{"id":87502,"url":"https://github.com/ai-boost/awesome-a2a","name":"awesome-a2a","description":"Agent2Agent (A2A) – awesome A2A agents, tools, servers \u0026 clients, all in one place.","projects_count":281,"last_synced_at":"2026-08-03T02:00:19.185Z","repository":{"id":287169235,"uuid":"963772821","full_name":"ai-boost/awesome-a2a","owner":"ai-boost","description":"Agent2Agent (A2A) – awesome A2A agents, tools, servers \u0026 clients, all in one place.","archived":false,"fork":false,"pushed_at":"2026-07-23T19:26:21.000Z","size":751,"stargazers_count":633,"open_issues_count":96,"forks_count":144,"subscribers_count":12,"default_branch":"main","last_synced_at":"2026-07-23T21:10:07.762Z","etag":null,"topics":["a2a","a2a-cli","a2a-mcp","a2a-protocol","a2a-server","agent","agent2agent","mcp"],"latest_commit_sha":null,"homepage":"http://agent2agent.ren/","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ai-boost.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-04-10T07:27:20.000Z","updated_at":"2026-07-23T19:26:26.000Z","dependencies_parsed_at":"2025-04-25T10:34:32.955Z","dependency_job_id":"b45af74f-9b07-409f-a747-969881f68c8a","html_url":"https://github.com/ai-boost/awesome-a2a","commit_stats":null,"previous_names":["ai-boost/awesome-a2a"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ai-boost/awesome-a2a","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-boost%2Fawesome-a2a","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-boost%2Fawesome-a2a/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-boost%2Fawesome-a2a/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-boost%2Fawesome-a2a/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ai-boost","download_url":"https://codeload.github.com/ai-boost/awesome-a2a/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-boost%2Fawesome-a2a/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36214553,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-08-03T02:00:06.975Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2025-04-10T15:56:41.474Z","updated_at":"2026-08-03T02:00:19.185Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["⚙️ Implementations \u0026 Libraries","🔗 Related Protocols \u0026 Concepts","📜 Specification \u0026 Core Concepts","🚀 Getting Started with A2A","🎬 Demos \u0026 Examples","🏛️ Official Resources","💬 Community","🛠️ Tools \u0026 Utilities","📚 Tutorials \u0026 Articles"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003ch1\u003e✨ Awesome A2A (Agent2Agent Protocol) ✨\u003c/h1\u003e\n\n  \u003cimg src=\"assets/banner.png\" alt=\"Awesome A2A Banner - Abstract network or connection graphic\" width=\"100%\"\u003e\n\n  \u003cp align=\"center\"\u003e\n    A curated list of awesome resources, implementations, tools, and examples related to the \u003cstrong\u003eAgent2Agent (A2A) Protocol\u003c/strong\u003e for AI agent interoperability.\n  \u003c/p\u003e\n\n  \u003c!-- Keep these links. Translations will automatically update with the README. --\u003e\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://zdoc.app/de/ai-boost/awesome-a2a\"\u003eDeutsch\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/en/ai-boost/awesome-a2a\"\u003eEnglish\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/es/ai-boost/awesome-a2a\"\u003eEspañol\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/fr/ai-boost/awesome-a2a\"\u003efrançais\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/ja/ai-boost/awesome-a2a\"\u003e日本語\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/ko/ai-boost/awesome-a2a\"\u003e한국어\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/pt/ai-boost/awesome-a2a\"\u003ePortuguês\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/ru/ai-boost/awesome-a2a\"\u003eРусский\u003c/a\u003e |\n    \u003ca href=\"https://zdoc.app/zh/ai-boost/awesome-a2a\"\u003e中文\u003c/a\u003e\n  \u003c/p\u003e\n\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://awesome.re\"\u003e\u003cimg src=\"https://awesome.re/badge.svg\" alt=\"Awesome\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://opensource.org/license/MIT\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-yellow.svg\" alt=\"License: MIT\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/ai-boost/awesome-a2a\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/ai-boost/awesome-a2a.svg?style=social\u0026label=Star\" alt=\"GitHub stars\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/ai-boost/awesome-a2a\"\u003e\u003cimg src=\"https://img.shields.io/github/forks/ai-boost/awesome-a2a.svg?style=social\u0026label=Fork\" alt=\"GitHub forks\"\u003e\u003c/a\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n\u003e 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.\n\n\n## Contents\n\n*   [🤔 What is A2A? (Briefly)](#-what-is-a2a-briefly)\n*   [💡 Key Principles](#-key-principles)\n*   [⚙️ How Does A2A Work? (High Level)](#️-how-does-a2a-work-high-level)\n*   [🚀 Getting Started with A2A](#-getting-started-with-a2a)\n*   [🏛️ Official Resources](#️-official-resources)\n*   [📜 Specification \u0026 Core Concepts](#-specification--core-concepts)\n*   [⚙️ Implementations \u0026 Libraries](#️-implementations--libraries)\n    *   [Official Samples](#official-samples)\n    *   [Framework Integrations (Official Samples)](#framework-integrations-official-samples)\n    *   [Community Implementations](#community-implementations)\n        *   [SDKs \u0026 Libraries (by language)](#sdks--libraries-by-language)\n        *   [Frameworks](#frameworks)\n        *   [Platforms \u0026 Integrated Solutions](#platforms--integrated-solutions)\n*   [🛠️ Tools \u0026 Utilities](#️-tools--utilities)\n*   [📚 Tutorials \u0026 Articles](#-tutorials--articles)\n*   [🎬 Demos \u0026 Examples](#-demos--examples)\n*   [🔗 Related Protocols \u0026 Concepts](#-related-protocols--concepts)\n*   [💬 Community](#-community)\n*   [Contributing](#contributing)\n\n---\n\n## 🤔 What is A2A? (Briefly)\n\nA2A (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.\n\n**⭐ Official Website:** [a2aproject.github.io/A2A](https://a2aproject.github.io/A2A) | **⭐ Official GitHub:** [github.com/a2aproject/A2A](https://github.com/a2aproject/A2A) | 🌐 **Multilingual Docs (EN/ZH/JA):** [agent2agent.ren](https://agent2agent.ren)\n\n## 💡 Key Principles\n\n*   **Simple:** Uses existing standards (HTTP, JSON-RPC, SSE).\n*   **Enterprise Ready:** Focuses on Auth, Security, Privacy, Monitoring.\n*   **Async First:** Handles long-running tasks \u0026 human-in-the-loop.\n*   **Modality Agnostic:** Supports Text, Files, Forms, Streams, etc.\n*   **Opaque Execution:** Agents interact without sharing internal logic/tools.\n\n## ⚙️ How Does A2A Work? (High Level)\n\n1.  **Discovery:** Agents publish an `Agent Card` (JSON) describing capabilities, endpoint, and auth needs.\n2.  **Communication:** A `Client` agent sends a `Task` request (containing a `Message` with `Parts`) to a `Remote Agent (Server)` using HTTP/JSON-RPC 2.0.\n3.  **Execution \u0026 Response:** The Server processes the task, updating its `status`. It responds with the final status and any generated `Artifacts` (results, also containing `Parts`).\n4.  **Updates:** For long tasks, the Server can optionally stream `TaskStatusUpdateEvent` or `TaskArtifactUpdateEvent` via Server-Sent Events (SSE) or use Push Notifications.\n\n*For details, see the [Official Technical Documentation](https://a2aproject.github.io/A2A/#/documentation).*\n\n---\n\n## 🚀 Getting Started with A2A\n\nNew to A2A? Here's a suggested path:\n\n1.  **Understand the Basics:** Read the sections above ([What is A2A?](#-what-is-a2a-briefly), [Key Principles](#-key-principles), [How it Works](#️-how-does-a2a-work-high-level)). Check the 📰 [Announcement Blog Post](https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/).\n2.  **Explore Core Concepts:** Dive into the 📖 [Official Technical Documentation](https://a2aproject.github.io/A2A/#/documentation), focusing on `Agent Card`, `Task`, `Message`, `Part`, and `Artifact`.\n3.  **See it in Action:** Watch the 🎥 [Official Demo Video](https://storage.googleapis.com/gweb-developer-goog-blog-assets/original_videos/A2A_demo_v4.mp4) and explore the code for the 🌐 [Multi-Agent Web App Demo](https://github.com/a2aproject/A2A/tree/v0.2.1/demo).\n4.  **Run the Samples:** Clone the [Official Samples Repo](https://github.com/a2aproject/a2a-samples) and follow its instructions to run a client (like the CLI) and a sample agent (e.g., LangGraph or Genkit agent).\n5.  **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.\n6.  **Try Building:** Adapt a sample or use a library to create your own basic A2A agent or client.\n\n---\n\n## 🏛️ Official Resources\n\n*   📄 [A2A Protocol Website](https://a2aproject.github.io/A2A) - The main documentation site.\n*   💻 [google/A2A GitHub Repository](https://github.com/a2aproject/A2A) - Source code for the spec, docs, and official samples.\n*   📰 [Google Developers Blog Post](https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/) - Announcement blog post explaining the motivation and partners.\n*   📰 [How A2A is Building a World of Collaborative Agents](https://developers.googleblog.com/how-a2a-is-building-a-world-of-collaborative-agents/) - 2026 official update on real-world A2A adoption, partner momentum, and the growing agent ecosystem.\n*   🏷️ [A2A Protocol v1.0.0 Release](https://github.com/a2aproject/A2A/releases/tag/v1.0.0) - Official March 2026 v1.0.0 release marking the first stable A2A specification milestone, including release notes, breaking changes, and conformance updates.\n*   🏷️ [A2A Protocol v1.0.1 Release](https://github.com/a2aproject/A2A/releases/tag/v1.0.1) - Official May 2026 v1.0.1 patch release with HTTP binding, transcoding error, and TaskStatus specification fixes following the v1.0.0 milestone.\n\n## 📜 Specification \u0026 Core Concepts\n\n*(See [How Does A2A Work?](#️-how-does-a2a-work-high-level) above for summaries)*\n\n*   📖 [A2A Technical Documentation](https://a2aproject.github.io/A2A/#/documentation) - **(Full Details)** Detailed explanation of actors, transport, auth, core objects (Task, Artifact, Message, Part), Agent Card, etc.\n*   📄 [JSON Specification](https://github.com/a2aproject/A2A/tree/main/specification/json) - The raw JSON schema definition for A2A structures.\n*   💡 [Key Principles (Docs)](https://a2aproject.github.io/A2A/#/documentation?id=key-principles) - Link to the principles section in the official docs.\n*   🃏 [Agent Card Specification (Docs)](https://a2aproject.github.io/A2A/#/documentation?id=agent-card) - Link to the Agent Card section in the official docs.\n*   🗺️ [Agent Discovery (Topic)](https://a2aproject.github.io/A2A/#/topics/agent_discovery.md) - Discussion on how clients can find agent cards.\n*   🔔 [Push Notifications (Topic)](https://a2aproject.github.io/A2A/#/topics/push_notifications.md) - Details on the push notification mechanism.\n*   🛡️ [Enterprise Readiness (Topic)](https://a2aproject.github.io/A2A/#/topics/enterprise_ready.md) - Discussion on security, auth, privacy aspects.\n\n## ⚙️ Implementations \u0026 Libraries\n\n#### Official Samples\n\n*These demonstrate basic A2A client/server communication.