A minimalist, multimodal AI assistant powered by Puter.js.
- Chat: Text-based conversation with AI (models can be selected in settings).
- Multimodal:
- Text-to-Image: Generate images from prompts.
- Text-to-Video: Create short videos.
- Text-to-Speech: Synthesize audio.
- OCR: Extract text from uploaded images.
- Transcription: Transcribe uploaded audio files.
- Privacy Mode: "Incognito" mode where history is not saved to local storage.
- Responsive: Mobile-first design with PWA capabilities.
- Export: Download entire chat history as a ZIP file containing Markdown and media.
- Framework: React + Vite
- Styling: Tailwind CSS
- AI Integration: Puter.js (v2)
- Markdown Rendering: react-markdown (GFM, KaTeX, Highlight.js)
-
Clone the repository
git clone https://github.com/yourusername/zen-ai.git cd zen-ai -
Install dependencies
npm install
-
Run development server
npm run dev
To create a production build (optimized for static hosting):
npm run buildThe output will be in the dist directory.
This project is optimized for Cloudflare Pages, Vercel, or Puter.com hosting.
MIT