GymBro

Inspiration We were inspired by the idea of a personal trainer that provides instant feedback—helping anyone level up their fitness journey.

What it does GymBro uses real-time pose detection to analyze and correct your workout form, offering spoken advice to keep you on track.

How we built it We combined a React Native frontend with Mediapipe-based computer vision. A lightweight backend receives camera frames, processes angles, and then returns tailored feedback.

Challenges we ran into Balancing real-time processing with accuracy and handling cross-platform camera permissions were our biggest hurdles.

Accomplishments that we're proud of We’re proud of delivering a fast, user-friendly MVP that effectively guides proper exercise form.

What we learned We gained hands-on experience with posture analysis, real-time data streaming, and the complexities of multi-platform development.

What's next for GymBro We aim to add more exercises, advanced analytics, and personalized workout plans to help users achieve even better results.

Built With

• base64
• cors
• expo.io
• flask
• json
• mediapipe
• neuphonic
• opencv
• python
• react-native
• typescript