*\n\n| Language          | Sample Name                | One-line Description                                         | GitHub URL                                                                                                                                                                              |\n| ----------------- | -------------------------- | ------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| 🔷 **TypeScript** | Genkit SDK Core            | TS SDK + CLI, builds shared code for front- and backend      | [https://github.com/a2aproject/a2a-samples/tree/main/samples/js](https://github.com/a2aproject/a2a-samples/tree/main/samples/js)                                                        |\n|                   | Movie Recommendation Agent | Movie-recommendation conversational agent built with Genkit  | [https://github.com/a2aproject/a2a-samples/tree/main/samples/js/src/agents/movie-agent](https://github.com/a2aproject/a2a-samples/tree/main/samples/js/src/agents/movie-agent)                                |\n|                   | TypeScript Client          | Pure-frontend call example written in TS                     | [https://github.com/a2aproject/a2a-samples/tree/main/samples/js/client](https://github.com/a2aproject/a2a-samples/tree/main/samples/js/client)                                          |\n|                   | Node Express Server        | A2A HTTP service implemented with Node/Express               | [https://github.com/a2aproject/a2a-samples/tree/main/samples/js/server](https://github.com/a2aproject/a2a-samples/tree/main/samples/js/server)                                          |\n| ☕ **Java**        | Custom Client              | Java client with streaming listener                          | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/custom_java_impl/client](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/custom_java_impl/client)    |\n|                   | Data Models                | Complete set of POJO data models                             | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/custom_java_impl/model](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/custom_java_impl/model)      |\n|                   | Custom Server              | Spring Boot A2A server implementation                        | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/custom_java_impl/server](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/custom_java_impl/server)    |\n|                   | Dice Agent (Multi-Transport) | Agent supporting multiple transport protocols              | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/dice_agent_multi_transport](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/dice_agent_multi_transport) |\n|                   | Magic 8-Ball (Security)    | Security-focused agent with OAuth2                           | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/magic_8_ball_security](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/magic_8_ball_security) |\n|                   | Content Writer Agent       | Content generation agent                                     | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/content_writer](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/content_writer)        |\n|                   | Content Editor Agent       | Content editing agent                                        | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/content_editor](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/content_editor)        |\n|                   | Weather MCP Agent          | Weather agent with MCP integration                           | [https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/weather_mcp](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/weather_mcp)              |\n| 💠 **.NET**       | Basic A2A Demo             | Echo and Calculator server examples                          | [https://github.com/a2aproject/a2a-samples/tree/main/samples/dotnet/BasicA2ADemo](https://github.com/a2aproject/a2a-samples/tree/main/samples/dotnet/BasicA2ADemo)                      |\n|                   | CLI Demo                   | Command-line client and server demo                          | [https://github.com/a2aproject/a2a-samples/tree/main/samples/dotnet/A2ACliDemo](https://github.com/a2aproject/a2a-samples/tree/main/samples/dotnet/A2ACliDemo)                          |\n|                   | Semantic Kernel Demo       | Integration with Semantic Kernel                             | [https://github.com/a2aproject/a2a-samples/tree/main/samples/dotnet/A2ASemanticKernelDemo](https://github.com/a2aproject/a2a-samples/tree/main/samples/dotnet/A2ASemanticKernelDemo)    |\n| 🐍 **Python**     | CLI Host                   | Command-line interface for interacting with A2A agents       | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/hosts/cli](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/hosts/cli)                                        |\n|                   | Hello World                | Recommended first-run \"Hello World\" scaffold                 | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/helloworld](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/helloworld)                          |\n|                   | LangGraph Agent            | Uses LangGraph to orchestrate multi-turn dialogue            | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/langgraph](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/langgraph)                            |\n|                   | CrewAI Agent               | Demonstrates multi-role collaboration with CrewAI            | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/crewai](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/crewai)                                  |\n|                   | Semantic Kernel Agent      | Orchestrates tools with Semantic Kernel                      | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/semantickernel](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/semantickernel)                  |\n|                   | AG2 Agent                  | Minimal AG2 mutual-call example                              | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/ag2](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/ag2)                                        |\n|                   | ADK Expense Reimbursement  | Multi-turn expense reimbursement with forms                  | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/adk_expense_reimbursement](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/adk_expense_reimbursement) |\n|                   | Birthday Planner (ADK)     | Multi-step birthday-party planner with ADK                   | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/birthday_planner_adk](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/birthday_planner_adk)    |\n|                   | Azure AI Foundry Agent     | Example using Azure AI Foundry SDK                           | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/azureaifoundry_sdk](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/azureaifoundry_sdk)         |\n|                   | A2A MCP Integration        | Multi-agent collaboration with MCP servers                   | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/a2a_mcp](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/a2a_mcp)                              |\n|                   | MCP without Framework      | Bare-metal MCP integration without frameworks                | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/a2a-mcp-without-framework](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/a2a-mcp-without-framework) |\n|                   | Travel Planner Agent       | One-stop travel-planning agent                               | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/travel_planner_agent](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/travel_planner_agent)    |\n|                   | Headless OAuth2            | OAuth2 flow for headless agents                              | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/headless_agent_auth](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/headless_agent_auth)      |\n|                   | Analytics Workflow         | Multi-agent orchestration for data-analytics                 | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/analytics](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/analytics)                            |\n|                   | A2A Telemetry              | Collects and displays agent telemetry data                   | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/a2a_telemetry](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/a2a_telemetry)                   |\n|                   | Multiagent Host            | Comprehensive multi-agent orchestration example              | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/hosts/a2a_multiagent_host](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/hosts/a2a_multiagent_host)        |\n|                   | GitHub Agent               | Agent with GitHub toolset integration                        | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/github-agent](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/github-agent)                      |\n|                   | Veo Video Generator        | Generates video via Veo API                                  | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/veo_video_gen](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/veo_video_gen)                  |\n|                   | LlamaIndex File Chat       | Q\u0026A retrieval over local files                               | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/llama_index_file_chat](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/llama_index_file_chat) |\n|                   | Marvin Agent               | Builds domain agents with Marvin                             | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/marvin](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/marvin)                                  |\n|                   | MindsDB Agent              | Calls MindsDB for prediction and querying                    | [https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/mindsdb](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/mindsdb)                                |\n| 🐹 **Go**         | Go Reference Impl          | Full A2A server + client implemented in Go                   | [https://github.com/a2aproject/a2a-samples/tree/main/samples/go](https://github.com/a2aproject/a2a-samples/tree/main/samples/go)                                                        |\n\n\u003e **Quick Start**\n\u003e First-time users: try **TypeScript `Movie Recommendation Agent`**, **Python `Hello World`**, or **Go `Go Reference Impl`** — minimal dependencies and the simplest startup commands.\n\n#### Framework Integrations (Official Samples)\n\n*These show how agents built with specific frameworks can expose an A2A interface.*\n\n| Language   | Agent Framework | Agent Description                           | Key A2A Features Demonstrated         | Link                                                                           |\n| :--------- | :-------------- | :------------------------------------------ | :-------------------------------------- | :----------------------------------------------------------------------------- |\n| 🐍 Python  | LangGraph       | Multi-turn dialogue orchestration           | Tools, Streaming, Multi-turn          | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/langgraph) |\n| 🐍 Python  | CrewAI          | Multi-role collaboration                    | Non-textual Artifacts (Files)         | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/crewai)   |\n| 🐍 Python  | Google ADK      | Expense reimbursement                       | Multi-turn, Forms (DataPart)          | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/adk_expense_reimbursement)|\n| 🐍 Python  | Semantic Kernel | Tool orchestration                          | Tools, Multi-turn                      | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/semantickernel) |\n| 🐍 Python  | AG2             | Mutual agent calls                          | Agent-to-Agent communication          | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/ag2) |\n| 🐍 Python  | Azure AI Foundry| Azure AI integration                        | Cloud deployment, Tools               | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/azureaifoundry_sdk) |\n| 🐍 Python  | LlamaIndex      | File Q\u0026A retrieval                          | RAG, Document processing              | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/agents/llama_index_file_chat) |\n| 🚀 JS/TS   | Genkit          | Movie info / Code generation                | Tools, Artifacts (Files), Async       | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/js/src/agents)          |\n| ☕ Java    | Spring Boot     | Multi-transport agent                       | HTTP/gRPC, Security                   | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/java/agents/dice_agent_multi_transport) |\n| 💠 .NET    | Semantic Kernel | .NET AI integration                         | Tools, .NET ecosystem                 | [Link](https://github.com/a2aproject/a2a-samples/tree/main/samples/dotnet/A2ASemanticKernelDemo) |\n\n#### Community Implementations\n\n##### SDKs \u0026 Libraries (by language)\n\n*   **Go**\n    *   🌟 [a2a-go](https://github.com/a2aproject/a2a-go) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-go?style=social)](https://github.com/a2aproject/a2a-go) - **Official** Go SDK for the A2A Protocol with high-level server (`a2asrv`) and client (`a2aclient`) APIs, multi-transport support (gRPC, REST, JSON-RPC), extensible architecture, and a CLI tool for agent discovery and messaging.