Count exercise reps on-device, for free — no SDK key, no cloud. Apple Vision body-pose rep counting with hysteresis + dual-joint anti-cheat. The open alternative to paid pose-fitness SDKs.
A lightweight, privacy-first, real-time rep counter for common bodyweight exercises. GC_Fit uses MediaPipe's Pose model and OpenCV to detect joint landmarks from a webcam feed and count repetitions of exercises (push-ups, sit-ups, squats) based on simple geometric rules.
🏋️♂️🤖Real-time AI Gym Trainer using YOLOv8, OpenCV and Python. Features Pose Estimation and Form Correction.
A computer vision pipeline that detects squats and counts reps in real time from video using MediaPipe pose estimation, geometric joint-angle analysis, and a hysteresis-based state machine — tested across multiple camera angles including front-facing and side profile views.
Exercise Detector is a real-time system that recognizes 7 different exercises using pose estimation and deep learning. It analyzes exercise form, counts repetitions, and achieves 99% accuracy on real-world detection. The lightweight model is optimized for edge devices, enabling fast and efficient performance on mobile and low-end hardware.
RepTrack AI is a computer-vision fitness analytics app that counts exercise reps from uploaded video and live camera input using pose estimation and generalized movement logic.
Deadlift-o-Meter is a project that utilizes a Scikit-Learn model, Mediapipe, and Tkinter to count correct deadlift reps using a live webcam feed. The application analyzes the user's body movements and provides real-time feedback on their performance.
A minimalist, AMOLED-first Rep Counter PWA designed for peak performance and zero distractions. Built with Svelte 5 and Tailwind CSS v4.
An AI-powered personal fitness coach with smart workout planning and progress tracking.
Real-time action recognition (squat/pushup/standing) using MediaPipe pose landmarks + joint angle geometry + Random Forest classifier
Count exercise repetitions from video with pretrained YOLO11-pose + ByteTrack. Hysteresis state machine, near-miss detection, angle chart, web UI and CLI, CPU or GPU, no training.
Add a description, image, and links to the rep-counter topic page so that developers can more easily learn about it.
To associate your repository with the rep-counter topic, visit your repo's landing page and select "manage topics."