• ✨ Features
• 🎬 Demo
• 🔧 Prerequisites
• ⚡ Installation & Setup
• 🔑 Configuration
  • Firebase Database Setup
  • Google Gemini AI Setup
  • Alternative: ChatGPT API
• 🚀 Running the Application
• 📱 Building for Release
• 🏗️ Project Structure
• 🛠️ Tech Stack
• ❓ Troubleshooting
• 🤝 Contributing
• 📄 License

• 🍔 AI Food Logging: Simply snap a photo or type a description (e.g., "Oatmeal with blueberries") and get instant macro analysis using Google Gemini AI
• 💬 AI Nutrition Coach: Chat with your personal AI nutritionist for personalized advice, meal suggestions, and dietary guidance

• 📈 Smart Dashboard: Real-time tracking of Calories, Protein, Carbs, and Fat against your personalized TDEE targets
• ⚖️ Weight Tracker: Log your weight daily and visualize trends over time with beautiful interactive charts
• 💧 Habit Tracking: Track daily water intake with quick-add buttons and visual progress indicators
• 📉 Trends & Insights: Analyze your nutrition patterns with detailed charts powered by fl_chart

• 🗓️ Weekly Meal Planner: Plan your entire week with organized meals (Breakfast, Lunch, Dinner, Snacks)
• 🛒 Smart Shopping List: Automatically generate a checklist of ingredients from your meal plan
• 📸 Barcode Scanner: Quickly log packaged foods by scanning barcodes (Mobile only)

• 🌙 Dark Mode Interface: Beautiful, modern dark-themed UI designed for extended use
• 🎯 Intuitive UX: Smooth animations and responsive design across all platforms
• 📱 Cross-Platform: Seamlessly works on Windows, Android, iOS, Web, macOS, and Linux

Main dashboard, AI food logging, and tracking features

Firebase images with store data

Note: Demo videos showcase the application's key features including AI-powered food logging, real-time macro tracking, weight trends, meal planning, and the AI nutrition coach.

Before you begin, ensure you have the following installed:

• Flutter SDK (version 3.0.0 or higher)

  • Download Flutter
  • Verify installation: flutter --version

• Dart SDK (comes with Flutter)

• Git (for cloning the repository)

  • Download Git

• Firebase Account (free tier available)

  • Create Firebase Account

• Google AI Studio Account (for Gemini API)

  • Get Gemini API Key

# Clone the repository
git clone https://github.com/yourusername/macro_tracker_ai.git

# Navigate to project directory
cd macro_tracker_ai

# Install Flutter packages
flutter pub get

# Run code generation for Riverpod and JSON serialization
flutter pub run build_runner build --delete-conflicting-outputs

# Check for any issues
flutter doctor

# List available devices
flutter devices

Tip: If flutter doctor shows any issues, follow the suggested fixes before proceeding.

MacroMate requires two main configurations: Firebase for data storage and Google Gemini AI for intelligent food logging.

Firebase is used for user authentication and storing all user data.

1. Go to Firebase Console
2. Create a new project (e.g., "MacroMate-AI")
3. Enable Authentication (Email/Password) and Cloud Firestore

The project comes with placeholder credentials in lib/firebase_options.dart. You need to replace them with your own:

1. In Firebase Console, go to Project Settings → Your apps
2. Add apps for the platforms you want to support (Web, Android, iOS, etc.)
3. Open lib/firebase_options.dart
4. Replace the dummy values (e.g., YOUR_WEB_API_KEY_HERE) with your actual credentials from Firebase Console

Note: For Android/iOS, you also need to download google-services.json / GoogleService-Info.plist and place them in the respective folders.

The AI food logging and nutrition coach features require a Google Gemini API key.

1. Visit Google AI Studio
2. Sign in with your Google account
3. Click "Get API Key" in the top navigation
4. Click "Create API key"
5. Select your Google Cloud project (or create a new one)
6. Copy the generated API key

Option 1: Configure in App (Recommended)

1. Launch MacroMate
2. Navigate to Settings page (bottom navigation)
3. Find "Gemini API Key" section
4. Paste your API key
5. Click "Save"
6. API key is securely stored locally on your device

Option 2: Environment Variables (Advanced)

# Windows PowerShell
$env:GEMINI_API_KEY="your-api-key-here"
flutter run

# macOS/Linux
export GEMINI_API_KEY="your-api-key-here"
flutter run

Security Note: Never commit API keys to version control. They are stored locally using shared_preferences and never transmitted except to Google AI services.