\n    *   🌟 [trpc-a2a-go](https://github.com/trpc-group/trpc-a2a-go) by [@trpc-group](https://github.com/trpc-group) [![Stars](https://img.shields.io/github/stars/trpc-group/trpc-a2a-go?style=social)](https://github.com/trpc-group/trpc-a2a-go) - 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.\n    *   🌟 [a2a-go](https://github.com/a2aserver/a2a-go) by [@a2aserver](https://github.com/a2aserver) [![Stars](https://img.shields.io/github/stars/a2aserver/a2a-go?style=social)](https://github.com/a2aserver/a2a-go) - A Go library for building A2A servers, with example implementations.\n    *  🌟 [a2a-go](https://github.com/yeeaiclub/a2a-go) by [@yeeaiclub](https://github.com/yeeaiclub) [![Stars](https://img.shields.io/github/stars/yeeaiclub/a2a-go?style=social)](https://github.com/yeeaiclub/a2a-go) - Agent-to-Agent Protocol Implementation for Go, fully supports all methods of the A2A protocol, referring to the official Python SDK implementation.\n    *   🌟 [agent-sdk-go](https://github.com/agenticenv/agent-sdk-go) by [@agenticenv](https://github.com/agenticenv) [![Stars](https://img.shields.io/github/stars/agenticenv/agent-sdk-go?style=social)](https://github.com/agenticenv/agent-sdk-go) - Production-grade Go SDK for durable AI agents built on Temporal workflows. Features first-class A2A server/client, MCP, AG-UI streaming, sub-agents, human-in-the-loop, and OpenTelemetry. Survives crashes and deploys automatically.\n*   **Rust**\n    *   🌟 [a2a-rs](https://github.com/a2aproject/a2a-rs) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-rs?style=social)](https://github.com/a2aproject/a2a-rs) - **Official** Rust SDK for the A2A Protocol. Workspace-based implementation with core types, async client/server, gRPC/SLIMRPC bindings, SSE streaming, protobuf interop, and a CLI tool.\n    *   🌟 [ra2a](https://github.com/qntx/ra2a) by [@qntx](https://github.com/qntx) [![Stars](https://img.shields.io/github/stars/qntx/ra2a?style=social)](https://github.com/qntx/ra2a) - Comprehensive Rust SDK for A2A v1.0 with all 12 JSON-RPC methods, gRPC/SSE streaming, pluggable storage (PostgreSQL/MySQL/SQLite), OAuth 2.0/mTLS security, OpenTelemetry tracing, and composable Axum handlers.\n    *   🌟 [a2a-rs](https://github.com/EmilLindfors/a2a-rs) by [@EmilLindfors](https://github.com/EmilLindfors) [![Stars](https://img.shields.io/github/stars/EmilLindfors/a2a-rs?style=social)](https://github.com/EmilLindfors/a2a-rs) - An idiomatic Rust implementation following hexagonal architecture principles.\n    *   🌟 [Agentic](https://github.com/jeremychone/rust-agentic) by [@jeremychone](https://github.com/jeremychone) [![Stars](https://img.shields.io/github/stars/jeremychone/rust-agentic?style=social)](https://github.com/jeremychone/rust-agentic) - A Rust crate providing essential building blocks for agentic applications, with an ergonomic API for MCP and A2A support. (Work in Progress)\n    *   🌟 [jamjet-a2a](https://github.com/jamjet-labs/jamjet-a2a) by [@jamjet-labs](https://github.com/jamjet-labs) [![Stars](https://img.shields.io/github/stars/jamjet-labs/jamjet-a2a?style=social)](https://github.com/jamjet-labs/jamjet-a2a) - Standalone Rust SDK for A2A v1.0 with client, server, coordinator routing, and MCP bridge. TCK conformant (75/76 mandatory). Two crates: `jamjet-a2a-types` (pure types, zero I/O) + `jamjet-a2a` (full SDK with feature flags).\n    *   🌟 [a2a-rust](https://github.com/tomtom215/a2a-rust) by [@tomtom215](https://github.com/tomtom215) - Pure Rust SDK for A2A v1.0 with quad transport (JSON-RPC/REST/WebSocket/gRPC), SSE streaming, agent card signing (JWS/ES256), pluggable stores (SQLite/PostgreSQL), multi-tenancy, and TCK conformance. Published on crates.io as `a2a-protocol-sdk`.\n    *   🌟 [awaken](https://github.com/awakenworks/awaken) by [@awakenworks](https://github.com/awakenworks) [![Stars](https://img.shields.io/github/stars/awakenworks/awaken?style=social)](https://github.com/awakenworks/awaken) - A Rust agent runtime that serves AI SDK, CopilotKit, A2A, and MCP from the same backend, featuring type-safe state, streaming LLM failure recovery, and plugin extensibility. Published on crates.io.\n    *   🌟 [turul-a2a](https://github.com/aussierobots/turul-a2a) by [@aussierobots](https://github.com/aussierobots) [![Stars](https://img.shields.io/github/stars/aussierobots/turul-a2a?style=social)](https://github.com/aussierobots/turul-a2a) - Proto-first Rust SDK for A2A v1.0 with ergonomic server/client crates, pluggable storage (SQLite/PostgreSQL/DynamoDB), multi-transport support (HTTP/JSON-RPC/SSE/gRPC/AWS Lambda), JWT/API-key auth, and interoperability-tested against the official Go SDK. Published on crates.io.\n*   **Python**\n    *   🌟 [a2a-python](https://github.com/a2aproject/a2a-python) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-python?style=social)](https://github.com/a2aproject/a2a-python) - **Official** Python SDK for running agentic applications as A2A servers following the Agent2Agent Protocol.\n    *   🌟 [a2a_min](https://github.com/pcingola/a2a_min) by [@pcingola](https://github.com/pcingola) [![Stars](https://img.shields.io/github/stars/pcingola/a2a_min?style=social)](https://github.com/pcingola/a2a_min) - A minimalistic Python SDK for A2A communication.\n    *   🌟 [python-a2a](https://github.com/themanojdesai/python-a2a) by [@themanojdesai](https://github.com/themanojdesai) [![Stars](https://img.shields.io/github/stars/themanojdesai/python-a2a?style=social)](https://github.com/themanojdesai/python-a2a) - An easy-to-use Python library for implementing the A2A protocol.\n    *   🌟 [fasta2a](https://github.com/datalayer/fasta2a) by [@datalayer](https://github.com/datalayer) [![Stars](https://img.shields.io/github/stars/datalayer/fasta2a?style=social)](https://github.com/datalayer/fasta2a) - Framework-agnostic Python A2A server library that lets developers expose agents through ASGI with pluggable storage, broker, and worker components.\n    *   🌟 [A2AServer](https://github.com/johnson7788/A2AServer) by [@johnson7788](https://github.com/johnson7788) [![Stars](https://img.shields.io/github/stars/johnson7788/A2AServer?style=social)](https://github.com/johnson7788/A2AServer) - A Python server framework implementing Google's A2A protocol with MCP integration.\n    *   🌟 [adk-modular-architecture](https://github.com/k-jarzyna/adk-modular-architecture) by [@k-jarzyna](https://github.com/k-jarzyna) [![Stars](https://img.shields.io/github/stars/k-jarzyna/adk-modular-architecture?style=social)](https://github.com/k-jarzyna/adk-modular-architecture) - A Python project demonstrating a modular architecture for ADK (Agent Development Kit) based agents, with A2A protocol considerations.\n    *   🌟 [codex-a2a](https://github.com/liujuanjuan1984/codex-a2a) by [@liujuanjuan1984](https://github.com/liujuanjuan1984) [![Stars](https://img.shields.io/github/stars/liujuanjuan1984/codex-a2a?style=social)](https://github.com/liujuanjuan1984/codex-a2a) - Full A2A Protocol implementation for Codex CLI, providing a stateful, production-oriented agent service with standardized transport and lifecycle mapping.\n    *   🌟 [opencode-a2a](https://github.com/Intelligent-Internet/opencode-a2a) by [@Intelligent-Internet](https://github.com/Intelligent-Internet) [![Stars](https://img.shields.io/github/stars/Intelligent-Internet/opencode-a2a?style=social)](https://github.com/Intelligent-Internet/opencode-a2a) - Full A2A Protocol implementation for OpenCode, providing a stateful A2A service with production-friendly deployment, auth, and session continuity.\n    *   🌟 [a2a-adapter](https://github.com/hybroai/a2a-adapter) by [@hybroai](https://github.com/hybroai) [![Stars](https://img.shields.io/github/stars/hybroai/a2a-adapter?style=social)](https://github.com/hybroai/a2a-adapter) - Python SDK that converts agents from n8n, LangGraph, CrewAI, LangChain, Claude Code, Codex, Ollama, and more into A2A-compatible servers with auto-generated AgentCards and streaming support. Published on PyPI.\n    *   🌟 [distributed_a2a](https://github.com/Barra-Technologies/distributed_a2a) by [@Barra-Technologies](https://github.com/Barra-Technologies) [![Stars](https://img.shields.io/github/stars/Barra-Technologies/distributed_a2a?style=social)](https://github.com/Barra-Technologies/distributed_a2a) - A Python library for building and orchestrating A2A agents with a registry service, router agent, routing client, and MCP management. MIT licensed and published on PyPI as `distributed-a2a`.\n*   **Ruby**\n    *   🌟 [a2a](https://github.com/wilsonsilva/a2a) by [@wilsonsilva](https://github.com/wilsonsilva) [![Stars](https://img.shields.io/github/stars/wilsonsilva/a2a?style=social)](https://github.com/wilsonsilva/a2a) - Ruby gem implementing A2A protocol data structures with serialization, validation, and case transformation support. Published on RubyGems.\n    *   🌟 [llm.rb](https://github.com/llmrb/llm.rb) by [@llmrb](https://github.com/llmrb) [![Stars](https://img.shields.io/github/stars/llmrb/llm.rb?style=social)](https://github.com/llmrb/llm.rb) - Ruby's most capable AI runtime with A2A support via `LLM::A2A`, letting agents consume remote A2A agent skills as local tools over REST/JSON-RPC. Licensed under 0BSD.\n    *   🌟 [agent2agent](https://github.com/general-intelligence-systems/agent2agent) by [@general-intelligence-systems](https://github.com/general-intelligence-systems) [![Stars](https://img.shields.io/github/stars/general-intelligence-systems/agent2agent?style=social)](https://github.com/general-intelligence-systems/agent2agent) - Full-featured Ruby SDK for A2A with server and client implementations, JSON-RPC 2.0 and HTTP+JSON/REST bindings, SSE streaming, SQLite persistence, push notifications, 47 protocol types, and extensive guides. Built on Falcon + Async for fiber-based concurrency. Published on RubyGems as `agent2agent`. Apache 2.0.\n*   **C++**\n    *   🌟 [agent-protocol](https://github.com/openJiuwen-ai/agent-protocol) by [@openJiuwen-ai](https://github.com/openJiuwen-ai) [![Stars](https://img.shields.io/github/stars/openJiuwen-ai/agent-protocol?style=social)](https://github.com/openJiuwen-ai/agent-protocol) - C++ SDK for the Agent2Agent (A2A) Protocol (and MCP), providing implementations of agent communication protocols for C++ environments.\n    *   🌟 [a2a-cpp](https://github.com/MisterVVP/a2a-cpp) by [@MisterVVP](https://github.com/MisterVVP) [![Stars](https://img.shields.io/github/stars/MisterVVP/a2a-cpp?style=social)](https://github.com/MisterVVP/a2a-cpp) - C++20 SDK for the Agent2Agent (A2A) Protocol with client/server APIs, discovery, REST/JSON-RPC/gRPC transports, streaming, authentication hooks, and CMake/vcpkg/Conan build integration.\n*   **Common Lisp**\n    *   🌟 [mcp-lisp](https://github.com/jsulmont/mcp-lisp) by [@jsulmont](https://github.com/jsulmont) [![Stars](https://img.shields.io/github/stars/jsulmont/mcp-lisp?style=social)](https://github.com/jsulmont/mcp-lisp) - Common Lisp SDK for MCP and A2A protocols with server, client, agent, and behavioral spec engine. Implements partial A2A v1.0 support (agent card discovery, messaging, skills, and task lifecycle). Features 438 unit tests, REPL agent with multi-provider LLM support, and agent swarm capabilities. Dual-licensed under MIT OR Apache-2.0.\n*   **C#/.NET**\n    *   🌟 [a2a-dotnet](https://github.com/a2aproject/a2a-dotnet) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-dotnet?style=social)](https://github.com/a2aproject/a2a-dotnet) - **Official** C#/.NET SDK for the A2A Protocol.\n    *   🌟 [a2adotnet](https://github.com/azixaka/a2adotnet) by [@azixaka](https://github.com/azixaka) [![Stars](https://img.shields.io/github/stars/azixaka/a2adotnet?style=social)](https://github.com/azixaka/a2adotnet) - A C#/.NET implementation of the A2A protocol.\n    *   🌟 [a2a-net](https://github.com/neuroglia-io/a2a-net) by [@neuroglia-io](https://github.com/neuroglia-io) [![Stars](https://img.shields.io/github/stars/neuroglia-io/a2a-net?style=social)](https://github.com/neuroglia-io/a2a-net) - .NET implementation of the Agent2Agent (A2A) protocol to enable secure, interoperable communication between autonomous agents across frameworks and vendors.