Vyom

Project Overview

Vyom is a feature-packed wellness app that brings yoga posture tracking, guided yoga tutorials, and smart meal planning into one unified experience. It runs real-time posture correction using on-device machine learning optimized for Arm hardware, ensuring fast, private, and reliable performance. The app also includes seamless Android TV integration, making guided yoga sessions more immersive on larger screens.

Functionality

Yoga Posture Tracking (On-Device ML)

• Real-time body landmark detection and angle calculations
• Live posture correction and accuracy scoring
• Fully on-device for low latency and privacy

Yoga Tutorials • Guided routines for beginner to advanced levels
• Step-by-step video or GIF instructions
• Seamless streaming to Android TV for big-screen practice

Meal Planner and Calorie Tracking • Personalized calorie goals
• Macro tracking such as carbs, protein, and fats
• Smart meal recommendations

Tech Stack

• Flutter (Mobile and Android TV)
• Node.js and PostgreSQL
• On-device ML model optimized for Arm
• JWT authentication and SMTP OTP

Setup Instructions (Arm-Compatible)

Prerequisites
• Node.js 18 or higher
• PostgreSQL
• Flutter SDK

Environment Setup Copy the .env.example file to .env and update the values for DATABASE_URL, JWT_SECRET, and SMTP settings.

Server Setup Enable Corepack and prepare pnpm, then install dependencies and push the database schema.

Run Mobile App Navigate to the frontend directory and run: flutter run

Run Android TV App Navigate to the frontend_tv directory and run: flutter run

Built With

• flutter
• node.js
• postgresql