DEVIS is a multi-agent system that helps create and deploy UI/UX designs through voice interaction and AI-powered code generation.
- Voice Agent: Captures and processes verbal feedback from engineers
- Frontend Agent: Generates React components and styles based on requirements
- Screenshot Agent: Captures and analyzes reference designs using Anthropic's Claude
- Deployment Agent: Automatically deploys generated code to GitHub and Vercel
- Install dependencies:
pip install -r requirements.txt- Create a
.envfile with the following keys:
OPENAI_API_KEY=your_openai_key
ANTHROPIC_API_KEY=your_anthropic_key
GITHUB_TOKEN=your_github_token
VERCEL_TOKEN=your_vercel_token
- Install system dependencies for PyAudio:
brew install portaudio- Run the main script:
python main.py- Speak your UI/UX requirements when prompted
- Optionally provide a reference URL for design inspiration
- The system will:
- Process your voice input
- Generate React components and styles
- Create a GitHub repository
- Deploy to Vercel automatically
from devis import DEVIS
devis = DEVIS()
devis.run_design_cycle(reference_url="https://example.com")- Make sure your microphone is properly configured
- Ensure you have sufficient permissions for GitHub and Vercel APIs
- The generated code uses React and Tailwind CSS by default