\n*   **JavaScript/TypeScript**\n    *   🌟 [a2a-js](https://github.com/a2aproject/a2a-js) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-js?style=social)](https://github.com/a2aproject/a2a-js) - **Official** JavaScript SDK for the Agent2Agent (A2A) Protocol.\n    *   🌟 [a2a-ai-provider](https://github.com/DracoBlue/a2a-ai-provider) by [@DracoBlue](https://github.com/DracoBlue) [![Stars](https://img.shields.io/github/stars/DracoBlue/a2a-ai-provider?style=social)](https://github.com/DracoBlue/a2a-ai-provider) - Community A2A provider for the Vercel AI SDK, enabling drop-in interoperability with A2A agents via `generateText` and `streamText`.\n    *   🌟 [nestjs-a2a](https://github.com/thestupd/nestjs-a2a) by [@thestupd](https://github.com/thestupd) [![Stars](https://img.shields.io/github/stars/thestupd/nestjs-a2a?style=social)](https://github.com/thestupd/nestjs-a2a) - A module for integrating the A2A protocol into NestJS applications.\n    *   🌟 [Artinet SDK](https://github.com/the-artinet-project/artinet-sdk) by [@the-artinet-project](https://github.com/the-artinet-project) [![Stars](https://img.shields.io/github/stars/the-artinet-project/artinet-sdk?style=social)](https://github.com/the-artinet-project/artinet-sdk) - TypeScript (Node.js) A2A compliant server/client simplifying interoperable AI agent creation, focusing on DX and production-readiness.\n    *   🌟 [a2a-mesh](https://github.com/oaslananka/a2a-mesh) by [@oaslananka](https://github.com/oaslananka) [![Stars](https://img.shields.io/github/stars/oaslananka/a2a-mesh?style=social)](https://github.com/oaslananka/a2a-mesh) - Production-ready TypeScript runtime for Google's A2A Protocol with multi-framework adapters, registry control plane, JWT/API-key auth, OpenTelemetry observability, CLI scaffolding, and testing toolkit. Published on npm.\n    *   🌟 [a2a-warp](https://github.com/oaslananka/a2a-warp) by [@oaslananka](https://github.com/oaslananka) [![Stars](https://img.shields.io/github/stars/oaslananka/a2a-warp?style=social)](https://github.com/oaslananka/a2a-warp) - Independent TypeScript runtime and toolkit for the A2A protocol, with server/client SDKs, registry, adapters for OpenAI/Anthropic/LangChain/Google ADK/LlamaIndex/CrewAI, CLI, MCP bridge, WebSocket/gRPC transports, and conformance tooling. Published on npm as `@oaslananka/a2a-warp`. Apache 2.0.\n    *   🌟 [a2a-reference-ts](https://github.com/reaatech/a2a-reference-ts) by [@reaatech](https://github.com/reaatech) [![Stars](https://img.shields.io/github/stars/reaatech/a2a-reference-ts?style=social)](https://github.com/reaatech/a2a-reference-ts) - Production-ready TypeScript reference implementation of Google's A2A protocol with server framework (Express/Hono adapters), client SDK, bidirectional A2A ↔ MCP bridge, canonical Zod schemas, pluggable auth (OAuth2/JWT/API key), Redis/Postgres persistence, SSE streaming, and OpenTelemetry observability. Published on npm as `@reaatech/*`.\n    *   🌟 [agent-to-agent-ts](https://github.com/A2A-tools/agent-to-agent-ts) by [@A2A-tools](https://github.com/A2A-tools) [![Stars](https://img.shields.io/github/stars/A2A-tools/agent-to-agent-ts?style=social)](https://github.com/A2A-tools/agent-to-agent-ts) - Practical TypeScript A2A implementation with gRPC-first transport, AgentCard discovery, task lifecycle management, JSON Schema validation, HTTP/WebSocket helpers, and a bundled CLI. Node 22+.\n*   **PHP**\n    *   🌟 [a2a-php](https://github.com/andreibesleaga/a2a-php) by [@andreibesleaga](https://github.com/andreibesleaga) [![Stars](https://img.shields.io/github/stars/andreibesleaga/a2a-php?style=social)](https://github.com/andreibesleaga/a2a-php) - PHP implementation of the A2A Protocol with a fully compliant reference server, strict JSON-RPC validation, task management, SSE streaming, push notifications, and 100% official TCK pass rate.\n*   **Java**\n    *   🌟 [a2a-java](https://github.com/a2aproject/a2a-java) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-java?style=social)](https://github.com/a2aproject/a2a-java) - **Official** Java SDK for the Agent2Agent (A2A) Protocol.\n    *   🌟 [a2a-jakarta](https://github.com/wildfly-extras/a2a-jakarta) by [@wildfly-extras](https://github.com/wildfly-extras) [![Stars](https://img.shields.io/github/stars/wildfly-extras/a2a-jakarta?style=social)](https://github.com/wildfly-extras/a2a-jakarta) - Jakarta EE integration for the A2A Java SDK, implementing A2A Protocol Specification 1.0 on WildFly, Tomcat, Jetty, and OpenLiberty. Apache 2.0.\n    *   🌟 [a2ajava](https://github.com/vishalmysore/a2ajava) by [@vishalmysore](https://github.com/vishalmysore) [![Stars](https://img.shields.io/github/stars/vishalmysore/a2ajava?style=social)](https://github.com/vishalmysore/a2ajava) - Java A2A server/client implementation using Spring Boot with annotations. Supports WebSockets, MCP integration, and includes enterprise/Kubernetes deployment tutorials.\n    *   🌟 [a2a4j](https://github.com/a2ap/a2a4j) by [@a2ap](https://github.com/a2ap) [![Stars](https://img.shields.io/github/stars/a2ap/a2a4j?style=social)](https://github.com/a2ap/a2a4j) - A2A4J is a comprehensive Java implementation of the Agent2Agent Protocol, including server, client, examples, and a starter — ready to use out of the box.\n    *   🌟 [spring-ai-a2a](https://github.com/spring-ai-community/spring-ai-a2a) by [@spring-ai-community](https://github.com/spring-ai-community) [![Stars](https://img.shields.io/github/stars/spring-ai-community/spring-ai-a2a?style=social)](https://github.com/spring-ai-community/spring-ai-a2a) - Spring Boot and Spring AI integration for building AI agent servers using the A2A Protocol. Features auto-configuration, full `@Tool` support, and multi-agent orchestration examples.\n    *   🌟 [rocketmq-a2a](https://github.com/apache/rocketmq-a2a) by [@apache](https://github.com/apache) [![Stars](https://img.shields.io/github/stars/apache/rocketmq-a2a?style=social)](https://github.com/apache/rocketmq-a2a) - Apache RocketMQ transport integration for the A2A Protocol. Provides `RocketMQTransport` for asynchronous client messaging and `RocketMQA2AServerRoutes` for Quarkus server-side routing, with samples for Google ADK, AgentScope, and LangGraph. Apache 2.0.\n*   **Kotlin**\n    *   🌟 [a2a-4k](https://github.com/a2a-4k/a2a-4k) by [@a2a-4k](https://github.com/a2a-4k) [![Stars](https://img.shields.io/github/stars/a2a-4k/a2a-4k?style=social)](https://github.com/a2a-4k/a2a-4k) - Kotlin implementation of the A2A protocol with client/server modules, Ktor-based server support, Redis-backed task storage, streaming support, and examples for Arc and LangChain4j integrations.\n*   **Swift**\n    *   🌟 [a2a-swift](https://github.com/Victory-Apps/a2a-swift) by [@Victory-Apps](https://github.com/Victory-Apps) [![Stars](https://img.shields.io/github/stars/Victory-Apps/a2a-swift?style=social)](https://github.com/Victory-Apps/a2a-swift) - A Swift SDK for A2A with full v1.0 data model, JSON-RPC routing, SSE streaming with reconnection, Vapor integration, and testing utilities. Supports macOS, Linux, iOS, tvOS, watchOS.\n*   **Elixir**\n    *   🌟 [a2a-elixir](https://github.com/actioncard/a2a-elixir) by [@actioncard](https://github.com/actioncard) [![Stars](https://img.shields.io/github/stars/actioncard/a2a-elixir?style=social)](https://github.com/actioncard/a2a-elixir) - Elixir implementation of the A2A protocol with behaviour-based GenServer agents, multi-turn conversations, SSE streaming, HTTP serving via Plug, skill-based agent registry, pluggable storage, and Telemetry integration.\n    *   🌟 [a2a_ex](https://github.com/lukaszsamson/a2a_ex) by [@lukaszsamson](https://github.com/lukaszsamson) [![Stars](https://img.shields.io/github/stars/lukaszsamson/a2a_ex?style=social)](https://github.com/lukaszsamson/a2a_ex) - Elixir client and server library for A2A with REST/JSON-RPC transports, SSE streaming utilities, Plug integration, typed structs, task store abstractions, and protocol compatibility modes.\n*   **Dart**\n    *   🌟 [a2a](https://github.com/shamblett/a2a) by [@shamblett](https://github.com/shamblett) [![Stars](https://img.shields.io/github/stars/shamblett/a2a?style=social)](https://github.com/shamblett/a2a) - Dart/Flutter SDK for the A2A protocol, modelled after the official `a2a-js` SDK. Provides an `A2AClient` with JSON-RPC, SSE streaming, push notification configuration, agent card retrieval, plus a CLI client and server-side support. Published on pub.dev as `a2a` by verified publisher `darticulate.com`; runs on Android, iOS, Linux, macOS, and Windows.\n\n##### Frameworks\n\n*Developer-first frameworks specifically designed for building A2A-compliant agents.*\n\n*   🚀 [A2A Lite](https://github.com/xvierd/a2a-lite) by [@xvierd](https://github.com/xvierd) [![Stars](https://img.shields.io/github/stars/xvierd/a2a-lite?style=social)](https://github.com/xvierd/a2a-lite) - The simplest way to build agents for Google's A2A Protocol. A decorator-based, multi-language (Python, TypeScript, Java) wrapper around the official A2A SDKs with built-in LLM integrations, `AgentNetwork` delegation, CLI tools, and an in-process test client. MIT licensed and published on PyPI/npm/Maven as `a2a-lite`.\n*   🚀 [ADK Go](https://github.com/google/adk-go) by [@google](https://github.com/google) [![Stars](https://img.shields.io/github/stars/google/adk-go?style=social)](https://github.com/google/adk-go) - Google's official open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with native A2A protocol support, MCP integration, multi-agent orchestration, and seamless Vertex AI / Gemini interoperability. Apache 2.0.\n*   🚀 [ADK Java](https://github.com/google/adk-java) by [@google](https://github.com/google) [![Stars](https://img.shields.io/github/stars/google/adk-java?style=social)](https://github.com/google/adk-java) - Google's official open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents. Version 1.0.0 introduces native A2A protocol integration for remote agent-to-agent communication, Google Maps grounding, human-in-the-loop workflows, and robust session management. Apache 2.0.\n*   🚀 [AgentUp](https://github.com/nolabs-ai/AgentUp) by [@nolabs-ai](https://github.com/nolabs-ai) [![Stars](https://img.shields.io/github/stars/nolabs-ai/AgentUp?style=social)](https://github.com/nolabs-ai/AgentUp) - 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.\n*   🚀 [Agenspy](https://github.com/SuperagenticAI/Agenspy) by [@SuperagenticAI](https://github.com/SuperagenticAI) [![Stars](https://img.shields.io/github/stars/SuperagenticAI/Agenspy?style=social)](https://github.com/SuperagenticAI/Agenspy) - A protocol-first AI agent framework built on top of DSPy, designed to create sophisticated, production-ready AI agents with native support for MCP and Agent2Agent protocols. Features comprehensive CLI, Python \u0026 JavaScript MCP servers, and automatic connection management. MIT licensed and published on PyPI as `agenspy`.\n*   🚀 [ANT AI](https://github.com/idea-idsia/ant-ai) by [@idea-idsia](https://github.com/idea-idsia) [![Stars](https://img.shields.io/github/stars/idea-idsia/ant-ai?style=social)](https://github.com/idea-idsia/ant-ai) - A lightweight Python framework from IDSIA for building tool-driven AI agents and multi-agent systems with first-class A2A protocol support (dedicated `a2a` module with client, server, executor, session, and translator). Features graph-based workflow orchestration, MCP tool integration, lifecycle hooks for guardrails, LLM-agnostic core, and built-in observability via Langfuse. MIT licensed and published on PyPI as `ant-ai`.\n*   🚀 [any-agent](https://github.com/mozilla-ai/any-agent) by [@mozilla-ai](https://github.com/mozilla-ai) [![Stars](https://img.shields.io/github/stars/mozilla-ai/any-agent?style=social)](https://github.com/mozilla-ai/any-agent) - A single interface to use and evaluate different agent frameworks, with first-class A2A serving and multi-agent support. Wraps TinyAgent, Google ADK, LangChain, LlamaIndex, OpenAI Agents, Smolagents, and Agno. Apache 2.0.