version 0.2 is also not a finished standard. Breaking changes before 1.0 are not merely possible but likely.
Where This Goes Next
By late June 2025, the next stage is clearly defined: harden the specification toward 1.0, add transports, and clarify identity. The foundation move should first make enterprise pilots easier, because legal and procurement teams are more receptive to a Linux Foundation standard than to a competitor's API. Cisco plans A2A support in its AGNTCY components, and AWS has announced contributions. Deliverable code from both would be the first substantive test of the new governance.
The practical vision remains grounded: a procurement agent at one company negotiates delivery windows with a logistics agent at a supplier — different vendors, different clouds, one shared protocol. That requires MCP within organizational boundaries and A2A across them. Whether A2A becomes the TCP/IP of agents or one protocol among several will be decided by implementations, not announcements. We are building against version 0.2, isolating the moving parts, and watching governance as closely as the specification.
Sources
- Linux Foundation: Launch of the Agent2Agent Protocol Project (23 Jun 2025)
- Google Developers Blog: Google Cloud donates A2A to Linux Foundation (23 Jun 2025)
- Google Developers Blog: Announcing the Agent2Agent Protocol (9 Apr 2025)
- Microsoft Cloud Blog: Empowering multi-agent apps with the open Agent2Agent (A2A) protocol (7 May 2025)
- A2A Protocol Specification v0.2.0 (2025)
- The New Stack: Google Donates the Agent2Agent Protocol to the Linux Foundation (23 Jun 2025)
