Your phone counts your squats. For real.
An experiment in Kotlin, Computer Vision, and AI
"You do not rise to the level of your goals. You fall to the level of your systems."
This project was born from a simple question: What if technology could make good habits effortless?
Inspired by Atomic Habits, I wanted to build a system that makes habits obvious, attractive, easy, and satisfying.
But beyond habit formation, this was my personal journey to explore Computer Vision, master TensorFlow Lite,
and build with Jetpack Compose.
"Every action you take is a vote for the type of person you wish to become."
"A habit must be established before it can be improved."
This app establishes the system. You improve the reps.
// Core Stack
Jetpack Compose + Material3 // Modern UI
TensorFlow Lite + MoveNet // AI pose detection
Room Database + Coroutines // Data persistence
MVVM + Clean Architecture // Solid foundation
// The Interesting Part
MoveNet Lightning → Optimized ML model (~4MB)
GPU-accelerated → Hardware inference
17 body keypoints → Full pose tracking
Custom squat logic → Validates proper form"The purpose of setting goals is to win the game. The purpose of building systems is to continue playing the game."
This project is open source for a reason. Want to explore TensorFlow Lite on Android? Learn Jetpack Compose in a real project? Study Clean Architecture? Experiment with Computer Vision?
Clone it. Break it. Fix it. Learn.