Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI-powered fitness assistant for real-time pose estimation, exercise counting, and workout feedback.
| Date | Stars |
|---|---|
| 2026-07-24 | 382 |
| 2026-07-25 | 382 |
| 2026-07-28 | 386 |
| 2026-07-30 | 386 |
| 2026-08-06 | 386 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Good-GYM: AI Fitness Assistant 💪 <div align="center"> <img src="assets/Logo.png" width="200px" alt="Good-GYM Logo"> [](https://github.com/yo-WASSUP/Good-GYM/stargazers) [](https://github.com/yo-WASSUP/Good-GYM/network/members) [](https://github.com/yo-WASSUP/Good-GYM/blob/main/LICENSE) **AI Fitness Assistant** [](https://apps.apple.com/cn/app/goodgym/id6761142874?l=en-GB) [English](README.md) | [中文](README_CN.md) []( https://www.xiaohongshu.com/explore/69a3fc8f000000001a01d824?xsec_token=ABhBaGBXZRds0UaBSmH1YsFBMWMX1h0DqzL4nRfvpZMm8=&xsec_source=pc_user) </div> --- <div align="center"> ### 📱 Download Good-GYM for iOS <img src="assets/ios-demo-en.gif" width="250px" alt="Good-GYM iOS demo"> <img src="assets/Screenshot-ch-appstore.jpg" width="250px" alt="Good-GYM App Store"> <img src="assets/Screenshot-en-history.PNG" width="250px" alt="Workout history"> <img src="assets/Screenshot-en-goal.PNG" width="250px" alt="Goal settings"> <img src="assets/Screenshot-en-setting.PNG" width="250px" alt="Settings"> [](https://apps.apple.com/cn/app/goodgym/id6761142874?l=en-GB) </div> ## 🆕 Changelog - **2025-06-07**: Major update! Dropped YOLO models and all GPU support. Good-GYM now uses RTMPose only for pose detection, supports CPU runtime, and is more compatible and easier to use. - **2025-06-12**: Optimized `exercise_counters.py`, improved counting accuracy, and cleaned up the code structure. - **2025-11-14**: Reverted to synchronous pose detection due to accuracy issues with asynchronous pose detection. Fixed a crash when switching from the statistics view back to the detection view. - **2025-11-15**: Added the exercise type database. All exercise configurations are now managed in `data/exercises.json`, so custom exercise types can be added or edited without changing code. - **2026-03-04**: Added optional GPU acceleration support for NVIDIA GPUs. - **2026-03-28**: Added mobile support. The iOS app is now available. - **2026-06-29**: Optimized the desktop UI and video streaming logic. - **2026-07-02**: Added `build_portable.ps1` for reproducible Windows portable builds. ## 📦 Release - **2026-07-02**: Published the Windows portable executable package `Good-GYM-Portable.zip` on [GitHub Releases](https://github.com/yo-WASSUP/Good-GYM/releases/latest). ## 🔮 Future Development - [x] Multi-language interface - [x] Improve pose detection accuracy - [x] Add support for more exercise types - [x] Add custom exercise templates - [x] Recognize motion accuracy - [x] Mobile app support - [ ] Motion correction prompts - [ ] Add voice interaction control --- <img src="assets/demo-en.gif" width="800px" alt="Demo"> <img src="assets/demo-status-en.gif" width="800px" alt="Status demo"> ## ✨ Features - **Real-time exercise counting** - Automatically counts your workout repetitions - **Multiple exercise support** - Includes squats, push-ups, sit-ups, dumbbell movements, and many more - **Advanced pose detection** - Uses RTMPose for accurate tracking - **CPU recommended** - CPU inference is the default; this RTMPose real-time webcam pipeline is small, so GPU acceleration may be slower - **Visual feedback** - Real-time skeleton visualization and angle measurement - **Workout statistics** - Track your fitness progress - **User-friendly interface** - Clean PyQt5 interface with intuitive controls - **Works with standard webcams** - No special hardware required - **Runs
Excerpt of 9,280 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:168aacdcb3bf55e8, topic:computer-vision, desc:pose estimation