A lightweight fitness demo app with AI voice coaching, real-time pose estimation, and exercise tracking.

1. Install dependencies:

pip install -r requirements.txt

2. Configure environment variables:

cp .env.example .env
# Edit .env with your DigitalOcean AI Agent credentials

3. Run the app:

streamlit run app.py

• Real-time pose estimation using MediaPipe
• AI voice coaching (Nice vs Mean personalities)
• Push-ups and Tricep Dips tracking
• Dark-themed UI
• Demo-ready with fake historical data

• Python 3.10+
• Streamlit (UI)
• OpenCV (Webcam)
• MediaPipe (Pose estimation)
• DigitalOcean AI Agent (Voice generation)
• pyttsx3 (Local text-to-speech)

1. Start screen
2. Dashboard
3. Select AI personality
4. Choose exercise
5. Webcam opens with skeleton overlay
6. Reps counted with voice feedback
7. Stats screen with fake historical data

This is a demo prototype. Many elements are intentionally hard-coded or faked for demonstration purposes.