What's in My Kitchen? – An AI Cooking Friend Powered by Google Gemma

Udhayavani — Sun, 01 Nov 2026 04:12:23 +0000

*What's in My Kitchen? – An AI Cooking Friend Powered by Google Gemma

This is my submission for the DEV Community Hacktoberfest Challenge – Build for a Friend.

What I Built

I created the concept of "What's in My Kitchen?", an AI-powered cooking assistant designed to help friends and family decide what to cook using ingredients already available at home.

Sometimes we open our refrigerator or kitchen cupboard and find several ingredients, but we don't know what to prepare with them. Instead of buying more groceries or wasting leftover food, this application helps users discover new recipes using what they already have.

The application uses Google's Gemma AI model to understand available ingredients and generate personalized recipe suggestions.

Main features:

Enter available kitchen ingredients.
Generate recipes using AI.
Get step-by-step cooking instructions.
Discover recipes using leftover ingredients.
Find alternative ingredients when something is missing.
Select vegetarian and non-vegetarian preferences.
Get quick and budget-friendly meal suggestions.
Ask cooking-related questions through an AI assistant.
Save favourite recipes.

The main innovation is using Gemma AI to understand ingredient combinations and generate useful cooking recommendations instead of simply displaying predefined recipes.

Demo

Live Demo: [ADD YOUR DEPLOYED WEBSITE LINK]

Demo Video: [ADD YOUR VIDEO LINK]

The demo will show how users enter available ingredients and receive AI-generated recipes with cooking instructions.

Code

GitHub Repository: [ADD YOUR PUBLIC GITHUB REPOSITORY LINK]

The repository will include the frontend, Python backend, Gemma AI integration, recipe generation system and installation instructions.

How I Built It

I developed this project using open-source technologies.

Technology Stack:

Frontend: HTML, CSS and JavaScript.
Backend: Python and Flask.
AI Model: Google Gemma.
AI Framework: Hugging Face Transformers.
Database: SQLite.
Interface: Responsive web design.

How Gemma AI works:

The user enters the ingredients available in their kitchen.
The backend sends the ingredients and preferences to the Gemma model.
Gemma analyses the ingredients and understands the user's requirements.
The model generates suitable recipe suggestions.
The application displays recipe names, ingredients, preparation time and cooking instructions.
Users can ask additional questions to the AI cooking assistant.

The application uses an open-weight AI model rather than depending on paid commercial AI APIs.

Why Does Open Innovation Matter?

Open innovation makes AI development accessible to students, independent developers and communities.

By using Google's Gemma model, developers can experiment with open-weight AI, customize applications and build useful solutions for everyday problems.

For this project, open innovation makes it possible to:

Build an AI-powered cooking assistant.
Experiment with open-weight language models.
Customize recipe generation.
Develop without depending entirely on expensive commercial APIs.
Encourage developers to contribute improvements.
Share useful technology with the community.

I believe open innovation helps transform simple everyday ideas into practical AI-powered solutions.

My Agent Session

[ADD YOUR DEVRELAY AGENT SESSION LINK IF AVAILABLE]

The Spirit of It

I wanted to create something simple but useful for someone close to me.

Many people face the same everyday question: "What should I cook today?"

Sometimes we have ingredients at home but lack ideas. Sometimes leftover food gets wasted because we don't know how to use it in another meal.

I wanted to build a small digital cooking friend that makes this process easier.

Instead of asking someone to buy more ingredients, this application helps them discover what they can create with what they already have.

My idea is simple:

Less Food Waste. More Creative Cooking. Smarter Everyday Living.

Prize Categories

[ADD ELIGIBLE PARTNER CATEGORIES IF APPLICABLE]

devchallenge #hf26challengeThis is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend*

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

ScamShield AI powered by Gemma

Udhayavani — Sun, 01 Nov 2026 02:42:58 +0000

*Build a complete Hacktoberfest Open-Source AI project named ScamShield AI.

IMPORTANT: Google Gemma must be the actual core AI model used in this application.

Model: google/gemma-4-E2B-it.

Project concept:
An Indian e-commerce shopping platform inspired by Meesho, with an integrated AI scam detection system.

Build the following:

Create an attractive shopping website with product categories, product cards, product descriptions, seller profiles and customer reviews.
Integrate the actual Gemma model using Hugging Face Transformers or a supported inference provider.
Create an AI scam analyser where users can submit:

Product descriptions.
Seller information.
WhatsApp messages.
SMS messages.
Suspicious payment requests.
Shopping offers.

Make Gemma analyse the submitted content and identify suspicious patterns.
Generate structured results:

Risk score from 0 to 100.
Low, Medium or High risk.
Suspicious indicators.
Detailed AI explanation.
Safety recommendations.

Add a scam detection dashboard with scan history and charts.
Use Python and Flask for the backend, HTML, CSS and JavaScript for the frontend, and SQLite for storage.
Do not use paid OpenAI APIs.
Do not generate fake AI responses or use only predefined if-else conditions. The actual Gemma model must process user input.
Combine Gemma's semantic analysis with transparent fraud detection rules. Clearly distinguish model-generated assessment from rule-based signals.
Create a Gradio-based demo version suitable for Hugging Face Spaces.
Provide the complete GitHub project structure, source code, requirements.txt, README.md and installation instructions.
Include sample genuine and suspicious messages for testing.
Ensure all features work and provide instructions for deployment.
Prepare the final Hacktoberfest submission using the official Week 4 template.

Build step by step. Do not claim that the model or demo is working until it has been successfully tested.This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine*

DEV Community: Udhayavani

What's in My Kitchen? – An AI Cooking Friend Powered by Google Gemma

devchallenge #hf26challengeThis is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend*

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

ScamShield AI powered by Gemma

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Spirit of It

Prize Categories