Spark Stack is an tool for building web applications through an AI-powered chat interface. Create quick MVPs and prototypes using natural language prompts. [Blog Post]

- π€ AI-powered code generation
- β‘οΈ Real-time development environment
- π¨ Multiple arbitrary starter templates (see
/images
) - π₯ Team collaboration and management
- π Git version control
- π Live preview
- π§ Chain-of-Thought reasoning for complex asks
- π Support for OpenAI and Anthropic models
- π± Multi-page app generation
- πΈ Sketch and screenshot uploads
- π Deployment to GitHub (+ Netlify, Vercel, etc)
- π Dark mode support
- π Share chats and projects publicly
- πΎ Prompt caching for cheaper responses
- π₯οΈ Virtual browser logs and screenshots for debugging
See backend/config.py
for the environment variables that are used to configure the app.
- Requires modal account to be created and configured.
- Requires AWS account and s3 bucket to be configured.
cd frontend && npm install && npm run dev
cd backend && pip install -r requirements.txt && python main.py
Railway (docker + postgres).

This project was a pressure test for writing code quickly with Cursor so I thought it was interesting to graph how it was built.

Red is my initial 2-day sprint to get an MVP (at this point it worked fully e2e but was a bit brittle). Dots are commits that I arbitrarily checkpointed as I was working on the project.