Cover image
Try Now
2025-04-14

A2A −GO是Google对代理到代理(A2A)协议的参考实现,包括与人类的模型上下文协议(MCP)提出的互操作性。

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

🌈 A2A‑Go

"Combine A2A and MCP to create advanced agentic systems!"

Go CI/CD Go Report Card GoDoc License: UNLICENSE Bugs Code Smells Duplicated Lines (%) Lines of Code Reliability Rating Security Rating Technical Debt Maintainability Rating Vulnerabilities

A2A‑Go

a2a‑go is a reference Go implementation of the Agent‑to‑Agent (A2A) protocol by Google, including the proposed interoperability with the Model Context Protocol (MCP).

🚧 Work in progress 🚧 Consider this project a proof of concept at best, and subject to sudden changes.

✨ Features

  • Agent‑to‑Agent (A2A) protocol implementation

    • Send Task to send a new task to an agent
    • Get Task to retrieve a task by ID 🔜
    • Cancel Task to cancel a task 🔜
    • Stream Task to stream the task results 🔜
    • Set Push Notification to configure push notifications for a task 🔜
    • Get Push Notification to retrieve the push notification configuration for a task 🔜
    • Structured Outputs to return structured data from an agent
    • Fine‑tuning to fine‑tune an agent on a dataset
    • Image Generation to generate images with an agent
    • Audio Transcription to transcribe audio
    • Text‑to‑Speech to convert text to speech
  • Model Context Protocol (MCP) interoperability

    • Tool Calling to call tools and receive the results
    • List Prompts to retrieve a list of prompts from an agent 🔜
    • Get Prompt to retrieve a prompt by ID 🔜
    • Set Prompt to create or update a prompt 🔜
    • Delete Prompt to delete a prompt by ID 🔜
    • List Resources to retrieve a list of resources from an agent 🔜
    • Get Resource to retrieve a resource by ID 🔜
    • Set Resource to create or update a resource 🔜
    • Delete Resource to delete a resource by ID 🔜
    • Sampling to sample a task from an agent 🔜
    • Roots to get the root task for a task 🔜
  • Built‑in tools

    • Browser to browse the web 🔜
    • Docker to run Docker commands 🔜
    • GitHub to search GitHub 🔜
    • Memory to store and retrieve memories 🔜
    • Qdrant to store and retrieve vectors 🔜
    • Neo4j to store and retrieve graph data 🔜

🚀 Quick Start

Run the docker-compose.yml for a full distributed system, demonstrating A2A and MCP interoperability.

docker compose up

To run individual, more contained examples, use the example cli command.

a2a-go example <example-name>

Add the --interactive flag to run the example in interactive mode.

a2a-go example <example-name> --interactive

All example code lives in the examples directory.

相关推荐

  • av
  • 毫不费力地使用一个命令运行LLM后端,API,前端和服务。

  • 1Panel-dev
  • 🔥1Panel提供了直观的Web接口和MCP服务器,用于在Linux服务器上管理网站,文件,容器,数据库和LLMS。

  • WangRongsheng
  • 🧑‍🚀 llm 资料总结(数据处理、模型训练、模型部署、 o1 模型、mcp 、小语言模型、视觉语言模型)|摘要世界上最好的LLM资源。

  • Byaidu
  • PDF科学纸翻译带有保留格式的pdf -基于ai完整保留排版的pdf文档全文双语翻译

  • rulego
  • ⛓️Rulego是一种轻巧,高性能,嵌入式,下一代组件编排规则引擎框架。

  • sigoden
  • 使用普通的bash/javascript/python函数轻松创建LLM工具和代理。

  • hkr04
  • 轻巧的C ++ MCP(模型上下文协议)SDK

  • RockChinQ
  • 😎简单易用、🧩丰富生态 -大模型原生即时通信机器人平台| 适配QQ / 微信(企业微信、个人微信) /飞书 /钉钉 / discord / telegram / slack等平台| 支持chatgpt,deepseek,dify,claude,基于LLM的即时消息机器人平台,支持Discord,Telegram,微信,Lark,Dingtalk,QQ,Slack

  • dmayboroda
  • 带有可配置容器的本地对话抹布

  • modelscope
  • 开始以更轻松的方式开始构建具有LLM授权的多代理应用程序。

    Reviews

    3 (1)
    Avatar
    user_ZBDcKxGW
    2025-04-24

    As a devoted user of the mcp application, I find a2a-go by TheApeMachine to be incredibly effective. This product streamlines my workflow, making it hassle-free to manage tasks. The user interface is intuitive, and the functionality aligns perfectly with my daily needs. Highly recommend for anyone looking to boost their productivity!