1. Go to the Dashboard
2. Click "Add Food" → "AI Analysis"
3. Type a food description or take a photo
4. If configured correctly, you'll see macro analysis results

⚠️ Current Status: MacroMate currently uses Google Gemini AI. ChatGPT integration would require code modifications.

If you want to use OpenAI's ChatGPT instead:

What You'll Need:

1. OpenAI API Key from OpenAI Platform
2. Replace google_generative_ai package with dart_openai in pubspec.yaml
3. Modify the AI service implementation in lib/services/

Steps for Integration:

# In pubspec.yaml, replace:
google_generative_ai: ^0.4.6

# With:
dart_openai: ^5.1.0

Then update the AI service to use OpenAI's API. If you need help with this integration, feel free to open an issue!

Once configuration is complete, you can run MacroMate on any platform:

# Windows
flutter run -d windows

# Android (with device/emulator connected)
flutter run -d android

# iOS (macOS only, with simulator/device)
flutter run -d ios

# Web
flutter run -d chrome

# macOS
flutter run -d macos

# Linux
flutter run -d linux

# List all available devices
flutter devices

# Run and select device
flutter run

While the app is running:

• Press r to hot reload
• Press R to hot restart
• Press q to quit

# Build APK (for direct installation)
flutter build apk --release

# Output: build/app/outputs/flutter-apk/app-release.apk

# Build App Bundle (for Play Store)
flutter build appbundle --release

# Build for iOS (requires macOS)
flutter build ios --release

# Open in Xcode for signing and distribution
open ios/Runner.xcworkspace

# Build Windows executable
flutter build windows --release

# Output: build\windows\runner\Release\

# Build for web deployment
flutter build web --release

# Output: build/web/

# Build for macOS
flutter build macos --release

macro_tracker_ai/
├── lib/
│   ├── core/              # Core utilities and constants
│   ├── features/          # Feature modules (dashboard, meals, weight, etc.)
│   │   ├── auth/         # Authentication screens
│   │   ├── dashboard/    # Main dashboard
│   │   ├── food/         # Food logging and AI analysis
│   │   ├── meals/        # Meal planning
│   │   ├── trends/       # Charts and analytics
│   │   ├── weight/       # Weight tracking
│   │   └── settings/     # App settings
│   ├── models/           # Data models (Food, User, Meal, etc.)
│   ├── providers/        # Riverpod state providers
│   ├── services/         # API services (Firebase, Gemini AI, etc.)
│   ├── firebase_options.dart  # Firebase configuration
│   └── main.dart         # App entry point
├── android/              # Android-specific code
├── ios/                  # iOS-specific code
├── windows/              # Windows-specific code
├── web/                  # Web-specific code
├── macos/                # macOS-specific code
├── linux/                # Linux-specific code
└── pubspec.yaml          # Dependencies

• Flutter ^3.0.0 - Cross-platform UI framework
• Dart ^3.0.0 - Programming language

• flutter_riverpod ^2.5.1 - Reactive state management
• riverpod_annotation ^2.3.5 - Code generation for Riverpod

• firebase_core ^4.2.1 - Firebase initialization
• firebase_auth ^6.1.2 - User authentication
• cloud_firestore ^6.1.0 - NoSQL database

• google_generative_ai ^0.4.6 - Gemini AI integration

• fl_chart ^0.68.0 - Interactive charts
• cupertino_icons ^1.0.6 - iOS-style icons

• shared_preferences ^2.2.3 - Local data persistence
• image_picker ^1.0.7 - Camera/gallery access
• mobile_scanner ^5.1.0 - Barcode scanning
• openfoodfacts ^3.4.0 - Food database API
• http ^1.1.0 - HTTP requests
• intl ^0.19.0 - Internationalization
• uuid ^4.4.0 - Unique ID generation

• build_runner ^2.4.9 - Code generation
• freezed ^2.5.2 - Immutable data classes
• json_serializable ^6.8.0 - JSON serialization

# Clean Flutter
flutter clean

# Remove existing symlinks (Windows only)
Remove-Item -Recurse -Force windows/flutter/ephemeral

# Reinstall dependencies
flutter pub get

# Rebuild
flutter run

If you encounter other issues:

1. Check Flutter Doctor: Run flutter doctor -v for diagnostic info
2. Review logs: Use flutter run --verbose for detailed output
3. Search issues: Check GitHub Issues
4. Ask for help: Open a new issue with:
   • Flutter version (flutter --version)
   • Platform (Windows, Android, etc.)
   • Error logs
   • Steps to reproduce

Contributions are welcome!

• This project is a comprehensive example of building a production-grade Flutter AI application using Clean Architecture, Riverpod, and Google Gemini for image recognition.

This project is licensed under the MIT License.