A Node-Based Frontend for CrewAI: Revolutionizing AI Workflow Creation
Features • Installation • Usage • Build • Documentation • Contributing
CrewAI-GUI empowers you to create sophisticated AI workflows with ease:
- 🖱️ Intuitive Node-Based Interface: Design complex AI agent interactions through a user-friendly drag-and-drop interface
- 🔗 JSON Export: Seamlessly export your CrewAI designs to JSON, enhancing modularity and reusability
- 🧠 Flexible AI Backend: Full support for both GPT-4 API and Ollama, catering to various AI needs
- 💻 Cross-Platform Compatibility: Create AI workflows on Windows, Linux, or macOS with equal efficiency
Click to watch our comprehensive video guide
Frontend GUI
Install the required dependencies:
pip install PySide6Backend
Install the necessary packages:
For Linux:
pip install 'crewai[tools]' langchain crewai networkxFor Windows:
pip install crewai[tools] langchain crewai networkxFrontend GUI
Launch the CrewAI-GUI interface:
python frontend.pyCreate, manipulate, save, and load Directed Acyclic Graph (DAG) structures for CrewAI as JSON files.
Backend
Run the backend with different configurations:
For GPT-4:
python backend.py --graph example.json --keys credentials.ini --tee output.logFor Ollama (e.g., Mistral):
python backend.py --graph example.json --llm mistral --tee output.logThe backend seamlessly converts JSON files into CrewAI tasks and agents.
Frontend GUI
Create a standalone executable with PyInstaller:
pip install pyinstaller
cd src
pyinstaller --onefile --additional-hooks-dir=. frontend.pyBackend
Package the backend with cx_Freeze:
pip install cx_Freeze
cd src
python setup-backend.py buildExplore CrewAI-GUI in-depth with our comprehensive GitHub Pages Documentation.
If you want see some example code for CrewAI, you can see crewai examples
Discover real-world applications of CrewAI-GUI in our example graph source.
- 🔒 The current version supports a limited set of node types and slots
- 🚧 Some advanced CrewAI variables and features are planned for future releases
We welcome contributions to CrewAI-GUI! Please refer to our CONTRIBUTING.md for guidelines on:
- Submitting pull requests
- Reporting issues
- Requesting new features
Join our community and help shape the future of AI workflow design!
CrewAI-GUI is open-source software, released under the MIT License. For full details, see the LICENSE file.
Have questions, suggestions, or want to collaborate? Open an issue on our GitHub repository.