Frigo Hero Pro

FrigoHero-Pro : Turn "I saw this" into dinner. We map saved recipes to your fridge, generating smart grocery lists to go from inspiration to the table instantly. Stop just saving start cooking.

Comment

Have you ever stood in front of your open fridge wondering “What’s for dinner?”, only to find that the answer lies in a single photo that transforms ingredient chaos into the meal of your dreams? 📸🍽️✨

💡 Inspiration Every day, millions of people worldwide face a recurring Hidden Kitchen Crisis characterized by a frustrating mix of food waste and nutritional guesswork. This problem is underscored by the staggering reality that nearly 1.3 billion tons of food are wasted globally each year, while rising costs of living make household budget management more difficult than ever.

Frigo Hero was born from my desire to bridge this gap by treating the refrigerator not just as a cold storage box, but as a real-time nutritional logistics engine that starts with the user’s actual reality — exactly what is sitting in their fridge and pantry.

I was inspired to transform the mundane chore of “checking the fridge” into a personalized culinary adventure that removes the cognitive load of calculating macros, planning meals, and deciding what to cook. By integrating advanced biometric data such as Age, Height, and Weight with specific fitness goals and critical allergy restrictions, I created an ecosystem that makes healthy, zero-waste eating feel intuitive and emotionally engaging — wrapped in a warm, Ghibli-inspired experience 🌱🎥.

Beyond AI-recommended recipes, Frigo Hero introduces a powerful shift: users are no longer limited to inspiration chosen for them — they can bring their own inspiration into real life.

🍳 From Saved Recipe to Dinner Made — The Eitan Bernath Use Case

Think of creators like Eitan Bernath, whose recipes are saved by millions on Instagram but rarely cooked. Frigo Hero closes this gap.

Instead of endlessly saving recipes, users can:

  • Upload or paste their own recipe (text or image)
  • In the future: paste a recipe video or link directly (Instagram, TikTok, YouTube)
  • Instantly transform inspiration into an actionable cooking plan

This means:

“I saw this recipe” → “I know what I’m missing” → “It’s on my table tonight.”

Just like Eitan’s philosophy of making cooking accessible, Frigo Hero turns passive inspiration into real execution.

🧠 Main Functionalities: Precision Nutrition, Custom Recipes & Smart Logistics

1️⃣ Biometric Integration & Fitness Intelligence 🏋️‍♂️

Biological Analysis: The AI establishes a nutritional foundation by analyzing your specific Age, Height (e.g., 180 cm), and Weight (e.g., 75 kg).

Custom Objectives: Whether your goal is Weight Loss, Maintenance, or Muscle Gain, the system dynamically adjusts caloric density, macros, and portion sizes.

Zero Manual Math: All nutritional equations are handled automatically by the AI, ensuring every meal serves your body’s exact needs — no guesswork required 🧮✨

2️⃣ AI “Fridge-to-Plate” Analysis 🤳🍳

Smart Scan: A single photo of your fridge or pantry allows the AI to recognize available ingredients with high precision.

Constraint Filtering: Ingredients are cross-referenced with Allergies (e.g., Lactose, Peanuts) and Dietary Regimes (Halal, Vegan, etc.) to guarantee full safety.

Macro Calculation: Every recipe includes a complete breakdown of Calories, Proteins, and Carbohydrates per serving.

Dynamic Scaling: Ingredient quantities are automatically scaled based on the number of people, ensuring zero-waste cooking ♻️

3️⃣ Add Your Own Recipe — AI Gap Analysis ✍️🤖

I added an “Add Own Recipe” button directly into the ScannerComponent.

Before scanning the fridge, users can now:

  • Input a custom recipe as text
  • Upload a recipe image
  • (Planned) Upload or paste a recipe link or video

When “Start Analysis” is triggered:

  • The AI receives both the fridge photos AND the user’s manual recipe
  • Ingredients are extracted from the custom recipe

  • A Gap Analysis is performed by comparing:

    • What the recipe requires
    • What actually exists in the fridge and pantry

The system then:

  • Identifies missing ingredients
  • Calculates estimated prices
  • Prioritizes the user’s own recipe at the top of the results
  • Generates a tailored grocery list that matches real availability

This effectively brings Instagram recipes into real life, turning saved posts into cooked meals.

4️⃣ Smart Shopping System & Real-Time Pricing 🛒💰

Gap Identification: Missing ingredients are automatically added to a smart grocery list.

Store Suggestions: Based on geolocation, the app suggests nearby stores such as Carrefour or Lidl.

Real-Time Pricing: Estimated prices are displayed in local currency (e.g., EUR), enabling informed, budget-conscious decisions.

🎨 UX/UI Design & Prototyping

Before writing a single line of code, I mapped the entire user journey in Figma, optimizing for a Zero-Friction experience — fewer than three taps from fridge scan to recipe.

The UI uses a calming Studio Ghibli-inspired aesthetic, implemented with Tailwind CSS and designed mobile-first for seamless responsiveness 📱✨

🚀 How I Built Frigo Hero (Technical Architecture & Engineering)

I engineered a robust, scalable full-stack architecture designed for performance, security, and long-term monetization, while strictly enforcing a Zero-Secret Frontend principle.