\n*   🚀 [ProtoLink](https://github.com/nMaroulis/protolink) by [@nMaroulis](https://github.com/nMaroulis) [![Stars](https://img.shields.io/github/stars/nMaroulis/protolink?style=social)](https://github.com/nMaroulis/protolink) - A lightweight Python framework that implements and extends Google's A2A specification at the wire level, providing a unified agent runtime with built-in client/server, swappable transports (HTTP/WebSocket/gRPC/in-memory), native LLM and MCP tool integration, OAuth2/API-key auth, structured deterministic flows (Pipeline/Parallel/Router/Graph), and Langfuse/LangSmith telemetry. MIT licensed and published on PyPI as `protolink`.\n*   🚀 [inference-gateway/adk](https://github.com/inference-gateway/adk) by [@inference-gateway](https://github.com/inference-gateway) [![Stars](https://img.shields.io/github/stars/inference-gateway/adk?style=social)](https://github.com/inference-gateway/adk) - A Go-based Agent Development Kit for building A2A-compatible agents with full protocol compliance, multi-LLM provider support (OpenAI, Ollama, Groq, Cohere), real-time streaming, OIDC/OAuth2 auth, push notifications, lifecycle callbacks for guardrails/caching/logging, file artifacts with filesystem and MinIO backends, task pausing and resumption, pluggable storage (in-memory/Redis), TLS, OpenTelemetry observability, and 14+ working examples. MIT licensed.\n*   🚀 [inference-gateway/rust-adk](https://github.com/inference-gateway/rust-adk) by [@inference-gateway](https://github.com/inference-gateway) [![Stars](https://img.shields.io/github/stars/inference-gateway/rust-adk?style=social)](https://github.com/inference-gateway/rust-adk) - A Rust-based Agent Development Kit for building A2A-compatible agents with full protocol compliance, featuring A2AServer/A2AClient/AgentBuilder APIs, health monitoring, LLM client integration, push notifications, OIDC/OAuth2 auth, TLS/mTLS, and comprehensive task lifecycle management. Published on crates.io as `inference-gateway-adk`. Apache 2.0.\n*   🚀 [Hyperterse](https://github.com/hyperterse/hyperterse) by [@hyperterse](https://github.com/hyperterse) [![Stars](https://img.shields.io/github/stars/hyperterse/hyperterse?style=social)](https://github.com/hyperterse/hyperterse) - A Go agentic server framework that ships declarative A2A agents (built on the official `a2aproject/a2a-go` SDK with per-agent JSON-RPC endpoints at `/agent/{name}`, agent cards, messaging, tasks, and streaming) alongside a full MCP server (tools/resources/prompts/completion to MCP spec 2025-11-25) from a single config-driven runtime. Features filesystem-based tool/agent/prompt discovery, database adapters (PostgreSQL/MySQL/SQLite/libSQL/MongoDB/Redis) exposed as typed MCP tools, optional TypeScript handlers for custom logic, multi-LLM providers (OpenAI-compatible + Gemini/Vertex), per-tool API-key auth plugins, in-memory caching, and OpenTelemetry tracing/metrics. Apache 2.0.\n*   🚀 [Mangaba AI](https://github.com/Mangaba-ai/mangaba_ai) by [@Mangaba-ai](https://github.com/Mangaba-ai) [![Stars](https://img.shields.io/github/stars/Mangaba-ai/mangaba_ai?style=social)](https://github.com/Mangaba-ai/mangaba_ai) - A professional Python multi-agent orchestration framework with native A2A and MCP protocol support, ReAct reasoning, function calling, RAG, persistent memory, advanced vector stores, and resilient multi-provider LLM interoperability. MIT licensed and published on PyPI as `mangaba`.\n*   🚀 [Agentic Kernel](https://github.com/Qredence/agentic-kernel) by [@Qredence](https://github.com/Qredence) [![Stars](https://img.shields.io/github/stars/Qredence/agentic-kernel?style=social)](https://github.com/Qredence/agentic-kernel) - A flexible foundation AI system for creating A2A-compatible autonomous AI agents that can collaborate, reason, and execute complex tasks. Built on Google's A2A standard and the ADK framework, featuring a modular multi-agent architecture, sophisticated workflow engine, dynamic planning with an Orchestrator Agent, and a Chainlit-based interactive UI. MIT licensed and published on PyPI as `agentic-kernel`.\n*   🚀 [Reactive Agents](https://github.com/tylerjrbuell/reactive-agents-ts) by [@tylerjrbuell](https://github.com/tylerjrbuell) [![Stars](https://img.shields.io/github/stars/tylerjrbuell/reactive-agents-ts?style=social)](https://github.com/tylerjrbuell/reactive-agents-ts) - A composable TypeScript AI agent framework with end-to-end Effect-TS type safety, a deterministic 12-phase execution engine, 5 reasoning strategies (ReAct, Reflexion, Plan-Execute, Tree-of-Thought, Adaptive), persistent 4-tier memory, production guardrails, cost routing, and native A2A protocol support (Agent Cards, JSON-RPC 2.0 server/client, SSE streaming). 5,000+ tests, 35 packages. MIT licensed and published on npm as `@reactive-agents/*`.\n*   🚀 [Swarm](https://github.com/fcn06/swarm) by [@fcn06](https://github.com/fcn06) [![Stars](https://img.shields.io/github/stars/fcn06/swarm?style=social)](https://github.com/fcn06/swarm) - A Rust framework for building and orchestrating intelligent multi-agent systems through open standards (A2A and MCP). Features a Planner Agent that produces static or dynamically generated workflows, an Executor Agent that carries them out with a built-in LLM-as-a-Judge evaluation loop for self-correction, an Agent Factory for programmatic agent instantiation at runtime, specialized Domain Agents, and an MCP Runtime that bridges agents to external tools. Workspace-organized crates built on `a2a-rs` and `rmcp`. Apache 2.0.\n*   🚀 [LLM Tornado](https://github.com/lofcz/LLMTornado) by [@lofcz](https://github.com/lofcz) [![Stars](https://img.shields.io/github/stars/lofcz/LLMTornado?style=social)](https://github.com/lofcz/LLMTornado) - A .NET provider-agnostic SDK for building, orchestrating, and deploying AI agents and workflows with first-class A2A protocol support via the dedicated `LlmTornado.A2A` package (AgentCard discovery, message send, SSE streaming, task lifecycle) and a companion `LlmTornado.A2A.AgentServer` for exposing Tornado agents as A2A servers. Features 30+ built-in LLM/vector DB connectors (OpenAI, Anthropic, Google, Cohere, xAI, Mistral, vLLM, Ollama, etc.), graph-based agent orchestration (Orchestrator/Runner/Advancer with handoffs and parallel execution), MCP integration, Anthropic Skills, multimodal I/O, and Microsoft.Extensions.AI interop. 100,000+ NuGet installs, 500+ tests. MIT licensed (license-stable commitment) and published on NuGet as `LlmTornado.*`.\n*   🚀 [trpc-agent-go](https://github.com/trpc-group/trpc-agent-go) by [@trpc-group](https://github.com/trpc-group) [![Stars](https://img.shields.io/github/stars/trpc-group/trpc-agent-go?style=social)](https://github.com/trpc-group/trpc-agent-go) - A powerful Go framework for building intelligent agent systems with first-class A2A interoperability. Features A2A server (one-click exposure of any agent as an A2A service with auto-generated AgentCards), A2AAgent client proxy for calling remote A2A agents, automatic bidirectional message protocol conversion, streaming and non-streaming modes, multi-agent orchestration (chain/parallel/graph-based workflows), persistent memory, prompt caching, and built-in telemetry. Published on pkg.go.dev. Apache 2.0.\n*   🚀 [Gocrewwai](https://github.com/Ecook14/gocrewwai) by [@Ecook14](https://github.com/Ecook14) [![Stars](https://img.shields.io/github/stars/Ecook14/gocrewwai?style=social)](https://github.com/Ecook14/gocrewwai) - A high-performance, strictly-typed agentic orchestration framework for Go. Inspired by CrewAI, LangChain, and LangGraph, with native A2A protocol support, durable flow persistence, MCP integration, recursive self-correction, and human-in-the-loop workflows. MIT licensed.\n*   🚀 [Atmosphere](https://github.com/Atmosphere/atmosphere) by [@Atmosphere](https://github.com/Atmosphere) [![Stars](https://img.shields.io/github/stars/Atmosphere/atmosphere?style=social)](https://github.com/Atmosphere/atmosphere) - JVM runtime for streaming, governable AI agents with first-class A2A, MCP, and AG-UI protocol support. Declare behavior with @Agent and deliver over WebSocket, SSE, gRPC, and WebTransport/HTTP3. Features runtime adapters for Spring AI, LangChain4j, Google ADK, and Quarkus, plus policy admission, human-in-the-loop approvals, and durable sessions. Apache 2.0.\n*   🚀 [Harness](https://github.com/mastersof-ai/harness) by [@mastersof-ai](https://github.com/mastersof-ai) [![Stars](https://img.shields.io/github/stars/mastersof-ai/harness?style=social)](https://github.com/mastersof-ai/harness) - An agent runtime with full system prompt control, defining agents in markdown and running them through a terminal TUI or multi-user web UI. Features bidirectional A2A protocol support — expose agents via auto-generated Agent Cards and call remote A2A agents with built-in discovery and invocation tools. Includes persistent memory, sandboxed execution, sub-agents, and MCP integration. MIT licensed.\n*   🚀 [ReachAI (Enterprise Agent Framework)](https://github.com/w8123/EnterpriseAgentFramework) by [@w8123](https://github.com/w8123) [![Stars](https://img.shields.io/github/stars/w8123/EnterpriseAgentFramework?style=social)](https://github.com/w8123/EnterpriseAgentFramework) - A developer-first enterprise AI capability framework for Java/Spring Boot. Register business APIs as governed AI capabilities via `@AiCapability` annotations, orchestrate agents in a visual studio with GraphSpec runtime, and expose them through Gateway, MCP, and A2A protocols with full RunOps and traceability. MIT licensed.\n*   🚀 [tinyagent](https://github.com/mozilla-ai/tinyagent) by [@mozilla-ai](https://github.com/mozilla-ai) [![Stars](https://img.shields.io/github/stars/mozilla-ai/tinyagent?style=social)](https://github.com/mozilla-ai/tinyagent) - A minimal Python agent framework with first-class tracing, callbacks, MCP tool support (stdio/SSE/streamable HTTP), and optional A2A/MCP serving. Built on `any-llm` and extracted from `any-agent`. Apache 2.0.\n*   🚀 [Solace Agent Mesh](https://github.com/SolaceLabs/solace-agent-mesh) by [@SolaceLabs](https://github.com/SolaceLabs) [![Stars](https://img.shields.io/github/stars/SolaceLabs/solace-agent-mesh?style=social)](https://github.com/SolaceLabs/solace-agent-mesh) - An event-driven framework for building and orchestrating multi-agent AI systems, enabling agents to discover and delegate tasks via the A2A protocol over Solace event messaging. Apache 2.0.\n*   🚀 [Kagenti ADK](https://github.com/kagenti/adk) by [@kagenti](https://github.com/kagenti) [![Stars](https://img.shields.io/github/stars/kagenti/adk?style=social)](https://github.com/kagenti/adk) - A developer toolkit that turns agents built with any framework into self-hostable, A2A-compliant services. Includes a CLI, Python SDK, TypeScript client SDK, and a runtime with LLM proxy, MCP connectors, vector search, auth, and observability. Apache 2.0.\n*   🚀 [orxhestra](https://github.com/NicolaiLassen/orxhestra) by [@NicolaiLassen](https://github.com/NicolaiLassen) [![Stars](https://img.shields.io/github/stars/NicolaiLassen/orxhestra?style=social)](https://github.com/NicolaiLassen/orxhestra) - Multi-agent orchestration framework for Python — turn any agent setup into a CLI or server. Compose multi-agent AI systems with async event streaming, agent hierarchies, and built-in support for MCP and A2A protocols (spec-compliant v1.0 server with JSON-RPC 2.0, agent card discovery, streaming, push notifications, and Ed25519 signing). Published on PyPI as `orxhestra`. Apache 2.0.\n*   🚀 [BeeAI Framework](https://github.com/i-am-bee/beeai-framework) by [@i-am-bee](https://github.com/i-am-bee) [![Stars](https://img.shields.io/github/stars/i-am-bee/beeai-framework?style=social)](https://github.com/i-am-bee/beeai-framework) - Build production-ready multi-agent systems in Python or TypeScript, with a Serve module that exposes agents via A2A and MCP. Apache 2.0.\n*   🚀 [ADK Rust](https://github.com/zavora-ai/adk-rust) by [@zavora-ai](https://github.com/zavora-ai) [![Stars](https://img.shields.io/github/stars/zavora-ai/adk-rust?style=social)](https://github.com/zavora-ai/adk-rust) - A production-ready, model-agnostic Rust Agent Development Kit with native A2A v1.0.0 support (`A2aServer::quick_start`), 39+ crates, MCP integration, RAG, memory, guardrails, realtime voice agents, and multi-provider LLM support. Apache 2.0 and published on crates.io as `adk-rust`.