Project · Full-Stack · AI
FitHub Gym
Gym management with a computer-vision rep counter.
A Django gym platform covering memberships and subscriptions, trainer dashboards and workout videos, plus an AI trainer that counts biceps curls from the webcam using OpenCV and MediaPipe pose tracking over WebSockets.
Completed
- Members
- Subscriptions
- Payments
- Webcam
- Pose model
- Rep counter
- Trainer dashboard
- Chatbot
What problem does FitHub Gym solve?
Running a gym means managing memberships, payments, trainers and workout guidance in separate places. FitHub Gym (Fitness Hub in the repository) puts them in one Django web app, with a workout video library and an AI trainer that tracks reps from the webcam.
Key features
- Memberships, subscriptions and Razorpay payments
- AI trainer: OpenCV + MediaPipe rep counting
- Real-time video over Django Channels
- Fitness chatbot and trainer dashboard
Architecture
- Frontend: HTML5, CSS3, JavaScript and Bootstrap.
- Backend: Django with OTP-verified sign-in, membership plans, and admin and trainer panels.
- Real time: Django Channels (WebSockets).
- AI trainer: OpenCV and MediaPipe pose estimation for rep tracking and form feedback.
- Chatbot: OpenAI-powered assistant for workout, diet and membership questions.
- Data and payments: SQLite in development, PostgreSQL or MySQL in production; Razorpay payments.
Tech stack
- Python
- Django
- Django Channels
- OpenCV
- MediaPipe
- Razorpay
- OpenAI API
Atharva's role
Designed and built the full stack.
Current status
Completed. The source code is on GitHub; there is no public deployment.
Sources
Page updated by Atharva Sonar.
More projects by Atharva Sonar
- SpendDecode — AI-powered personal finance and spending intelligence.
- Velquix Learn — Structured roadmaps and curated resources for developers.
- ClaimBlitz — Nine AI agents that process an insurance claim together.
- SafeHer AI — Proactive personal-safety monitoring with risk scoring.
- All projects