✨ Awesome A2A (Agent2Agent Protocol) ✨

A curated list of awesome resources, implementations, tools, and examples related to the Agent2Agent (A2A) Protocol for AI agent interoperability.

Deutsch | English | Español | français | 日本語 | 한국어 | Português | Русский | 中文

The Agent2Agent (A2A) Protocol is revolutionizing how AI agents communicate and collaborate - enabling seamless interoperability across different frameworks, vendors, and platforms. This repository collects the best resources to help developers build A2A-compatible agents.

• 🤔 What is A2A? (Briefly)
• 💡 Key Principles
• ⚙️ How Does A2A Work? (High Level)
• 🚀 Getting Started with A2A
• 🏛️ Official Resources
• 📜 Specification & Core Concepts
• ⚙️ Implementations & Libraries
  • Official Samples
  • Framework Integrations (Official Samples)
  • Community Implementations
    • SDKs & Libraries (by language)
    • Frameworks
    • Platforms & Integrated Solutions
• 🛠️ Tools & Utilities
• 📚 Tutorials & Articles
• 🎬 Demos & Examples
• 🔗 Related Protocols & Concepts
• 💬 Community
• Contributing

A2A (Agent2Agent) is an open protocol from Google and partners enabling different AI agents (from various vendors/frameworks) to communicate securely and collaborate on tasks. It aims to break down silos between isolated agent systems, allowing for more complex cross-application automation.

⭐ Official Website: a2aproject.github.io/A2A | ⭐ Official GitHub: github.com/a2aproject/A2A | 🌐 Multilingual Docs (EN/ZH/JA): agent2agent.ren

• Simple: Uses existing standards (HTTP, JSON-RPC, SSE).
• Enterprise Ready: Focuses on Auth, Security, Privacy, Monitoring.
• Async First: Handles long-running tasks & human-in-the-loop.
• Modality Agnostic: Supports Text, Files, Forms, Streams, etc.
• Opaque Execution: Agents interact without sharing internal logic/tools.

1. Discovery: Agents publish an Agent Card (JSON) describing capabilities, endpoint, and auth needs.
2. Communication: A Client agent sends a Task request (containing a Message with Parts) to a Remote Agent (Server) using HTTP/JSON-RPC 2.0.
3. Execution & Response: The Server processes the task, updating its status. It responds with the final status and any generated Artifacts (results, also containing Parts).
4. Updates: For long tasks, the Server can optionally stream TaskStatusUpdateEvent or TaskArtifactUpdateEvent via Server-Sent Events (SSE) or use Push Notifications.

For details, see the Official Technical Documentation.

New to A2A? Here's a suggested path:

1. Understand the Basics: Read the sections above (What is A2A?, Key Principles, How it Works). Check the 📰 Announcement Blog Post.
2. Explore Core Concepts: Dive into the 📖 Official Technical Documentation, focusing on Agent Card, Task, Message, Part, and Artifact.
3. See it in Action: Watch the 🎥 Official Demo Video and explore the code for the 🌐 Multi-Agent Web App Demo.
4. Run the Samples: Clone the Official Samples Repo and follow its instructions to run a client (like the CLI) and a sample agent (e.g., LangGraph or Genkit agent).
5. Review the Code: Look at the common (Python) or server/client (JS/TS) libraries in the official samples to see how A2A communication is implemented.
6. Try Building: Adapt a sample or use a library to create your own basic A2A agent or client.

• 📄 A2A Protocol Website - The main documentation site.
• 💻 google/A2A GitHub Repository - Source code for the spec, docs, and official samples.
• 📰 Google Developers Blog Post - Announcement blog post explaining the motivation and partners.

(See How Does A2A Work? above for summaries)

• 📖 A2A Technical Documentation - (Full Details) Detailed explanation of actors, transport, auth, core objects (Task, Artifact, Message, Part), Agent Card, etc.
• 📄 JSON Specification - The raw JSON schema definition for A2A structures.
• 💡 Key Principles (Docs) - Link to the principles section in the official docs.
• 🃏 Agent Card Specification (Docs) - Link to the Agent Card section in the official docs.
• 🗺️ Agent Discovery (Topic) - Discussion on how clients can find agent cards.
• 🔔 Push Notifications (Topic) - Details on the push notification mechanism.
• 🛡️ Enterprise Readiness (Topic) - Discussion on security, auth, privacy aspects.

These demonstrate basic A2A client/server communication.