\n*   🚀 [Microsoft Agent Framework](https://github.com/microsoft/agent-framework) by [@microsoft](https://github.com/microsoft) [![Stars](https://img.shields.io/github/stars/microsoft/agent-framework?style=social)](https://github.com/microsoft/agent-framework) - An open, multi-language framework for building production-grade AI agents and multi-agent workflows in .NET and Python, with first-class A2A hosting and consumption support (AgentCard discovery, SSE streaming, background tasks, A2AAgent/A2ACardResolver), graph-based orchestration, durability, observability, and human-in-the-loop. MIT licensed.\n*   🚀 [Microsoft Agent Framework for Go](https://github.com/microsoft/agent-framework-go) by [@microsoft](https://github.com/microsoft) [![Stars](https://img.shields.io/github/stars/microsoft/agent-framework-go?style=social)](https://github.com/microsoft/agent-framework-go) - The Go implementation of Microsoft Agent Framework (MAF) for building production-grade AI agents and multi-agent workflows with first-class A2A protocol support, MCP integration, graph-based orchestration, OpenTelemetry observability, and Microsoft Foundry agents. MIT licensed.\n*   🚀 [Agno](https://github.com/agno-agi/agno) by [@agno-agi](https://github.com/agno-agi) [![Stars](https://img.shields.io/github/stars/agno-agi/agno?style=social)](https://github.com/agno-agi/agno) - A lightweight library for building agentic AI systems. AgentOS exposes agents, teams, and workflows as A2A-compatible services with `A2AClient` and `RemoteAgent` for calling remote A2A agents, and also supports AG-UI. Apache 2.0 and published on PyPI as `agno`.\n*   🚀 [YoMo](https://github.com/yomorun/yomo) by [@yomorun](https://github.com/yomorun) [![Stars](https://img.shields.io/github/stars/yomorun/yomo?style=social)](https://github.com/yomorun/yomo) - Open-source serverless LLM function-calling framework for building scalable, geo-distributed AI agents with A2A protocol support. Apache 2.0.\n*   🚀 [fast-agent](https://github.com/evalstate/fast-agent) by [@evalstate](https://github.com/evalstate) [![Stars](https://img.shields.io/github/stars/evalstate/fast-agent?style=social)](https://github.com/evalstate/fast-agent) - A flexible Python framework for building and evaluating LLM agents with first-class A2A protocol support, MCP/ACP integration, agent skills, and an interactive TUI. Apache 2.0 and published on PyPI as `fast-agent-mcp`.\n*   🚀 [Evolver](https://github.com/EvoMap/evolver) by [@EvoMap](https://github.com/EvoMap) [![Stars](https://img.shields.io/github/stars/EvoMap/evolver?style=social)](https://github.com/EvoMap/evolver) - A GEP-powered self-evolution engine for AI agents. Turns ad hoc prompt tweaks into auditable Genes and Capsules, with A2A protocol support for connecting to the EvoMap hub to share and sync evolution assets. Published on npm as `@evomap/evolver`. GPL-3.0.\n*   🚀 [Forge](https://github.com/initializ/forge) by [@initializ](https://github.com/initializ) [![Stars](https://img.shields.io/github/stars/initializ/forge?style=social)](https://github.com/initializ/forge) - An open, secure, portable AI agent runtime for the enterprise. Write a `SKILL.md`, compile it into a hardened agent, and deploy it anywhere containers run — including as an A2A endpoint with a spec-conformant Agent Card at `/.well-known/agent-card.json`. Features egress controls, encrypted secrets, Ed25519 build signing, audit logging, MCP client, channel connectors, cron scheduling, and Kubernetes deployment. Apache 2.0.\n\n##### Platforms \u0026 Integrated Solutions\n\n*   🌟 [AG2 (AutoGen)](https://github.com/ag2ai/ag2) by [@ag2ai](https://github.com/ag2ai) [![Stars](https://img.shields.io/github/stars/ag2ai/ag2?style=social)](https://github.com/ag2ai/ag2) - 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).\n*   🌟 [AURA](https://github.com/mezmo/aura) by [@mezmo](https://github.com/mezmo) [![Stars](https://img.shields.io/github/stars/mezmo/aura?style=social)](https://github.com/mezmo/aura) - An agentic harness that turns LLM models into reliable, autonomous services for real SRE work. Provides guardrails, API servers, state management, authentication, streaming, error handling, MCP tool integrations, multi-agent orchestration, vector search, and native A2A protocol endpoints for cross-agent interoperability. Apache 2.0.\n*   🌟 [Agentlas OS](https://github.com/agentlas-ai/Agentlas-OS) by [@agentlas-ai](https://github.com/agentlas-ai) [![Stars](https://img.shields.io/github/stars/agentlas-ai/Agentlas-OS?style=social)](https://github.com/agentlas-ai/Agentlas-OS) - Local-first Agent OS that keeps specialist agents in a hub and spins up a temporary orchestrator per task, with A2A Agent Card import/export and caller-gated inter-agent boundaries. Apache 2.0.\n*   🌟 [Skales](https://github.com/skalesapp/skales) by [@skalesapp](https://github.com/skalesapp) [![Stars](https://img.shields.io/github/stars/skalesapp/skales?style=social)](https://github.com/skalesapp/skales) - Private AI desktop agent for Windows, macOS, Linux, Android \u0026 iOS. Set a goal and let it work autonomously in the background, with Teams (pair two desktops, agents + humans), Agent2Agent protocol support, Workflows, Codework, multi-agent orgs, desktop + browser automation, and 15+ AI providers. BSL 1.1 licensed.\n*   🌟 [Bindu](https://github.com/GetBindu/Bindu) by [@GetBindu](https://github.com/GetBindu) [![Stars](https://img.shields.io/github/stars/GetBindu/Bindu?style=social)](https://github.com/GetBindu/Bindu) - Open-source identity, communication, and payments layer for AI agents. Wrap any handler with `bindufy()` to add DID identity, A2A protocol (message/send, tasks/get, message/stream), mTLS/OAuth2 security, and USDC/x402 payments. Framework-agnostic with Python, TypeScript, and Kotlin SDKs. Apache 2.0.\n*   🌟 [Agent Stack](https://github.com/i-am-bee/agentstack) by [@i-am-bee](https://github.com/i-am-bee) [![Stars](https://img.shields.io/github/stars/i-am-bee/agentstack?style=social)](https://github.com/i-am-bee/agentstack) - Open infrastructure for turning AI agents into running services in minutes. Built on the Agent2Agent (A2A) Protocol so all agents are automatically exposed as A2A-compatible services. Features a self-hostable runtime, 15+ LLM providers, vector storage and RAG, S3-compatible file storage, MCP integrations, secrets management, Web UI, Python SDK, and Helm charts. Apache 2.0, hosted by the Linux Foundation AI \u0026 Data program.\n*   🌟 [bitterbot-desktop](https://github.com/Bitterbot-AI/bitterbot-desktop) by [@Bitterbot-AI](https://github.com/Bitterbot-AI) [![Stars](https://img.shields.io/github/stars/Bitterbot-AI/bitterbot-desktop?style=social)](https://github.com/Bitterbot-AI/bitterbot-desktop) - A local-first personal AI with biological memory, a dream engine, and a P2P skills economy. Features native A2A Protocol v1.0.0 support for external agent discovery at `/.well-known/agent.json` and task delegation via JSON-RPC with SSE streaming. MIT licensed.\n*   🌟 [Aser](https://github.com/AmeNetwork/aser) by [@AmeNetwork](https://github.com/AmeNetwork) [![Stars](https://img.shields.io/github/stars/AmeNetwork/aser?style=social)](https://github.com/AmeNetwork/aser) - A lightweight, modular Python AI agent framework with first-class Google A2A protocol support (server/client examples built on the official `a2a-sdk`), plus MCP, memory, RAG, and multi-agent orchestration. MIT licensed and published on PyPI as `aser`.\n*   🌟 [Elkar](https://github.com/elkar-ai/elkar-a2a) by [@elkar-ai](https://github.com/elkar-ai) [![Stars](https://img.shields.io/github/stars/elkar-ai/elkar-a2a?style=social)](https://github.com/elkar-ai/elkar-a2a) - 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.\n*   🌟 [Aira](https://github.com/IhateCreatingUserNames2/Aira) by [@IhateCreatingUserNames2](https://github.com/IhateCreatingUserNames2) [![Stars](https://img.shields.io/github/stars/IhateCreatingUserNames2/Aira?style=social)](https://github.com/IhateCreatingUserNames2/Aira) - An A2A network implementation for hosting, registering, discovering, and interacting with agents. Includes agent discovery mechanisms.\n*   🌟 [Cognisphere](https://github.com/IhateCreatingUserNames2/Cognisphere) by [@IhateCreatingUserNames2](https://github.com/IhateCreatingUserNames2) [![Stars](https://img.shields.io/github/stars/IhateCreatingUserNames2/Cognisphere?style=social)](https://github.com/IhateCreatingUserNames2/Cognisphere) - An AI agent development framework built on Google's ADK, facilitating agent creation potentially for A2A networks.\n*   🌐 [Grasp](https://github.com/aircodelabs/grasp) by [@adcentury](https://github.com/adcentury) [![Stars](https://img.shields.io/github/stars/aircodelabs/grasp?style=social)](https://github.com/aircodelabs/grasp) - A Self-hosted Browser Using Agent with built-in MCP and A2A support.\n*   🌟 [swissknife](https://github.com/daltonnyx/swissknife) by [@daltonnyx](https://github.com/daltonnyx) [![Stars](https://img.shields.io/github/stars/daltonnyx/swissknife?style=social)](https://github.com/daltonnyx/swissknife) - 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.\n*   🌟 [n8n-nodes-agent2agent](https://github.com/pjawz/n8n-nodes-agent2agent) by [@pjawz](https://github.com/pjawz) [![Stars](https://img.shields.io/github/stars/pjawz/n8n-nodes-agent2agent?style=social)](https://github.com/pjawz/n8n-nodes-agent2agent) - Adds nodes to n8n for interacting with AI agents using Google's Agent2Agent (A2A) protocol.\n*   🌟 [google-calendar-agent](https://github.com/inference-gateway/google-calendar-agent) by [@inference-gateway](https://github.com/inference-gateway) [![Stars](https://img.shields.io/github/stars/inference-gateway/google-calendar-agent?style=social)](https://github.com/inference-gateway/google-calendar-agent) - A standalone A2A agent that can manage a user's Google Calendar, compatible with any OpenAI-compatible API for its LLM.\n*   🌟 [google-maps-a2a](https://github.com/pab1it0/google-maps-a2a) by [@pab1it0](https://github.com/pab1it0) [![Stars](https://img.shields.io/github/stars/pab1it0/google-maps-a2a?style=social)](https://github.com/pab1it0/google-maps-a2a) - An open-source A2A-compliant server that provides Google Maps capabilities — geocoding, reverse geocoding, directions, places search, and distance matrix — to other agents via the standardized protocol.\n*   🌟 [A2AApp](https://github.com/tanaikech/A2AApp) by [@tanaikech](https://github.com/tanaikech) [![Stars](https://img.shields.io/github/stars/tanaikech/A2AApp?style=social)](https://github.com/tanaikech/A2AApp) - 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.\n*   🌟 [AgentAnycast](https://github.com/AgentAnycast/agentanycast) by [@AgentAnycast](https://github.com/AgentAnycast) [![Stars](https://img.shields.io/github/stars/AgentAnycast/agentanycast?style=social)](https://github.com/AgentAnycast/agentanycast) - A decentralized P2P runtime for the A2A protocol, powered by libp2p. Features end-to-end encryption (Noise_XX), automatic NAT traversal, skill-based anycast routing, MCP tool bridging, and framework adapters (CrewAI, LangGraph). Zero-config — agents communicate across any network without public IPs or VPNs. SDKs for Python and TypeScript.\n*   🌟 [a2a-client-hub](https://github.com/liujuanjuan1984/a2a-client-hub) by [@liujuanjuan1984](https://github.com/liujuanjuan1984) [![Stars](https://img.shields.io/github/stars/liujuanjuan1984/a2a-client-hub?style=social)](https://github.com/liujuanjuan1984/a2a-client-hub) - A self-hosted A2A client hub for teams and individuals to manage, invoke, and operate multiple A2A agents across web and mobile with unified session history and governance.\n*   🌟 [routa](https://github.com/phodal/routa) by [@phodal](https://github.com/phodal) [![Stars](https://img.shields.io/github/stars/phodal/routa?style=social)](https://github.com/phodal/routa) - Workspace-first multi-agent coordination platform for AI development, with shared Specs, Kanban orchestration, and MCP/ACP/A2A support across web and desktop.\n*   🌟 [hermes-a2a](https://github.com/iamagenius00/hermes-a2a) by [@iamagenius00](https://github.com/iamagenius00) [![Stars](https://img.shields.io/github/stars/iamagenius00/hermes-a2a?style=social)](https://github.com/iamagenius00/hermes-a2a) - A2A protocol plugin for Hermes Agent enabling peer-to-peer agent communication with instant wake, session injection, and persistent conversation storage.