A New Chapter for A2A: Joining the Agentic AI Foundation
The Agent2Agent (A2A) protocol has officially been accepted as a Growth Stage project at the Agentic AI Foundation (AAIF). By joining the AAIF’s open agentic stack, A2A provides an open standard for how autonomous AI agents discover each other, delegate tasks, and collaborate across distinct frameworks and vendor boundaries.
The horizontal orchestration layer
The Model Context Protocol (MCP) is the vertical integration layer that connects agents to internal tools and databases, while A2A is the horizontal protocol that enables peer-to-peer collaboration. Before A2A, handing off work between agents built on different frameworks required writing custom integration code from scratch for every new pairing. Today, an agent can publish a structured Agent Card detailing its capabilities and contact methods, allowing other independent agents to read it securely, negotiate modalities, and delegate tasks without manual intervention. See What is A2A? and A2A and MCP .
Ecosystem adoption and scale
Since reaching its stable v1.0 specification, the protocol has seen rapid adoption. It is backed by over 150 organizations and runs in production across supply chains, financial services, and mobile platforms. Major cloud providers, including Google Cloud, AWS Bedrock AgentCore Runtime, and Microsoft Azure AI Foundry, have built native A2A support directly into their infrastructure.
The enterprise SaaS ecosystem has also adopted the standard, with platforms such as ServiceNow, Salesforce, Atlassian, and SAP using A2A to connect workflows across their products. Across the developer ecosystem, major frameworks including LangGraph, CrewAI, Pydantic AI, AG2, and IBM BeeAI support A2A, reflecting industry alignment around a shared communication standard. For the organizations involved, see Partners .
Neutral governance
Foundational infrastructure must evolve openly and predictably. By operating under the Linux Foundation-directed AAIF alongside sibling projects such as MCP, goose, and AGENTS.md, A2A is protected from single-vendor constraints. This neutral governance ensures that the community shapes the standard’s roadmap, giving engineering teams the confidence to build multi-agent systems without platform lock-in. See the Roadmap .
Where to start
To get started, follow the Python tutorial , or see the Partners to learn who is already building with A2A.
Source: A New Chapter for A2A: Joining the Agentic AI Foundation (official blog) ; the AAIF announcement is on aaif.io .