This guide provides an overview of hosting Agent2Agent (A2A) agents onCloud Run.

For an introduction on A2A concepts, seeKey Concepts in A2A.

Relationship of AI Agents and the A2A Protocol

AI Agents are software programs that can perceive their environment, makedecisions, and take autonomous actions to achieve specific goals. These agentsare becoming increasingly sophisticated, often leveraging Large Language Models(LLMs) for complex tasks like reasoning, planning, and natural languageinteractions.

As more specialized AI agents are developed, the need for them to communicateand collaborate becomes essential. TheAgent2Agent (A2A) Protocol is an openstandard designed to enable seamless and secure communication andinteroperability between AI agents, even if they are built using differentframeworks, by different vendors, or are running on separate servers. A2A allowsagents to work together as peers without exposing their internal state or logic.

The following diagram illustrates the architecture of an A2A Agent system,showing an A2A Client (user or agent) interacting with the A2A Agent:

The A2A Agent's core is a serving and orchestration layer, such asCloud Run. This layer manages interactions with AI models likeGemini and Vertex AI, memory storages like AlloyDB andA2A TaskStore, and external tools through APIs. Clients interact with the agentby sending requests, such as "Get Agent Card" or "send message," and receivetask updates.

For information about A2A request lifecycle, see theA2A Request Lifecyclesection.

What's next

• To learn the practical steps for deploying your own A2A agents, seeBuild and deploy an A2A agent on Cloud Run.