✨ Awesome A2A (Agent2Agent Protocol) ✨

English | 简体中文 | 日本語 | Español | Deutsch | Français

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

Contents

• 🤔 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)
    • Platforms & Integrated Solutions
• 🛠️ Tools & Utilities
• 📚 Tutorials & Articles
• 🎬 Demos & Examples
• 🔗 Related Protocols & Concepts
• 💬 Community
• Contributing

---

🤔 What is A2A? (Briefly)

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

💡 Key Principles

• 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.

⚙️ How Does A2A Work? (High Level)

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.

---

🚀 Getting Started with A2A

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 Repo and follow the instructions in /samples to run a client (like the CLI) and a sample agent (e.g., LangGraph or Genkit agent). See the Official Samples tables below for links.
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.

---

🏛️ Official Resources

• 📄 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.

📜 Specification & Core Concepts

(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.

⚙️ Implementations & Libraries

Official Samples

These demonstrate basic A2A client/server communication.

Language	Type	Framework	Description	Link
🐍 Python	Common Library	-	Core HTTP, JSON-RPC, SSE handling	Link
🐍 Python	Host (Client)	CLI	Command-line client example	Link
🐍 Python	Host (Agent)	ADK	Orchestrator agent delegating to A2A agents	Link
🚀 JS/TS	Server Library	Express	Core server implementation	Link
🚀 JS/TS	Client Library	-	Client implementation	Link
🚀 JS/TS	Host (Client)	CLI	Command-line client example	Link

Framework Integrations (Official Samples)

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

Language	Agent Framework	Agent Description	Key A2A Features Demonstrated	Link
🐍 Python	LangGraph	Currency conversion	Tools, Streaming, Multi-turn	Link
🐍 Python	CrewAI	Image generation	Non-textual Artifacts (Files)	Link
🐍 Python	Google ADK	Expense reimbursement	Multi-turn, Forms (DataPart)	Link
🚀 JS/TS	Genkit	Movie info / Code generation	Tools, Artifacts (Files), Async	Link

Community Implementations

SDKs & Libraries (by language)

• 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.
• 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 @google - 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.
• C#/.NET
  • 🌟 a2adotnet by @azixaka - A C#/.NET implementation of the A2A protocol.
• JavaScript/TypeScript
  • 🌟 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
  • 🌟 a2ajava by @vishalmysore - Java A2A server/client implementation using Spring Boot with annotations. Supports WebSockets, MCP integration, and includes enterprise/Kubernetes deployment tutorials.

Platforms & Integrated Solutions

• 🌟 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.

🛠️ Tools & Utilities

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 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.

📚 Tutorials & Articles

• 📄 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.

🎬 Demos & Examples

• 🌐 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.

🔗 Related Protocols & Concepts

• 📦 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.

💬 Community

• 🐞 google/A2A GitHub Issues - For reporting bugs or suggesting protocol improvements.
• 💬 google/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!

---

Contributing

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