This project provides an AI-powered platform for automatically generating and editing enterprise application configurations through modular agent flows. It targets developers and power users seeking to accelerate full-stack web application development by leveraging AI for structured generation, offering a benefit of rapid, consistent app specification creation.

How It Works

The system employs a modular, agent-based architecture orchestrated by FastAPI. User interactions are routed to specialized agent flows (e.g., Create App, Edit App) that execute a series of AI and tool-based steps. Core to its approach is the use of OpenAI APIs for AI reasoning, combined with Pydantic models and JSON schemas to ensure structured, type-safe, and consistent output generation. Real-time communication via WebSockets enhances the user experience by providing immediate feedback on flow execution and chat messages.

Quick Start & Requirements

• Installation: Clone the repository, set up Python virtual environments for backend (venv) and install dependencies (pip install -r requirements.txt), and Node.js dependencies for frontend (npm install).
• Configuration: Requires setting environment variables, notably OPENAI_API_KEY, DB_URL (defaults to SQLite), and FRONTEND_ORIGIN for the backend, and NEXT_PUBLIC_BACKEND_URL for the frontend.
• Running: Start the backend with python main.py or uvicorn main:app --reload, and the frontend with npm run dev.
• Prerequisites: Python 3.x, Node.js, OpenAI API key.
• Links: Backend API at http://localhost:8000, Frontend at http://localhost:3000.

Highlighted Details

• Modular agent-based system for AI-driven app generation and editing.
• Leverages OpenAI APIs with structured generation via Pydantic models and JSON schemas.
• Real-time chat and status updates using WebSockets.
• Supports distinct agent flows for creating and editing applications.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or roadmap are provided in the README. Contributions are welcomed via pull requests.

Licensing & Compatibility

This project is licensed under the MIT License, which is permissive and generally compatible with commercial use and closed-source linking.

Limitations & Caveats

The "Application Preview" feature is explicitly noted as a work in progress. The system's functionality is dependent on the availability and cost of the OpenAI API. Setup requires careful configuration of API keys and environment variables.