The Agent2Agent Protocol (A2A), the open standard that lets AI agents discover one another, delegate tasks and exchange work across different frameworks and vendors, has joined the Agentic AI Foundation (AAIF) as a hosted project. The foundation announced the move on Monday, positioning A2A and the Model Context Protocol (MCP) as complementary pillars of an emerging open "agentic stack." For more stories like this, see our breaking AI news coverage.
A2A addresses one of the most persistent headaches in deploying multi-agent systems: agents built on different frameworks historically could not hand off work to each other without custom integration code written for each pairing. "The cost wasn't in the agents themselves but in the integrations between them," the foundation wrote in its announcement.
The protocol works through structured discovery. An agent publishes an "agent card" — a machine-readable description of what it can do and how to reach it. Other agents read the card and delegate tasks without a human brokering the handoff.
From Google project to neutral foundation
Google launched A2A in April 2025 and later donated it to the Linux Foundation, with founding organizations including AWS, Cisco, Google, Microsoft, Salesforce, SAP and ServiceNow. In August 2025, IBM's Agent Communication Protocol merged into A2A — an early signal that the field was consolidating around 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 support, and signed agent cards for cryptographic identity verification — features aimed squarely at enterprise deployment and security requirements, as Techstrong.ai's Steven Vaughan-Nichols reported. The stable spec arrived roughly a year after the protocol's public debut, an unusually fast maturation for infrastructure software.
The AAIF says the project is now backed by more than 150 organizations and is running in production across supply chains, financial services, enterprise IT and mobile platforms. "Pretty impressive for a protocol that's just over a year old," Vaughan-Nichols wrote.
Running at operating-system scale
Among the most striking deployments cited by the foundation: Huawei has standardized A2A as the protocol between Celia, its operating-system-level AI assistant on HarmonyOS, and in-app agents across the developer platform. Supported scenarios include Celia handing long-running tasks to an app agent, controlling app interfaces through an agent, and requesting contextual recommendations.
Tencent's WeChat is among the first major applications integrating with Huawei and other Android OEM assistants over A2A, enabling messages, voice calls and video calls initiated through an AI assistant — with the flow protected by dual authorization through the protocol.
"This is agent communication between an OS assistant and an application running at mobile platform scale," the foundation noted.
Why governance matters
For the companies betting on agentic AI, the transfer of A2A to a neutral foundation is as consequential as the technology itself. Open standards governed by foundations — rather than controlled by a single vendor — reduce the risk of lock-in for enterprises wiring multi-agent systems into core operations. As Techstrong.ai reported, A2A will now be managed alongside MCP under the AAIF, giving the two dominant agent protocols a shared, vendor-neutral home.
Not everyone in the industry welcomes the consolidation, and questions remain about how quickly rival standards efforts will align. But with more than 150 organizations behind it and production deployments spanning mobile operating systems to supply chains, A2A's move to the AAIF marks a significant step toward the interoperable agent ecosystem that enterprises have been waiting for.
---
Stay Ahead of AIGet the latest AI news, analysis, and breakthroughs — all in one place.
