This application provides an interactive user interface for the CrewAI framework, simplifying the creation and management of AI agent crews without requiring coding. It targets users who want to leverage autonomous AI agents for complex workflows, offering a streamlined experience for defining roles, tasks, and execution processes.

How It Works

The application uses a Node.js frontend (TypeScript, Next.js, GraphQL) to manage user interactions and a Python backend (via node-calls-python) to execute CrewAI orchestration. It leverages PostgreSQL for data persistence and Prisma for database interactions. The architecture allows for role-based agent customization, dynamic task assignment, and supports both sequential and hierarchical process execution.

Quick Start & Requirements

• Installation: Clone the repository, install Node.js dependencies (npm install or yarn), create and activate a Python virtual environment (python -m venv venv, source venv/bin/activate), install Python requirements (pip install -r requirements.txt), and set up environment variables in a .env file (copy .env.template).
• Prerequisites: PostgreSQL, Node.js, Python 3.x, Gemini API Key.
• Setup: Run database migrations (npx prisma generate, npx prisma migrate deploy).
• Start: Run npm run dev to start the development server. Access at http://localhost:3000.
• Non-developer setup: Use provided setup_win.bat or setup_linux_mac.sh scripts.

Highlighted Details

• Intuitive UI for creating and managing AI crews.
• Role-based agent customization via forms.
• Support for sequential and hierarchical task execution.
• Ability to save mission outputs.
• Includes ARXIV and PubMed tools for agent functionality.

Maintenance & Community

The project is actively maintained by Eng-Elias. Contributions are welcome via pull requests.

Licensing & Compatibility

Released under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

Currently relies on the Gemini model, with plans to integrate others. The setup requires familiarity with both Node.js and Python development environments, although simplified scripts are provided for non-developers.