AI Fitness Coach — A full-stack AI fitness and nutrition assistant built with Next.js and Gemini AI. Generates personalized workout plans and diet guidance with chat sessions, profile memory, streaming AI responses, and a modern UI. Deployed on Vercel.

An AI-powered fitness assistant that generates personalized workout and diet plans based on user needs.

Your Ultimate Fitness Companion

Microsoft AI School 8기, First Team Project

vital-ai is a Django-based API that integrates with OpenAI's ChatGPT to provide personalized health advice based on Apple Health data. The system analyzes users' sleep patterns, step counts, and activity levels, generating custom insights and suggestions for improved well-being.

HUBXAi Intelligence Labs Biomechanics Aware Intelligence Layer for Human Performance. AI coaching, recovery intelligence, biomechanics diagnostics, and adaptive performance systems built by FastFitHub.

Open-source AI fitness body transformation simulator — production-ready Next.js SaaS that visualizes physique goals with photorealistic AI body transformation. For personal trainers, gyms, and fitness apps. Stripe billing, credits, NextAuth, and Prisma.

大健康行为数据基础设施 · AI×Web5 · PoPB v1.0 MIT开源 · 用户拥有自己的健康数据 · 7 years live · 9 AI Agents 24/7

This project implements an AI-powered exercise classification system that detects and classifies different workout poses (e.g., push-ups, squats, planks, lunges, etc.) from pose landmark data. The model leverages MediaPipe pose estimation outputs and Random Forest machine learning to identify exercises based on human body landmarks.

Real-time exercise repetition counter using computer vision and pose estimation. Detects and counts reps for 5 exercises with form validation and session analytics. Powered by MediaPipe and OpenCV.

AI fitness platform — biometric-based personalised training plan generation, progressive overload tracking, fatigue index monitoring, and LLM-driven adaptive weekly coaching.

Interactive AI-powered fitness guide offering personalized workout and diet plans

SmartFit AI uses machine learning to analyze fitness and health data, predict calorie burn, BMI, and body fat, and group users into fitness archetypes. It combines PCA, K-Means, and neural networks to generate personalized workout and diet recommendations with clear visual insights.

Real-time AI-powered Ab Wheel rep counter. Uses MediaPipe for robust pose estimation and a smart state machine to accurately track exercise repetitions and record sessions.

Self-supervised motion error detection for fitness exercises using trajectory extraction and contrastive learning. (NYCU Deep Learning Final Project)

AI Pose Estimation for Fitness Tracking (Capstone Project)

AI-powered fitness recommendation system using a hybrid Reinforcement Learning and Genetic Algorithm approach (HAFRA) with NLP-based user interaction.

An AI-powered fitness assistant utilizing Google Gemini and Firebase to provide data-driven body recomposition strategies and macronutrient optimization.

A deep learning-based system for detecting weight training form errors using 3D-CNN enhanced with a novel biomechanical attention mechanism. This project includes a full pipeline from video-based pose estimation (MediaPipe) to skeleton-based action recognition and future error classification.