Project Info

Winner

Creao: Best Designed Web App

AI-Powered Food Bank Management System

This project did not submit a description on Devpost.

Foodsafe - AI-Powered Food Bank Management System

A comprehensive food bank management system that leverages AI to streamline inventory management, food recognition, and recipe generation. Built with React, TypeScript, and integrated with multiple AI services.

CalHacks 12.0 Creao.AI Best Design Winners

Created by Eric Wu, Ethan Lai, Maleeka Raddygala, and William Wang

UI and Integration by Eric
Recipe Generation & Inventory Logging Algo by Ethan
ML Image Processing by Maleeka
Barcode Scanning Database by William

Devpost: Calhacks 12.0 Hackathon Submission

🚀 Live Demo

Try Creao Now

✨ Key Features

📦 Smart Inventory Management

Real-time inventory tracking with quantity management
Advanced filtering by dietary preferences and allergens
Low stock alerts and automated notifications
Nutritional information display for each item
Image support with automatic product photos

📸 AI-Powered Food Recognition

Barcode scanning with OpenFoodFacts integration
Computer vision for automatic food detection from photos
Nutritional analysis using ImgRecModel AI
Product information lookup with detailed nutritional data
Allergen detection and dietary tag classification

🍳 Intelligent Recipe Generation

AI-generated recipes based on available inventory
Dietary restriction support (vegetarian, vegan, gluten-free, etc.)
Serving size optimization with inventory validation
Recipe bundling for efficient meal planning
Automatic ingredient deduction when recipes are used

🔧 Technical Features

Modern React architecture with TypeScript
Responsive design optimized for mobile and desktop
Real-time data synchronization with local storage
RESTful API integration with multiple AI services
Comprehensive error handling and user feedback

🏗️ Architecture

Frontend (Creao_Codebase)

React 19 with TypeScript
TanStack Router for navigation
TanStack Query for data management
Radix UI components with Tailwind CSS
Local storage with IndexedDB for offline capability

Backend APIs

Recipe Generation API - Google Gemini AI integration
OpenFoodFacts API - Product database integration

🚀 Getting Started

API Setup

Recipe Generation API

cd APIs/API_generateRecipes
pip install -r requirements.txt
# Set GOOGLE_API_KEY environment variable

OpenFoodFacts API

cd APIs/API_openFoodFacts
npm install
# Deploy to Vercel

📱 Usage Guide

Adding Items to Inventory

Camera Tab: Take photos of food items for AI recognition
Barcode Tab: Enter product barcodes for instant lookup
Review: Edit detected information before saving
Save: Items are automatically added to inventory

Managing Inventory

View Items: Browse all inventory with search and filters
Adjust Quantities: Use quick adjust buttons or set exact amounts
Nutritional Info: View detailed nutritional data for each item
Allergen Warnings: See allergen information and dietary tags

Generating Recipes

Recipes Tab: Access the recipe generation interface
Set Servings: Specify total number of servings needed
AI Generation: System generates 3 unique recipes from available inventory
Review Recipes: Check ingredients and cooking instructions
Make Recipe: Deduct ingredients from inventory when cooking

🔧 Configuration

Environment Variables

# Recipe Generation API
GOOGLE_API_KEY=your_google_api_key
API_KEY=your_optional_api_key

# Barcode Scanner API
GOOGLE_APPLICATION_CREDENTIALS=path_to_service_account.json

# OpenFoodFacts API
# No authentication required

API Endpoints

Recipe Generation: POST /api/generate_recipes
OpenFoodFacts: GET /v1/products/{barcode}

🛠️ Development

Project Structure

calhacks/
├── Creao_Codebase/          # React frontend application
│   ├── src/
│   │   ├── components/      # UI components
│   │   ├── hooks/           # Custom React hooks
│   │   ├── routes/          # Application routes
│   │   └── lib/             # Utilities and types
├── APIs/                    # Backend API services
│   ├── API_generateRecipes/ # Recipe generation service
│   └── API_openFoodFacts/   # Product lookup service

Available Scripts

# Frontend development
npm run dev          # Start development server
npm run build        # Build for production
npm run check        # Run type checking and linting
npm run test         # Run test suite

# API development
python main.py       # Start API server
python test_api.py   # Run API tests

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

OpenFoodFacts for comprehensive product database
Google Gemini AI for intelligent recipe generation
ImgRecModel for nutritional analysis
Creao platform for rapid application development

Built with ❤️ for food banks and community organizations

Analysis

Compare with all teams

View

Metric

eric
5

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only

CSSIn code
ExpressIn code
HTMLIn code
JavaScriptIn code
PythonIn code
ReactIn code
Tailwind CSSIn code
TypeScriptIn code
FlaskClaimed
Google GeminiClaimed
Node.jsClaimed
VercelClaimed

8 of 12 appear in the indexed code. 4 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

726 KB

Source files

200

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

Repository

ericrcwu001/calhacks

246 files · 1.3 MB · @ 9919a5f

Structure

Interface
58 files · 24%
Screens, components and styles rendered to the user.
API & routing
10 files · 4%
Request entry points: routes, handlers and controllers.
Application logic
46 files · 19%
Domain rules, services and shared utilities.
Data & schema
68 files · 28%
Schema definitions, migrations and data access.

Supporting

Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.

Languages

TypeScript71%
Python12%
Markdown9%
JavaScript4%
Shell3%
CSS1%
Other (1)0%

Share of indexed source by file size. Binary and vendored files are excluded.