🖥️ Frontend Architecture

The frontend was built using Angular 18, leveraging Signals for reactive, high-performance state management. This allowed:

  • Instant UI updates with minimal overhead
  • Cleaner logic compared to traditional RxJS-heavy patterns
  • Smooth handling of data-intensive flows such as image analysis and nutrition computation

To deliver a true native experience:

  • Ionic was used for cross-platform UI components
  • Capacitor wrapped the app into native iOS and Android applications with access to device features such as the camera and local storage

📱 Mobile Deployment

The mobile builds were fully prepared and tested using:

  • Xcode for iOS deployment
  • Android Studio for Android deployment

This included:

  • App signing and certificate management
  • Platform-specific performance optimizations
  • Readiness for release on the Apple App Store and Google Play Store

🛡️ Backend

A Spring Boot (Java 17) backend acts as a secure middleware layer between the client and all AI services.

This backend proxy:

  • Hides all API keys and system prompts
  • Centralizes AI request validation and orchestration
  • Enforces strict JSON response structures to avoid frontend parsing errors
  • Prevents sensitive logic from ever being exposed in client code

This architecture guarantees: ✅ Security even if the app is reverse-engineered 🔐

🧠 AI Engine

I integrated Gemini 3 to handle multimodal intelligence:

  • Fridge and pantry photo analysis
  • Custom recipe ingredient extraction
  • Allergy, diet, and biometric constraint reasoning

For visual engagement, I used Imagen 4.0 to generate recipe illustrations in a calming Studio Ghibli–inspired style, enhancing emotional connection and UX 🎨

🔥 Database & Authentication

Firebase serves as the real-time backbone of the system:

  • Firestore for live data synchronization (recipes, preferences, allergies, nutrition data)

  • Firebase Authentication with secure login via:

    • Google
    • Facebook

💳 Monetization & Subscription Architecture

To support a sustainable business model, I integrated RevenueCat to manage monetization across platforms.

Technologies Used

  • RevenueCat SDK integrated into the mobile application

  • RevenueCat Firebase Extension to automatically sync:

    • User subscription status
    • Entitlements
    • Feature access flags

This setup enables:

  • In-app purchases and recurring subscriptions
  • Real-time subscription state updates across devices
  • Centralized pricing, experiments, and paywall management without app updates
  • Clean separation between payment logic and AI logic

Premium features can be gated dynamically, such as:

  • Unlimited fridge scans
  • Advanced nutrition insights
  • Custom recipe uploads
  • Unlimited Ghibli-style image generation 💳✨

Note for Judges regarding RevenueCat Integration:

"The provided APK is a Signed Release build fully integrated with RevenueCat using production Google Play Store keys.

To verify that subscriptions are actually purchasable and bypass the 'test store' configuration, your Google account must be whitelisted in the 'License Testers' section of my Google Play Console.

Please provide your testing email address so I can add you to the list immediately. This will allow you to trigger the official Google Play Billing (Sandbox) flow and confirm the SDK is correctly configured for production."

🧪 Quality Assurance & Testing

  • Frontend: Karma + Jasmine
  • Backend: Mockito + JUnit 5

Ensuring reliability, security, and structured AI responses.

⚠️ Challenges I Ran Into

  • Context complexity when scaling macros with allergies
  • Enforcing strictly structured JSON from LLMs
  • Multilingual consistency across Arabic, French, and English 🌍

🏆 Accomplishments I’m Proud Of

  • Production-ready AI architecture
  • Seamless fusion of nutrition science and emotional UX
  • Turning fridge chaos into instant, personalized clarity ✨

📚 What I Learned

  • Advanced multimodal prompt engineering
  • Angular Signals mastery
  • Designing AI systems that feel human, not robotic

🔮 What’s Next for Frigo Hero

🚀 My journey doesn’t end with the hackathon.

  • 💳 Premium Subscription Launch
  • 🔗 Direct Recipe Upload (Instagram / TikTok / YouTube)
  • 📲 Global App Store Release on Apple App Store & Google Play

Note: Although not featured in the video, we utilized this recipe by Eitan Bernath as a primary use-case example for our AI analysis: https://www.instagram.com/eitan/reel/DUbngbpj4ju/

Frigo Hero isn’t just about recipes — it’s about finally cooking what you already love, with what you already have.

Built With

  • android-studio
  • angular-18
  • angular-signals
  • capacitor
  • ci/cd-pipelines
  • cloud-based
  • computer-vision
  • css
  • facebook-authentication
  • figma
  • firebase
  • firebase-authentication
  • firestore
  • gemini-3-api
  • geolocation-apis
  • git
  • github
  • google-authentication
  • gradle
  • html
  • imagen-4.0-api
  • ionic
  • jasmine
  • java
  • javascript
  • json-schema-enforcement
  • junit-5
  • karma
  • large-language-models-(llms)
  • maven
  • mobile-first-design
  • mockito
  • multimodal-ai
  • price-comparison-apis
  • prompt-engineering
  • responsive-design
  • rest-apis
  • revenuecat-extension
  • revenuecat-sdk
  • spring-boot
  • tailwind-css
  • typescript
  • xcode
Share this project:

Updates