A modern, mobile-first plant disease detection application built with Next.js, Supabase, and AI-powered inference.

• 🔐 Authentication: Email/password and Google OAuth
• 📱 Mobile-first Design: Responsive with bottom navigation
• 🤖 AI-powered Detection: ONNX runtime with Gemini fallback
• 📊 Analytics Dashboard: Plant health tracking and statistics
• 📚 Disease Library: Comprehensive plant disease database
• 💬 AI Assistant: Chatbot for plant care guidance
• 🌙 Dark/Light Theme: Customizable appearance
• 📱 PWA Ready: Installable web app experience

• Frontend: Next.js 14, TypeScript, Tailwind CSS, shadcn/ui
• Backend: Supabase (Auth, Database, Storage, Edge Functions)
• AI/ML: ONNX Runtime Web, Google Gemini API
• Charts: Recharts
• State Management: Zustand
• Deployment: Vercel

• Node.js 18+ and npm
• Supabase account
• Google Gemini API key (for AI features)

1. Clone the repository:

git clone <repository-url>
cd leaf-labs

2. Install dependencies:

npm install

3. Set up environment variables:

cp .env.example .env.local

Fill in your Supabase and Google Gemini API credentials.

4. Set up Supabase:

   • Create a new Supabase project
   • Enable Google OAuth in Authentication settings
   • Add your GEMINI_API_KEY as a secret in Project Settings > Edge Functions

5. Add your ONNX model:

   • Place your trained plant disease model as public/models/plant-disease-model.onnx

6. Start the development server:

npm run dev

• Email/password signup and login
• Google OAuth integration
• Protected routes with middleware

• Camera capture and file upload
• Client-side ONNX inference
• Gemini API fallback for failed inferences
• Confidence scoring and top-3 predictions

• Plant health statistics
• Interactive charts showing health trends
• Quick action buttons
• Recent scan history

• Comprehensive disease database
• Categorized by type (fungal, bacterial, viral)
• Detailed descriptions and treatment advice
• Scan history with full details

• Gemini-powered chatbot
• Context-aware responses
• Plant care guidance
• Treatment recommendations
• Conversational AI with memory

The app is configured for deployment on Vercel:

1. Connect your repository to Vercel
2. Add environment variables in Vercel dashboard
3. Deploy Supabase Edge Functions using the Supabase CLI
4. Deploy automatically on push to main branch

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Submit a pull request

MIT License - see LICENSE file for details