This repository provides a comprehensive infrastructure for running Generative AI agents, targeting developers and researchers building complex AI systems. It offers a modular backend, router, master agents, database, frontend UI, and CLI, enabling the connection and management of various agent types.

How It Works

The system is built around a microservices architecture orchestrated via Docker Compose. It includes a backend router for managing agent communication, master agents for core logic, a PostgreSQL database for state management, and Redis with Celery for asynchronous task processing. This modular design facilitates scalability and maintainability, allowing individual components to be updated or replaced independently.

Quick Start & Requirements

• Install: Clone the repository, create a .env file from .env-example, and run make up or docker compose up.
• Prerequisites: Docker, Docker Compose, and make (optional).
• Setup: Estimated setup time is minimal, assuming Docker is installed and running.
• Links: Frontend UI: http://localhost:3000/, Swagger API Docs: http://localhost:8000/docs#/

Highlighted Details

• Supports GenAI Agents (via genai-protocol), MCP Servers, and A2A Servers.
• Includes a CLI for agent registration and management.
• Optional Ngrok setup for exposing local WebSocket endpoints.
• Troubleshooting tips for local development and Docker issues are provided.

Maintenance & Community

No specific details on contributors, sponsorships, or community channels (like Discord/Slack) are mentioned in the README.

Licensing & Compatibility

• License: MIT.
• Compatibility: The MIT license generally permits commercial use and linking with closed-source projects.

Limitations & Caveats

The README notes that MCP servers must support streamable-http protocol, and the sse protocol is deprecated in favor of stdio (which is not yet supported). Local development requires specific handling for Docker networking (host.docker.internal).