Quick Start First-time users: try TypeScript Movie Recommendation Agent, Python Hello World, or Go Go Reference Impl — minimal dependencies and the simplest startup commands.

These show how agents built with specific frameworks can expose an A2A interface.

• Go
  • 🌟 trpc-a2a-go by @trpc-group - Go A2A implementation by the tRPC team featuring full client/server support, in-memory task management, streaming responses, session management, multiple auth methods (JWT, API Key, OAuth2), and comprehensive examples.
  • 🌟 a2a-go by @a2aserver - A Go library for building A2A servers, with example implementations.
  • 🌟 a2a-go by @yeeaiclub - Agent-to-Agent Protocol Implementation for Go, fully supports all methods of the A2A protocol, referring to the official Python SDK implementation.
• Rust
  • 🌟 a2a-rs by @EmilLindfors - An idiomatic Rust implementation following hexagonal architecture principles.
  • 🌟 Agentic by @jeremychone - A Rust crate providing essential building blocks for agentic applications, with an ergonomic API for MCP and A2A support. (Work in Progress)
• Python
  • 🌟 a2a-python by @a2aproject - Official Python SDK for running agentic applications as A2A servers following the Agent2Agent Protocol.
  • 🌟 a2a_min by @pcingola - A minimalistic Python SDK for A2A communication.
  • 🌟 python-a2a by @themanojdesai - An easy-to-use Python library for implementing the A2A protocol.
  • 🌟 A2AServer by @johnson7788 - A Python server framework implementing Google's A2A protocol with MCP integration.
  • 🌟 adk-modular-architecture by @k-jarzyna - A Python project demonstrating a modular architecture for ADK (Agent Development Kit) based agents, with A2A protocol considerations.
• C#/.NET
  • 🌟 a2adotnet by @azixaka - A C#/.NET implementation of the A2A protocol.
  • 🌟 a2a-net by @neuroglia-io - .NET implementation of the Agent2Agent (A2A) protocol to enable secure, interoperable communication between autonomous agents across frameworks and vendors.
• JavaScript/TypeScript
  • 🌟 a2a-js by @a2aproject - Official JavaScript SDK for the Agent2Agent (A2A) Protocol.
  • 🌟 nestjs-a2a by @thestupd - A module for integrating the A2A protocol into NestJS applications.
  • 🌟 Artinet SDK by @the-artinet-project - TypeScript (Node.js) A2A compliant server/client simplifying interoperable AI agent creation, focusing on DX and production-readiness.
• Java
  • 🌟 a2a-java by @a2aproject - Official Java SDK for the Agent2Agent (A2A) Protocol.
  • 🌟 a2ajava by @vishalmysore - Java A2A server/client implementation using Spring Boot with annotations. Supports WebSockets, MCP integration, and includes enterprise/Kubernetes deployment tutorials.
  • 🌟 a2a4j by @a2ap - A2A4J is a comprehensive Java implementation of the Agent2Agent Protocol, including server, client, examples, and a starter — ready to use out of the box.

Developer-first frameworks specifically designed for building A2A-compliant agents.

• 🚀 AgentUp by @RedDotRocket - A developer-first, open-source AI agent framework designed to make agents portable, scalable, and secure. Features configuration-driven architecture, built-in OAuth2/JWT/API key authentication, automatic A2A discovery, asynchronous task management, and support for both A2A and MCP protocols. Built by engineers who've created open-source solutions powering mission-critical systems at Google, GitHub, Nvidia, Red Hat, Shopify and more.

• 🌟 AG2 (AutoGen) by @ag2ai - Open-source multi-agent framework with native A2A protocol support. Features A2aAgentServer for exposing AG2 agents as A2A services and A2aRemoteAgent for connecting to any A2A-compatible agent. Enables cross-framework interoperability (e.g., with Pydantic AI).
• 🌟 Elkar by @elkar-ai - An open-source task-management layer for AI agents — based on Google's Agent2Agent Protocol (A2A). Send, track, and orchestrate tasks across AI agents — effortlessly.
• 🌟 Aira by @IhateCreatingUserNames2 - An A2A network implementation for hosting, registering, discovering, and interacting with agents. Includes agent discovery mechanisms.
• 🌟 Cognisphere by @IhateCreatingUserNames2 - An AI agent development framework built on Google's ADK, facilitating agent creation potentially for A2A networks.
• 🌐 Grasp by @adcentury - A Self-hosted Browser Using Agent with built-in MCP and A2A support.
• 🌟 swissknife by @daltonnyx - A multi-agent chat application with MCP support, aiming to expose agents via the A2A protocol and connect to remote A2A agents as a client.
• 🌟 n8n-nodes-agent2agent by @pjawz - Adds nodes to n8n for interacting with AI agents using Google's Agent2Agent (A2A) protocol.
• 🌟 google-calendar-agent by @inference-gateway - A standalone A2A agent that can manage a user's Google Calendar, compatible with any OpenAI-compatible API for its LLM.
• 🌟 A2AApp by @tanaikech - An Agent2Agent (A2A) network built with Google Apps Script, enabling secure, decentralized AI communication and integration within Google Workspace as both an A2A server and client.

