An open standard for seamless communication and interoperability between AI agents
Documentation | Specification | Discussions
The Agent2Agent (A2A) Protocol is an open standard designed to facilitate communication and interoperability between independent, potentially opaque AI agent systems. In an ecosystem where agents might be built using different frameworks, languages, or by different vendors, A2A provides a common language and interaction model, enabling agents to discover capabilities, negotiate modalities, and collaborate on complex tasks.
Join this short course on A2A: The Agent2Agent Protocol, built in partnership with Google Cloud and IBM Research, and taught by Holt Skinner, Ivan Nardini, and Sandi Besen.
- 📚 Read the Documentation for guides and tutorials
- 🔍 Review the Specification for protocol details
- 💻 Use our SDKs to start building:
A2A- Core protocol specification and technical documentationa2a-python- Official Python SDK implementationa2a-js- Official JavaScript/TypeScript SDK implementationa2a-java- Official Java SDK implementationa2a-go- Official Go SDK implementationa2a-dotnet- Official C#/.NET SDK implementationa2a-samples- Example agents, clients, and multi-agent workflowsa2a-inspector- Validation tools for A2A-enabled agentsa2a-tck- Technology Compatibility Kit for implementation testing
We welcome contributions of all kinds! Whether you want to fix bugs, improve documentation, or propose new protocol extensions, please see our contributing guide to get started.
Have questions? Join the discussion in our community forum.
The Agent2Agent (A2A) Protocol is an open source project hosted by The Linux Foundation, originally contributed by Google, and open to contributions from the entire community.
