This project provides a web UI for interacting with AutoGen, a framework for building multi-agent LLM applications. It's designed for developers and researchers looking for a straightforward way to prototype and test multi-agent conversations using AutoGen's AgentChat API, offering a chat interface powered by Next.js and a FastAPI backend.

How It Works

The application leverages AutoGen's AgentChat API to manage multi-agent conversations. A FastAPI backend serves a /generate endpoint that orchestrates agent interactions based on a predefined team configuration (specified in a JSON file). The backend streams results to a Next.js frontend, which presents a chat-like interface for users to input prompts and receive responses from the agent team.

Quick Start & Requirements

• Install via pip: pip install autogenui or from source.
• Requires Python 3.9+.
• Requires OPENAI_API_KEY environment variable.
• Run server: autogenui (default port 8081).
• Frontend development: cd frontend, yarn install, yarn dev.
• Official Docs: AutoGen Studio (mentioned as a more complete example).

Highlighted Details

• Demonstrates building UIs with the AutoGen AgentChat API.
• Backend built with FastAPI, frontend with Next.js.
• Supports streaming results to the client.
• CLI for running the UI server.

Maintenance & Community

This project is presented as a starting point. For more comprehensive features and updates, users are directed to the AutoGen Studio project.

Licensing & Compatibility

The repository does not explicitly state a license in the provided README. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is explicitly stated as a starting point with potential for breaking changes due to ongoing API evolution in AutoGen. Features like storing history, multiple team configurations, and security (authentication/authorization) are noted as areas for future extension, with AutoGen Studio recommended for a more complete solution.