This section aims to list standalone tools and utilities related to the A2A protocol. The ecosystem is still developing, and community contributions are welcome!

• Agent Discovery Services
  • Some platform-level implementations (like Aira) include agent registration and discovery mechanisms within their features.
  • Community contributions welcome: Standalone agent directory service implementations, Agent Card search engines, etc.
• A2A Validation Tool
  • ⚙️ a2a-inspector by @a2aproject - Official validation tools for A2A agents, including compliance checking and debugging utilities.
  • ⚙️ A2A Validation Tool by @llmx-de - Cross-platform desktop app for testing & validating A2A protocol implementations, with features like multi-agent connection and session management.
  • Community contributions welcome: Online or command-line validators for checking if Agent Card, Task/Artifact structures comply with A2A JSON Schema specifications, or IDE plugins, etc.
• Monitoring/Tracing Adapters
  • Community contributions welcome: Adapters or libraries for integrating A2A task flow data into mainstream monitoring platforms like OpenTelemetry, Prometheus, Grafana, etc.
• Other Utilities
  • Community contributions welcome: e.g., A2A message construction helper tools, Agent Card generators, Mock A2A Server/Client, etc.
  • 🌟 autoa2a by NapthaAI - Easily convert agents and orchestrators from existing agent frameworks to A2A servers.

• 📄 Official A2A Conceptual Overview (README) - High-level explanation in the official repo's README.
• 🚀 Getting Started Guide (Official README) - Links to docs, spec, samples in the official repo's README.
• 🌐 Agent2Agent Protocol Documentation Site - Community-driven, open-source documentation site for the A2A protocol. Built with React/TypeScript, supports English, Chinese, and Japanese. (Source Code)
• 📄 A Survey of AI Agent Protocols - Academic paper surveying existing LLM agent communication protocols (including the category A2A falls into), classifying them, analyzing performance, and discussing future challenges.
• 📚 A2A and MCP Tutorial by @Tsadoq - A tutorial on how to use Model Context Protocol by Anthropic and Agent2Agent Protocol by Google.

• 🌐 Official Multi-Agent Web App (Python/Mesop) - Demonstrates the orchestrator agent interacting with multiple remote agents, rendering text, images, and forms. Requires running Python code.
• 🎥 Official Demo Video (Section Link) - Link to the video embedded in the official repository's README.
• 💻 Agent2Agent (A2A) Samples by @a2aproject - Official repository containing code samples and demos which use the Agent2Agent (A2A) Protocol.

• 📦 Model Context Protocol (MCP) - Complementary protocol focused on providing tools/context to agents. (A2A and MCP Discussion).
• 📞 Function Calling / Tool Use Standards - Community contributions welcome: Discussion on patterns, best practices, or relevant standards for function calling/tool use in conjunction with A2A.

• 🐞 A2A GitHub Issues - For reporting bugs or suggesting protocol improvements.
• 💬 A2A GitHub Discussions - For general questions, ideas, and community discussions about the A2A protocol.
• 🔒 Private Feedback Form - Google form for private feedback.

Let's Make Awesome A2A More Useful, Together!

A2A is still pretty new, and good resources or practical tips can be scattered. We created this list to bring the good stuff together, making it easier for everyone to find, learn, and reference.

Keeping this list high-quality and up-to-date relies on the community:

• ⭐ Star it: If you find it useful, it's a great way to show support and makes it easy to find later.
• ➕ Share what you find: Found a great library, article, tool, or even a common pitfall? Add it via an Issue or PR – let's build this resource together.
• 📣 Spread the word: Let others know about this list if they're exploring or working with A2A.

Thanks for your interest and contributions!

Contributions are welcome! 🙌 Please read the contributing guidelines first. Let's build this list together!