ag2a

# AG2A: AutoGen Agent-to-Agent A framework for creating [AG2](https://github.com/ag2ai/ag2) (formerly AutoGen) agents that communicate using the [A2A Protocol](https://google.github.io/A2A) and leverage tools via [MCP](https://modelcontextprotocol.io/). ## Overview AG2A makes it simple to: 1. Define agents using JSON specifications 2. Connect AG2 agents with MCP-powered tools 3. Expose agents via the standardized A2A protocol 4. Build multi-agent systems that communicate seamlessly ## Installation ```bash # Install from PyPI pip install ag2a # Install with dev dependencies pip install ag2a[dev] ``` ## Quick Start ### Define an Agent Specification Create a JSON file with your agent's specification: ```json { "name": "MyAssistant", "system_message": "You are a helpful assistant that answers questions concisely.", "model": "gpt-4o", "temperature": 0.7 } ``` ### Run the Agent Start the agent server: ```bash # Export your API key export OPENAI_API_KEY=your-api-key-here # Run the agent with your specification python -m ag2a --spec agent_spec.json --port 8080 ``` ### Connect to the Agent The agent now exposes an A2A protocol endpoint at `http://localhost:8080`. You can connect to it using any A2A-compatible client. ## Adding MCP Tools To use MCP tools, add an `mcp_command` to your agent spec: ```json { "name": "YoutubeAssistant", "system_message": "You can help with analyzing YouTube videos.", "model": "gpt-4o", "mcp_command": "mcp-youtube" } ``` ## Using Structured Response Models For agents that need structured output, you can specify a Pydantic response model: ```bash python -m ag2a --spec agent_spec.json --response-model my_module.ResponseModel ``` ## Contributing Contributions are welcome! Please feel free to submit a Pull Request. ## License This project is licensed under the MIT License - see the LICENSE file for details.