An AI-powered web application that generates custom trackers for tasks, habits, expenses, studies, and more. Built with Flask, React, and Claude AI, with Supabase for data storage and synchronization.

• AI-Powered Tracker Generation: Describe what you want to track in natural language, and the AI creates a custom tracker structure for you
• Dynamic Field Types: Supports text, number, time, date, and boolean field types
• Tracker History: View and manage all your previously created trackers
• Data Persistence: All tracker templates and entries are stored in Supabase for seamless synchronization
• Modern UI: Clean and intuitive React-based user interface

• Flask: Python web framework
• Anthropic Claude AI: For intelligent tracker generation
• Supabase: Database and backend-as-a-service
• Flask-CORS: Cross-origin resource sharing

• React 19: Modern React with hooks
• Vite: Fast build tool and dev server
• ESLint: Code linting and quality

Before you begin, ensure you have the following installed:

• Python 3.8 or higher
• Node.js 16 or higher
• npm or yarn
• A Supabase account and project
• An Anthropic API key (Claude AI)

git clone https://github.com/Muhammad-Rayyan-Moosani/TrackerFlow-AI.git
cd TrackerFlow-AI

# Navigate to backend directory
cd backend

# Create a virtual environment (recommended)
python -m venv venv

# Activate virtual environment
# On macOS/Linux:
source venv/bin/activate
# On Windows:
venv\Scripts\activate

# Install dependencies
pip install -r Requirements.txt

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

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

SUPABASE_URL=your_supabase_url
SUPABASE_KEY=your_supabase_key
CLAUDE-API-KEY=your_anthropic_api_key

You'll need to create the following tables in your Supabase database:

CREATE TABLE tracker_templates (
  id SERIAL PRIMARY KEY,
  user_id TEXT NOT NULL,
  tracker_name TEXT NOT NULL,
  fields_schema JSONB NOT NULL,
  created_at TIMESTAMP DEFAULT NOW()
);

CREATE TABLE tracker_entries (
  id SERIAL PRIMARY KEY,
  template_id INTEGER REFERENCES tracker_templates(id) ON DELETE CASCADE,
  data JSONB NOT NULL,
  created_at TIMESTAMP DEFAULT NOW()
);

cd backend
python app.py

The Flask server will run on http://127.0.0.1:5000

cd frontend
npm run dev

The React app will run on http://localhost:5173 (or another port if 5173 is occupied)

1. Generate a Tracker: Enter a description of what you want to track (e.g., "Daily exercise tracker with exercise type, duration, and calories burned")
2. Fill in Data: The AI generates a custom form with appropriate fields based on your description
3. Submit Entry: Save your tracker entry to the database
4. View History: Access all your previously created trackers and their entries

• "I want a daily tasks tracker with Task, Start Time, End Time, Notes"
• "Create a habit tracker for reading with book title, pages read, and date"
• "Make an expense tracker with item name, amount, category, and date"
• "Build a workout tracker with exercise type, sets, reps, and weight"

TrackerFlow-AI/
├── backend/
│   ├── app.py              # Flask application and API routes
│   ├── prompt.txt          # AI prompt template for tracker generation
│   ├── Requirements.txt    # Python dependencies
│   └── .env                # Environment variables (not in repo)
├── frontend/
│   ├── src/
│   │   ├── App.jsx         # Main application component
│   │   ├── components/
│   │   │   ├── TrackerInput.jsx      # Tracker generation form
│   │   │   ├── TrackerHistory.jsx    # History of created trackers
│   │   │   └── TrackerEntries.jsx    # Display tracker entries
│   │   ├── StylesSheet.css # Application styles
│   │   └── main.jsx        # React entry point
│   ├── package.json        # Node.js dependencies
│   └── vite.config.js      # Vite configuration
└── README.md

Generates a tracker structure based on user prompt.

Request Body:

{
  "prompt": "I want a daily tasks tracker"
}

Response:

{
  "tracker_name": "Daily Tasks Tracker",
  "fields": [
    {"name": "Task", "type": "text"},
    {"name": "Start Time", "type": "time"},
    {"name": "End Time", "type": "time"},
    {"name": "Notes", "type": "text"}
  ]
}

Saves a tracker entry to the database.

Request Body:

{
  "user_id": "user123",
  "tracker_name": "Daily Tasks Tracker",
  "fields_schema": [...],
  "entry_data": {...}
}

Retrieves all tracker templates for a user.

Retrieves all entries for a specific tracker.

Contributions are welcome! Please feel free to submit a Pull Request.

This project is open source and available under the MIT License.

Muhammad Rayyan Moosani

• GitHub: @Muhammad-Rayyan-Moosani

• Anthropic for Claude AI
• Supabase for the backend infrastructure
• The React and Flask communities