\n*   🌟 [OpenClaw A2A Gateway](https://github.com/win4r/openclaw-a2a-gateway) by [@win4r](https://github.com/win4r) [![Stars](https://img.shields.io/github/stars/win4r/openclaw-a2a-gateway?style=social)](https://github.com/win4r/openclaw-a2a-gateway) - Production-ready OpenClaw plugin implementing the A2A protocol with bidirectional agent communication, adaptive bio-inspired routing, auto-discovery (DNS-SD/mDNS), and resilient multi-transport support (JSON-RPC, REST, gRPC).\n*   🌟 [UnifAI](https://github.com/redhat-community-ai-tools/UnifAI) by [@redhat-community-ai-tools](https://github.com/redhat-community-ai-tools) [![Stars](https://img.shields.io/github/stars/redhat-community-ai-tools/UnifAI?style=social)](https://github.com/redhat-community-ai-tools/UnifAI) - Production-grade multi-agent orchestration engine with A2A and MCP protocol support. Features a pluggable catalog of Agents, LLMs, tools, and retrievers, built-in RAG pipeline for enterprise knowledge retrieval, and a visual drag-and-drop blueprint builder. Execute locally with LangGraph or distributed with Temporal.\n*   🌟 [Hector](https://github.com/verikod/hector) by [@verikod](https://github.com/verikod) [![Stars](https://img.shields.io/github/stars/verikod/hector?style=social)](https://github.com/verikod/hector) - An A2A-Native AI Agent Platform written in Go. One self-contained binary, one YAML config, production-ready defaults. Deploy on-premise, in air-gapped environments, or in any cloud with zero external dependencies and zero telemetry. A2A v0.3.0 compliant.\n*   🌟 [E.D.D.I](https://github.com/labsai/EDDI) by [@labsai](https://github.com/labsai) [![Stars](https://img.shields.io/github/stars/labsai/EDDI?style=social)](https://github.com/labsai/EDDI) - Production-grade, config-driven multi-agent orchestration middleware for conversational AI (Java/Quarkus). Features native A2A and MCP protocol support, 12+ LLM providers, RAG, persistent memory, and enterprise compliance. Ships as a Red Hat-certified Docker image.\n*   🌟 [TrainPPTAgent](https://github.com/johnson7788/TrainPPTAgent) by [@johnson7788](https://github.com/johnson7788) [![Stars](https://img.shields.io/github/stars/johnson7788/TrainPPTAgent?style=social)](https://github.com/johnson7788/TrainPPTAgent) - Template-based PPT generation system powered by A2A, ADK, and MCP. Features a Vue.js frontend, Python FastAPI backend, and GRPO reinforcement learning for optimized content generation.\n*   🌟 [ContextForge](https://github.com/IBM/mcp-context-forge) by [@IBM](https://github.com/IBM) [![Stars](https://img.shields.io/github/stars/IBM/mcp-context-forge?style=social)](https://github.com/IBM/mcp-context-forge) - Open-source AI Gateway, registry, and proxy that federates MCP, A2A, and REST/gRPC services into a unified endpoint with centralized discovery, governance, and observability. Includes a dedicated Agent Gateway routing A2A protocol traffic alongside OpenAI/Anthropic agents, plus JWT/SSO/RBAC auth, OpenTelemetry tracing, plugin extensibility, sample A2A agents, and Helm/Kubernetes deployment. Apache 2.0, published on PyPI as `mcp-contextforge-gateway` and as a container on GHCR.\n*   🌟 [RustyHand](https://github.com/ginkida/rustyhand) by [@ginkida](https://github.com/ginkida) [![Stars](https://img.shields.io/github/stars/ginkida/rustyhand?style=social)](https://github.com/ginkida/rustyhand) - Open-source Agent OS in Rust (124K LOC, 1,577 tests, zero clippy warnings). One ~32MB binary with autonomous agents, 61 built-in tools, 26 LLM providers, 37 channel adapters (Telegram/Discord/Slack...), MCP server, and A2A protocol endpoints for cross-instance agent communication.\n*   🌟 [ISEK](https://github.com/isekOS/ISEK) by [@isekOS](https://github.com/isekOS) [![Stars](https://img.shields.io/github/stars/isekOS/ISEK?style=social)](https://github.com/isekOS/ISEK) - Decentralized agent-to-agent network framework for cooperative AI societies, combining Google's A2A protocol with ERC-8004 smart contracts for on-chain agent identity, reputation, and trust. Provides local agent hosting, P2P relay via libp2p for NAT-traversed peer connections, an Agent Explorer for discovery, and a sample multi-agent ChatApp. Published on PyPI as `isek` and MIT licensed.\n*   🌟 [AgentScope Runtime](https://github.com/agentscope-ai/agentscope-runtime) by [@agentscope-ai](https://github.com/agentscope-ai) [![Stars](https://img.shields.io/github/stars/agentscope-ai/agentscope-runtime?style=social)](https://github.com/agentscope-ai/agentscope-runtime) - Production-grade runtime framework for agent applications with native A2A protocol support — A2A protocol adapter, Nacos-based A2A agent registry, and Agent-as-a-Service (AaaS) deployers that automatically expose A2A endpoints with SSE streaming. Features secure tool sandboxing (Python/Shell/GUI/Browser/Filesystem/Mobile), framework-agnostic adapters (AgentScope, Agno, AutoGen, LangGraph, Microsoft Agent Framework), full-stack observability, and multi-target deployment (local, Kubernetes, Knative, OpenKruise, Function Compute, serverless). Apache 2.0 licensed and published on PyPI as `agentscope-runtime`.\n*   🌟 [Zeph](https://github.com/bug-ops/zeph) by [@bug-ops](https://github.com/bug-ops) [![Stars](https://img.shields.io/github/stars/bug-ops/zeph?style=social)](https://github.com/bug-ops/zeph) - Memory-first Rust AI agent runtime for long-running work with a dedicated `zeph-a2a` crate implementing the A2A protocol (JSON-RPC 2.0, agent discovery via `/.well-known/agent.json`, SSE streaming, bearer auth, and Invocation-Bound Capability Tokens). Features temporal graph memory, self-learning skills, multi-model cascade routing (Ollama / Claude / Gemini / OpenAI / GGUF / TEE), sub-agents, MCP + ACP integration, sandboxed tools, CLI, and TUI. Published on crates.io as `zeph` (with `zeph-a2a` as a feature-gated standalone crate). MIT licensed.\n*   🌟 [persona-agent](https://github.com/memenow/persona-agent) by [@memenow](https://github.com/memenow) [![Stars](https://img.shields.io/github/stars/memenow/persona-agent?style=social)](https://github.com/memenow/persona-agent) - A Python-based API server for creating AI persona agents using Google A2A protocol and Model Context Protocol (MCP) tools integration. Each persona is exposed as an independent A2A ASGI sub-app with discoverable agent cards and a JSON-RPC endpoint, plus a REST API for persona management, file upload, and direct chat. Supports OpenAI-compatible LLMs, YAML/JSON persona definitions, and stdio MCP servers. Apache 2.0 licensed.\n*   🌟 [rsclaw](https://github.com/rsclaw-ai/rsclaw) by [@rsclaw-ai](https://github.com/rsclaw-ai) [![Stars](https://img.shields.io/github/stars/rsclaw-ai/rsclaw?style=social)](https://github.com/rsclaw-ai/rsclaw) - A Rust AI agent engine with three-layer persistent memory, 15 LLM providers, 13 messaging channels, and full Google A2A protocol v1.0 support (streaming, push notifications, task persistence, cancellation, INPUT_REQUIRED interrupts). Ships as a single ~15MB binary. Dual-licensed MIT/Apache-2.0 and published on crates.io.\n*   🌟 [Agent Scrum](https://github.com/TensorOpsAI/agent-scrum) by [@TensorOpsAI](https://github.com/TensorOpsAI) [![Stars](https://img.shields.io/github/stars/TensorOpsAI/agent-scrum?style=social)](https://github.com/TensorOpsAI/agent-scrum) - Multi-agent simulation platform where AI agents self-organize on a Kanban board — built with LangGraph, Google A2A, and MCP. Features a full A2A implementation (tasks/send, tasks/get, tasks/cancel, Agent Cards, WebSocket streaming), domain-specific board templates, 14 MCP tools, and both simulation and real LLM modes. MIT licensed.\n*   🌟 [AX (Agent eXecutor)](https://github.com/google/ax) by [@google](https://github.com/google) [![Stars](https://img.shields.io/github/stars/google/ax?style=social)](https://github.com/google/ax) - Google's open-source distributed agent runtime with native A2A protocol support. Coordinates agentic loops with durable event-log execution and automatic recovery, integrating A2A agents via multi-transport (gRPC, JSON-RPC, HTTP+JSON REST), AgentCard discovery, and SSE streaming. Apache 2.0.\n*   🌟 [Agentic Sandbox](https://github.com/jmagly/agentic-sandbox) by [@jmagly](https://github.com/jmagly) [![Stars](https://img.shields.io/github/stars/jmagly/agentic-sandbox?style=social)](https://github.com/jmagly/agentic-sandbox) - Self-hostable runtime for persistent autonomous coding agents with KVM-isolated VMs (or rootless containers), A2A-protocol executor with signed AgentCard discovery, web dashboard, CLI, and gRPC/WebSocket/HTTP interfaces. Runs on your hardware; no hosted control plane. AGPL-3.0.\n*   🌟 [SWE Squad](https://github.com/ArtemisAI/SWE-Squad) by [@ArtemisAI](https://github.com/ArtemisAI) [![Stars](https://img.shields.io/github/stars/ArtemisAI/SWE-Squad?style=social)](https://github.com/ArtemisAI/SWE-Squad) - Autonomous software engineering agent platform with a persistent LLM session, 16 custom tools, and a native A2A protocol implementation for inter-agent communication. Features multi-engine delegation, React WebUI, semantic memory, and 6,800+ tests. MIT licensed.\n*   🌟 [NullClaw](https://github.com/nullclaw/nullclaw) by [@nullclaw](https://github.com/nullclaw) [![Stars](https://img.shields.io/github/stars/nullclaw/nullclaw?style=social)](https://github.com/nullclaw/nullclaw) - The smallest fully autonomous AI assistant infrastructure written in Zig. One 678 KB static binary with 5,300+ tests, 50+ LLM providers, 19 channels, 35+ tools, and native Google A2A protocol v0.3.0 support (Agent Card discovery, JSON-RPC 2.0 endpoint, SSE streaming, bearer auth). MIT licensed.\n*   🌟 [Aloha](https://github.com/ec-jrc/aloha) by [@ec-jrc](https://github.com/ec-jrc) [![Stars](https://img.shields.io/github/stars/ec-jrc/aloha?style=social)](https://github.com/ec-jrc/aloha) - Aloha (AI Logical Orchestrator Hub for Agents) is a centralized hub to manage and interconnect data, tools and agents leveraging the MCP and A2A protocols. Features out-of-the-box MCP server management with multi-auth strategies, A2A agent registration and streaming task execution, proxy servers with identity propagation, and browser-based agentic loop development. EUPL-1.2 licensed.\n*   🌟 [Coworker](https://github.com/Array-Ventures/coworker) by [@Array-Ventures](https://github.com/Array-Ventures) [![Stars](https://img.shields.io/github/stars/Array-Ventures/coworker?style=social)](https://github.com/Array-Ventures/coworker) - Open-source AI agent platform built with Mastra featuring MCP UI, app builder, skills marketplace, A2A protocol support for agent discovery and communication, scheduled tasks, Google Workspace integration, WhatsApp bridge, and multi-provider chat. Self-hostable with Docker and Railway. MIT licensed.\n*   🌟 [a2awebagent](https://github.com/vishalmysore/a2awebagent) by [@vishalmysore](https://github.com/vishalmysore) [![Stars](https://img.shields.io/github/stars/vishalmysore/a2awebagent?style=social)](https://github.com/vishalmysore/a2awebagent) - An A2A agent for AI-driven web automation, test execution, and evidence capture using Selenium. Enables agents to control browsers, validate UI flows, and record structured results through the A2A protocol. MIT licensed.\n*   🌟 [SAP Joule A2A Agent Toolkit](https://github.com/SAP-samples/joule-a2a-agent-toolkit) by [@SAP-samples](https://github.com/SAP-samples) [![Stars](https://img.shields.io/github/stars/SAP-samples/joule-a2a-agent-toolkit?style=social)](https://github.com/SAP-samples/joule-a2a-agent-toolkit) - Build, deploy, and connect AI agents to SAP Joule via the A2A protocol on BTP Cloud Foundry. Supports TypeScript (Express or CAP) and Python agents with LangGraph and SAP GenAI Hub, featuring automated scaffolding, Cloud Foundry deployment, and Joule capability integration. Apache 2.0.\n*   🌟 [AgentArea](https://github.com/agentarea/agentarea) by [@agentarea](https://github.com/agentarea) [![Stars](https://img.shields.io/github/stars/agentarea/agentarea?style=social)](https://github.com/agentarea/agentarea) - A cloud-native platform for building agentic networks with governance, isolation, and approval controls. Features VPC-inspired agent isolation, granular tool permissions with approval workflows, event-driven orchestration, MCP server hosting, and A2A protocol support for interoperability with external agent systems. Apache 2.0.