Dependencies

Creao_Codebase/package.json

npm · 85

@fortawesome/fontawesome-svg-core
@fortawesome/free-brands-svg-icons
@fortawesome/react-fontawesome
@hookform/resolvers
@protobuf-ts/runtime
@radix-ui/react-accordion
@radix-ui/react-alert-dialog
@radix-ui/react-aspect-ratio
@radix-ui/react-avatar
@radix-ui/react-checkbox
@radix-ui/react-collapsible
@radix-ui/react-context-menu
@radix-ui/react-dialog
@radix-ui/react-dropdown-menu
@radix-ui/react-hover-card
@radix-ui/react-label
@radix-ui/react-menubar
@radix-ui/react-navigation-menu
+67 more

APIs/API_ImageRecognitionAI/requirements.txt

pypi · 5

google-genai
pandas
Pillow
requests
werkzeug

APIs/API_openFoodFacts/package.json

npm · 4

axios
cors
express
lru-cache

APIs/API_generateRecipes/requirements.txt

pypi · 1

requests

Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.

Feature verification

9 Verified2 Code-supported3 Claimed only

Advanced filtering by dietary preference and allergensVerified
Advanced filtering by dietary preferences and allergens
Claimed on readmehigh confidence
- Creao_Codebase/src/routes/index.tsx:310 — filter logic excludes items with selected allergens and matches selected dietary tags
AI camera/computer-vision food recognitionVerified
Computer vision for automatic food detection from photos using ImgRecModel AI
Claimed on readmehigh confidence
- Creao_Codebase/src/routes/index.tsx:1617 — CameraView calls vision classification then the ImgRecModel API on the captured photo
- Creao_Codebase/src/hooks/use-img-rec-model.ts:1 — hook wraps the ImgRecogModel API client and defines nutritional response types
- APIs/API_ImageRecognitionAI/api/image-recognition.py — backend image recognition service implementing food detection
AI recipe generation via GeminiVerified
AI-generated recipes based on available inventory using Google Gemini
Claimed on readmehigh confidence
- Creao_Codebase/src/hooks/use-recipe-generator.ts:1 — recipe generator hook and types for inventory-based recipe suggestions
- APIs/API_generateRecipes/api/recipe_generator.py:42 — RecipeGenerator class uses gemini-2.5-flash model and GOOGLE_API_KEY to generate recipes
Automatic ingredient deduction from recipesVerified
Automatic ingredient deduction when recipes are used / recipe bundling
Claimed on readmehigh confidence
- Creao_Codebase/src/routes/index.tsx:2718 — makeRecipe mutation deducts ingredient quantities from inventory when a recipe is cooked
Barcode scanning with OpenFoodFacts lookupVerified
Barcode scanning with OpenFoodFacts integration for instant product lookup
Claimed on readmehigh confidence
- Creao_Codebase/src/routes/index.tsx:1843 — handleBarcodeSubmit calls lookupBarcode mutation and inserts item/intake with barcode as source
- Creao_Codebase/src/hooks/use-openfoodfacts.ts:6 — useOpenFoodFactsMutation hook defines OpenFoodFactsInput/Product types used for the lookup
- APIs/API_openFoodFacts/server.js — backend Express service implementing the OpenFoodFacts product lookup API
Dietary restriction support in recipesVerified
Dietary restriction support (vegetarian, vegan, gluten-free, etc.) in recipe generation
Claimed on readmemedium confidence
- Creao_Codebase/src/hooks/use-recipe-generator.ts:30 — GenerateRecipesInput has a dietaryRestrictions field passed to the generator
Live/real-time inventory synchronizationVerified
Live inventory tracking with real-time data synchronization
Claimed on readmemedium confidence
- Creao_Codebase/src/routes/index.tsx:1783 — React Query cache invalidation on items/intakes after mutations keeps inventory views in sync
Nutritional info and allergen/dietary tag displayVerified
Nutritional information display and allergen detection / dietary tag classification
Claimed on readmehigh confidence
- Creao_Codebase/src/routes/index.tsx:292 — collects allergens and dietary_tags from inventory items and filters the list by them
- Creao_Codebase/src/routes/index.tsx:1740 — calories/protein/carbs/fat/sodium nutritional fields saved on item records
Real-time inventory tracking with quantity managementVerified
Real-time inventory tracking with quantity management
Claimed on readmehigh confidence
- Creao_Codebase/src/routes/index.tsx:350 — setAbsoluteQuantity mutation and quantity adjustment UI update item quantities live via React Query invalidation
Add weight during intakeCode-supported
Scan, auto-fill, add weight during item intake
Claimed on Devpostmedium confidence
- Creao_Codebase/src/routes/index.tsx:1420 — Quantity per Unit field with a unit selector (supports g/kg) lets the user record item weight during intake
- Creao_Codebase/src/components/data/schema/intake.json:75 — intake schema has a weight_kg field, but it is not populated by the save-item mutation in index.tsx, so the weight-recording path is only partially wired
Faster check-ins via phone-as-scanner workflowCode-supported
Any phone becomes a scanner for faster food bank check-ins
Claimed on Devpostmedium confidence
- Creao_Codebase/src/routes/index.tsx:1521 — CameraView component supports both camera vision capture and manual/scanned barcode entry as mobile-friendly intake paths, but no dedicated hardware scanner integration was found
Instant CSV export for auditsClaimed only
Live inventory + instant CSVs for audits
Claimed on Devposthigh confidence
Low stock alerts / automated notificationsClaimed only
Low stock alerts and automated notifications
Claimed on readmehigh confidence
Offline capability with local IndexedDB storageClaimed only
Local storage with IndexedDB for offline capability
Claimed on readmehigh confidence

An AI agent derived these features from the project’s Devpost page and readme, then searched the code for each one. Verified features are backed by cited code; claimed-only features had no supporting code, which is not by itself proof a feature is missing.