Valet - AI Health Agent

A full-stack AI agent web application that provides personalized wellness insights by analyzing your calendar, health logs, and daily context.

🚀 Features

• Smart Calendar Integration: Sync with Google Calendar to analyze your schedule
• AI-Powered Insights: Get personalized wellness recommendations using Gemini AI
• Health Tracking: Log and track your health metrics
• Real-time Dashboard: View your daily timeline and AI recommendations

🛠️ Tech Stack

Frontend

• Next.js 14 (App Router) with TypeScript
• Tailwind CSS for styling
• shadcn/ui components
• Google OAuth integration

Backend

• FastAPI with Python
• MongoDB Atlas for data storage
• Google Calendar API integration
• Gemini AI for intelligent analysis

📁 Project Structure

valet/
├── frontend/                 # Next.js application
│   ├── app/                 # App Router pages
│   ├── components/          # Reusable UI components
│   ├── lib/                # Utilities and configurations
│   └── types/              # TypeScript type definitions
├── backend/                 # FastAPI application
│   ├── app/                # FastAPI app and routes
│   ├── models/             # Data models
│   ├── services/           # Business logic
│   └── config/             # Configuration files
└── docs/                   # Documentation

🚀 Quick Start

Prerequisites

• Node.js 18+
• Python 3.9+
• MongoDB Atlas account
• Google Cloud Console project

Environment Setup

1. Clone the repository

   git clone <repository-url>
   cd valet

2. Frontend Setup

   cd frontend
   npm install
   cp .env.example .env.local
   # Configure your environment variables
   npm run dev

3. Backend Setup

   cd backend
   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   pip install -r requirements.txt
   cp .env.example .env
   # Configure your environment variables
   uvicorn app.main:app --reload # On Different Port: uvicorn app.main:app --reload --port 8001

Environment Variables

Frontend (.env.local)

NEXT_PUBLIC_API_URL=http://localhost:8000
NEXT_PUBLIC_GOOGLE_CLIENT_ID=your_google_client_id

Backend (.env)

MONGODB_URI=your_mongodb_atlas_uri
GOOGLE_CLIENT_ID=your_google_client_id
GOOGLE_CLIENT_SECRET=your_google_client_secret
GEMINI_API_KEY=your_gemini_api_key

🔧 API Endpoints

Calendar

• POST /calendar/sync - Sync Google Calendar events
• GET /calendar/events - Get user's calendar events

Agent

• POST /agent/analyze - Analyze user context with Gemini AI
• GET /agent/recommendations - Get stored AI recommendations

Health

• POST /health/logs - Log health metrics
• GET /health/logs - Get health history

🤖 AI Features

The application uses Gemini AI to provide:

• Schedule Analysis: Understand your daily commitments and stress levels
• Health Insights: Correlate health logs with calendar events
• Personalized Recommendations: Suggest wellness actions based on your context
• Contextual Awareness: Consider sleep, medication, and recent activities

📊 Dashboard Features

• Timeline View: Visual representation of today's calendar events
• Health Summary: AI-generated health insights and recommendations
• Interactive Chat: Direct communication with the health agent
• Real-time Updates: Live sync with calendar and health data

🔐 Security

• Google OAuth 2.0 for secure authentication
• MongoDB Atlas with proper access controls
• Environment variable protection for API keys
• CORS configuration for frontend-backend communication

📝 License

MIT License - see LICENSE file for details.

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

📞 Support

For support or questions, please open an issue in the repository.