\n*   🌟 [Evo AI](https://github.com/evolution-foundation/evo-ai) by [@evolution-foundation](https://github.com/evolution-foundation) [![Stars](https://img.shields.io/github/stars/evolution-foundation/evo-ai?style=social)](https://github.com/evolution-foundation/evo-ai) - An open-source platform for creating and managing AI agents with native Google A2A protocol support. Features 7 agent types (including a dedicated A2A Agent), Google ADK and LangGraph integration, MCP server configuration, encrypted API key management, JWT authentication, and a Next.js-based web UI. Built with FastAPI and PostgreSQL. Apache 2.0 licensed.\n*   🌟 [OpenAgents](https://github.com/openagents-org/openagents) by [@openagents-org](https://github.com/openagents-org) [![Stars](https://img.shields.io/github/stars/openagents-org/openagents?style=social)](https://github.com/openagents-org/openagents) - Open-source multi-agent network platform with native A2A and MCP protocol support. Features a Workspace, Launcher, and Network SDK for building agent networks that can discover, connect, and collaborate across frameworks. Apache 2.0 licensed.\n*   🌟 [AI-SNS](https://github.com/ai-sns/ai-sns) by [@ai-sns](https://github.com/ai-sns) [![Stars](https://img.shields.io/github/stars/ai-sns/ai-sns?style=social)](https://github.com/ai-sns/ai-sns) - Decentralized social network for AI agents built on the A2A protocol and federated XMPP, featuring real-time 3D visualization on Google Maps, local-first execution, and cross-framework agent collaboration. MIT licensed.\n*   🌟 [LangChain Data Agent](https://github.com/eosho/langchain_data_agent) by [@eosho](https://github.com/eosho) [![Stars](https://img.shields.io/github/stars/eosho/langchain_data_agent?style=social)](https://github.com/eosho/langchain_data_agent) - A natural language to SQL (NL2SQL) platform built on LangGraph and Azure OpenAI, featuring multi-database support, intent-based routing, SQL validation, data visualization, and native A2A protocol interoperability. MIT licensed.\n*   🌟 [Agentgateway](https://github.com/agentgateway/agentgateway) by [@agentgateway](https://github.com/agentgateway) [![Stars](https://img.shields.io/github/stars/agentgateway/agentgateway?style=social)](https://github.com/agentgateway/agentgateway) - Open-source, Linux Foundation AI gateway/proxy for LLM, MCP, and A2A traffic. Rewrites Agent Cards, proxies A2A tasks, and applies unified auth (JWT/mTLS/OAuth), RBAC, AI guardrails, rate limiting, and OpenTelemetry observability. Deploy standalone, via Docker, or on Kubernetes with Helm. Apache 2.0.\n*   🌟 [Echo Agent](https://github.com/fuyuxiang/echo-agent) by [@fuyuxiang](https://github.com/fuyuxiang) [![Stars](https://img.shields.io/github/stars/fuyuxiang/echo-agent?style=social)](https://github.com/fuyuxiang/echo-agent) - A self-hosted, long-running AI agent with cross-session cognitive memory, self-evolving skills, unified multi-channel entry points, and native A2A JSON-RPC/MCP client and server support. MIT licensed.\n*   🌟 [MultiGen](https://github.com/lingyuanli/MultiGen) by [@lingyuanli](https://github.com/lingyuanli) [![Stars](https://img.shields.io/github/stars/lingyuanli/MultiGen?style=social)](https://github.com/lingyuanli/MultiGen) - A general-purpose AI agent system for fully private deployment, featuring Planner + ReAct multi-agent architecture, sandboxed Docker execution, multimodal generation, and native A2A/MCP interoperability. MIT licensed.\n*   🌟 [C2S Agent](https://github.com/C2SAgent/c2sagent) by [@C2SAgent](https://github.com/C2SAgent) [![Stars](https://img.shields.io/github/stars/C2SAgent/c2sagent?style=social)](https://github.com/C2SAgent/c2sagent) - A lightweight AI agent construction platform with configurable online agents, MCP services, and single-port multi-A2A service support. MIT licensed.\n*   🌟 [OmniRoute](https://github.com/diegosouzapw/OmniRoute) by [@diegosouzapw](https://github.com/diegosouzapw) [![Stars](https://img.shields.io/github/stars/diegosouzapw/OmniRoute?style=social)](https://github.com/diegosouzapw/OmniRoute) - Free open-source AI gateway that unifies 160+ LLM providers behind one endpoint, with built-in MCP server, smart auto-fallback, token compression, guardrails, and native Google A2A protocol support (6 skills, JSON-RPC 2.0). MIT licensed.\n*   🌟 [OpenFang](https://github.com/RightNow-AI/openfang) by [@RightNow-AI](https://github.com/RightNow-AI) [![Stars](https://img.shields.io/github/stars/RightNow-AI/openfang?style=social)](https://github.com/RightNow-AI/openfang) - Open-source Agent Operating System built in Rust (137K LOC, 14 crates, 1,700+ tests) with autonomous Hands, 53 built-in tools, MCP/A2A bridge, 40 channel adapters, WASM sandbox, knowledge graphs, and a Tauri desktop app. Dual-licensed under MIT/Apache-2.0.\n*   🌟 [Proximo](https://github.com/john-broadway/proximo) by [@john-broadway](https://github.com/john-broadway) [![Stars](https://img.shields.io/github/stars/john-broadway/proximo?style=social)](https://github.com/john-broadway/proximo) - The Proxmox MCP you can hand the keys — VE + Backup Server + Mail Gateway + Datacenter Manager on one audited trust core (plan · prove · undo · diagnose). Features 352 tools, least-privilege defaults, hash-chained audit ledger, snapshot rollback, and an experimental A2A face. Apache 2.0.\n*   🌟 [Agentic MCP Gateway \u0026 Registry](https://github.com/agentic-community/mcp-gateway-registry) by [@agentic-community](https://github.com/agentic-community) [![Stars](https://img.shields.io/github/stars/agentic-community/mcp-gateway-registry?style=social)](https://github.com/agentic-community/mcp-gateway-registry) - Enterprise-ready unified control plane for MCP servers, AI agents, reusable skills, and custom entities. Features A2A agent discovery, authentication, access control, semantic search, federation, and peer-to-peer agent communication. Apache 2.0.\n*   🌟 [Kagenti](https://github.com/kagenti/kagenti) by [@kagenti](https://github.com/kagenti) [![Stars](https://img.shields.io/github/stars/kagenti/kagenti?style=social)](https://github.com/kagenti/kagenti) - A framework-neutral, cloud-native platform for deploying and orchestrating multi-agent AI systems on Kubernetes with native A2A and MCP protocol support, SPIFFE-based zero-trust identity, dynamic AgentCard discovery and verification, and built-in observability. Apache 2.0.\n*   🌟 [Agent Kernel](https://github.com/yaalalabs/agent-kernel) by [@yaalalabs](https://github.com/yaalalabs) [![Stars](https://img.shields.io/github/stars/yaalalabs/agent-kernel?style=social)](https://github.com/yaalalabs/agent-kernel) - The Operating System for scalable, compliant enterprise AI agents. Run, orchestrate, and deploy production agents across frameworks (OpenAI Agents SDK, LangGraph, CrewAI, Google ADK) and clouds with built-in guardrails, observability, channels, and native A2A/MCP support. Apache 2.0 and published on PyPI as `agentkernel`.\n\u003c!-- Add yours here! See CONTRIBUTING.md --\u003e\n\n## 🛠️ Tools \u0026 Utilities\n\nThis section aims to list standalone tools and utilities related to the A2A protocol. The ecosystem is still developing, and community contributions are welcome!\n\n*   **Agent Discovery Services**\n    *   Some platform-level implementations (like [Aira](https://github.com/IhateCreatingUserNames2/Aira)) include agent registration and discovery mechanisms within their features.\n    *   ⚙️ [A2A Agent Registry on AWS](https://github.com/awslabs/a2a-agent-registry-on-aws) by [@awslabs](https://github.com/awslabs) [![Stars](https://img.shields.io/github/stars/awslabs/a2a-agent-registry-on-aws?style=social)](https://github.com/awslabs/a2a-agent-registry-on-aws) - Scalable serverless agent registry for A2A protocol AgentCards with semantic search (Amazon Bedrock, S3 Vectors), Python SDK, and React Web UI.\n    *   ⚙️ [A2A Registry](https://github.com/prassanna-ravishankar/a2a-registry) by [@prassanna-ravishankar](https://github.com/prassanna-ravishankar) [![Stars](https://img.shields.io/github/stars/prassanna-ravishankar/a2a-registry?style=social)](https://github.com/prassanna-ravishankar/a2a-registry) - Community-driven, open-source directory of live, hosted A2A agents with web UI, REST API, Python client, MCP server, and health conformance checking.\n    *   ⚙️ [DNS-AID Core](https://github.com/dns-aid/dns-aid-core) by [@dns-aid](https://github.com/dns-aid) [![Stars](https://img.shields.io/github/stars/dns-aid/dns-aid-core?style=social)](https://github.com/dns-aid/dns-aid-core) - DNS-based Agent Identification and Discovery reference implementation (IETF BANDAID draft). Lets agents publish and discover each other via DNS instead of centralized registries, with first-class support for A2A and MCP. Includes CLI and Python SDK, an MCP server, OpenTelemetry integration, and pluggable DNS backends (Route 53, Cloudflare, NS1). Apache 2.0.\n    *   ⚙️ [LAD-A2A](https://github.com/franzvill/lad) by [@franzvill](https://github.com/franzvill) [![Stars](https://img.shields.io/github/stars/franzvill/lad?style=social)](https://github.com/franzvill/lad) - An open protocol for discovering A2A-capable AI agents on local networks — the discovery \u0026 trust bootstrap layer beneath A2A. Uses mDNS/DNS-SD, well-known endpoints, signed AgentCards, and DIDs, with explicit user consent before standard A2A communication begins. Apache 2.0.\n    *   ⚙️ [A2ARegistry](https://github.com/OyadotAI/A2ARegistry) by [@OyadotAI](https://github.com/OyadotAI) [![Stars](https://img.shields.io/github/stars/OyadotAI/A2ARegistry?style=social)](https://github.com/OyadotAI/A2ARegistry) - Centralized registry service for discovering and managing A2A agents, with lexical and semantic search, OAuth 2.0, cross-registry federation, Redis caching, and Docker/Kubernetes deployment. Apache 2.0.\n    *   ⚙️ [A2A Directory](https://github.com/sing1ee/a2a-directory) by [@sing1ee](https://github.com/sing1ee) [![Stars](https://img.shields.io/github/stars/sing1ee/a2a-directory?style=social)](https://github.com/sing1ee/a2a-directory) - A curated, multilingual directory of A2A AgentCards, servers, clients, official samples, community implementations, and practical guides (A2A vs MCP, TypeScript/Python getting started, sample methods, etc.). MIT licensed.\n    *   ⚙️ [HOL Registry Broker Skills](https://github.com/hashgraph-online/registry-broker-skills) by [@hashgraph-online](https://github.com/hashgraph-online) [![Stars](https://img.shields.io/github/stars/hashgraph-online/registry-broker-skills?style=social)](https://github.com/hashgraph-online/registry-broker-skills) - AI agent skills for the Universal Agentic Registry. Search live agent inventory, chat with any agent, register your own — consumable by Claude, Codex, Cursor, OpenClaw, and any AI coding assistant. Apache 2.0.\n*   **A2A Validation Tool**\n    *   ⚙️ [a2a-inspector](https://github.com/a2aproject/a2a-inspector) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-inspector?style=social)](https://github.com/a2aproject/a2a-inspector) - **Official** validation tools for A2A agents, including compliance checking and debugging utilities.\n    *   ⚙️ [a2a-tck](https://github.com/a2aproject/a2a-tck) by [@a2aproject](https://github.com/a2aproject) [![Stars](https://img.shields.io/github/stars/a2aproject/a2a-tck?style=social)](https://github.com/a2aproject/a2a-tck) - **Official** Technology Compatibility Kit (TCK) for the A2A Protocol. A pytest-based conformance suite that validates A2A implementations across gRPC, JSON-RPC, and HTTP+JSON transports, with RFC 2119 MUST/SHOULD/MAY level filtering and automated HTML/JSON report generation. Apache 2.0.\n    *   ⚙️ [A2A Validation Tool](https://github.com/llmx-de/a2a-validation-tool) by [@llmx-de](https://github.com/llmx-de) [![Stars](https://img.shields.io/github/stars/llmx-de/a2a-validation-tool?style=social)](https://github.com/llmx-de/a2a-validation-tool) - Cross-platform desktop app for testing \u0026 validating A2A protocol implementations, with features like multi-agent connection and session management.\n    *   ⚙️ [a2a-compliance](https://github.com/UltraSkye/a2a-compliance) by [@UltraSkye](https://github.com/UltraSkye) [![Stars](https://img.shields.io/github/stars/UltraSkye/a2a-compliance?style=social)](https://g","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/ai-boost%2Fawesome-a2a/projects"}