Overview

A feature-rich fitness tracking application with ML-powered nutrition analysis. It studies a user's macro and micronutrient gaps and suggests personalized meals and recipes to fill them, backed by the Open Food Facts database and a user-built custom food database.

Role

Mobile developer

Platforms

iOS & Android

Stack focus

Flutter, Firebase, Riverpod, Hive, ML

Data

Open Food Facts API

Gallery

The Challenge

Most nutrition trackers tell users what they ate but not what to do about it. The goal was an app that closes that loop — turning raw tracking data into concrete, personalized guidance on what to eat next, without burying the user in spreadsheets.

The Solution

The app analyzes logged intake against macro and micronutrient targets and uses ML to surface meals and recipes that close the gaps. Users can scan barcodes and food labels, pull entries from Open Food Facts, and build their own food and recipe database. FL Chart powers the nutrition visualizations, with Firebase and Hive handling data and offline persistence and Riverpod managing state.

Key Features

Tech Stack

Flutter Firebase Riverpod Hive OpenFoodFacts API FL Chart Machine Learning

My Role

I built the Flutter app end to end — the nutrition analysis and suggestion logic, Open Food Facts integration with barcode and label scanning, the custom food/recipe database, FL Chart visualizations, and offline-capable storage with Firebase and Hive.