💪 AI Fitness Assistant 🤖

Highlights:

• 🚀 Tech stack: Next.js, React, Tailwind & Shadcn UI
• 🎙️ Voice AI Assistant (Vapi)
• 🧠 LLM Integration (Gemini AI)
• 🏋️ Personalized Workout Plans
• 🥗 Custom Diet Programs
• 🔒 Authentication & Authorization (Clerk)
• 💾 Database (Convex)
• 🎬 Real-time Program Generation
• 💻 Layouts
• 🎭 Client & Server Components

Features

• Smart AI Assistant: Engage in conversation with an AI that asks about your fitness goals, physical condition, and preferences
• Personalized Workout Plans: Get custom exercise routines based on your fitness level, injuries, and goals
• Diet Recommendations: Receive personalized meal plans accounting for your allergies and dietary preferences
• User Authentication: Sign in with GitHub, Google, or email/password
• Program Management: Create and view multiple fitness programs with only the latest one active
• Responsive Design: Beautiful UI that works across all devices

Available Scripts

• npm run dev - Start Next.js development server
• npm run build - Build the application for production
• npm run start - Start production server
• npm run lint - Run ESLint
• npm run convex:dev - Start Convex development mode (watches for changes)
• npm run convex:deploy - Deploy Convex functions to development
• npm run convex:deploy:prod - Deploy Convex functions to production

Getting Started

Quick Setup

1. Clone the repository

   git clone <repository-url>
   cd ai-fitness-trainer

2. Install dependencies

   npm install

3. Set up Convex (Database)

   Important: Convex setup is required before running the app!

   # Install Convex CLI (if not already installed)
   npm install -g convex
   
   # Login to Convex
   npx convex login
   
   # Initialize and deploy Convex backend
   npx convex dev

   This will:

   • Create a new Convex project
   • Generate your deployment URL
   • Create a .env.local file with NEXT_PUBLIC_CONVEX_URL

   For detailed Convex setup instructions, see SETUP.md

4. Set up your environment variables

   Create a .env.local file in the root directory with the following variables:

   # Convex Database (auto-generated by `npx convex dev`)
   CONVEX_DEPLOYMENT=your-deployment-name
   NEXT_PUBLIC_CONVEX_URL=https://your-deployment.convex.cloud
   
   # Clerk Authentication
   NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_test_...
   CLERK_SECRET_KEY=sk_test_...
   
   # Clerk Redirect URLs
   NEXT_PUBLIC_CLERK_SIGN_IN_URL=/sign-in
   NEXT_PUBLIC_CLERK_SIGN_UP_URL=/sign-up
   
   # Clerk Webhook Secret (for Convex HTTP endpoint)
   CLERK_WEBHOOK_SECRET=whsec_...
   
   # Gemini AI (for Convex HTTP endpoint)
   # Also set in Convex: npx convex env set GEMINI_API_KEY your-key
   GEMINI_API_KEY=your-gemini-api-key
   
   # Vapi Voice AI
   NEXT_PUBLIC_VAPI_WORKFLOW_ID=your-workflow-id
   NEXT_PUBLIC_VAPI_API_KEY=your-vapi-api-key

5. Update Convex configuration

   • Create JWT Template in Clerk (REQUIRED):
     • Go to Clerk Dashboard → Configure → JWT Templates
     • Create a new template with name exactly convex (lowercase)
     • This fixes the "No JWT template exists with name: convex" error
   • Update convex/auth.config.ts with your Clerk domain (see SETUP.md for details)
   • Set Convex environment variables:

     npx convex env set GEMINI_API_KEY your-gemini-api-key
     npx convex env set CLERK_WEBHOOK_SECRET your-clerk-webhook-secret

6. Run the development server

   npm run dev

7. Open http://localhost:3000 in your browser

Need Help with Setup?

For detailed setup instructions, especially for Convex configuration, see SETUP.md.

Deployment

This application can be easily deployed to Vercel:

npm run build
npm run start

Or connect your GitHub repository to Vercel for automatic deployments.

Technologies Used

• Next.js: React framework for building the frontend and API routes
• Tailwind CSS & Shadcn UI: For styling and UI components
• Clerk: Authentication and user management
• Vapi: Voice agent platform for conversational AI
• Convex: Real-time database
• Gemini AI: Large Language Model for generating personalized fitness programs

Learn More

To learn more about the technologies used in this project:

• Next.js Documentation
• Clerk Documentation
• Vapi Documentation
• Convex Documentation
• Gemini AI Documentation