DEV Community: Mohammad Oves

PantryPulse — Your Kitchen, Organized

Mohammad Oves — Sun, 25 Oct 2026 12:55:06 +0000

🥕 PantryPulse — Your Kitchen, Organized

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

What I Built

PantryPulse is a kitchen companion that helps you cook with what you already have and throw away less food. It aims to:

📸 Scan ingredients and keep a running inventory of your fridge
⏰ Watch expiry dates and flag items that should be used first
🍳 Suggest recipes based on what’s in stock
🛒 Build grocery lists so you only buy what you need
🌱 Cut food waste with smarter day-to-day planning

The idea is to spend less time managing your kitchen and more time enjoying what comes out of it.

Demo

💻 GitHub: MohdOves/Dev-Weekeend-Challenge-3

How I Built It

PantryPulse pairs a cross-platform mobile front end with a Python backend and AI-assisted food features.

React Native + Expo for the mobile and web app
TypeScript for safer, easier-to-maintain code
FastAPI (Python) for the backend API and logic
Expo SQLite for local storage of inventory and grocery data
Docker to containerize the backend
Gemma 3 4B (planned) for on-device ingredient recognition and recipe help, not yet implemented

A key goal is privacy-friendly, offline-first AI that works across devices.

Why Does Open Innovation Matter?

Open-source tools let me inspect, adapt, and improve what I build on. For PantryPulse, that means I can try running AI locally instead of relying on closed services, and other developers can contribute features, fixes, and new ideas.

StoreAI: Snap a Photo, Get a Shop Listing (Powered by a Local Open-Weight Model)

Mohammad Oves — Sun, 18 Oct 2026 17:51:32 +0000

The itch I wanted to scratch

Walk into any neighbourhood kirana store and you’ll see the same chore: someone typing out product names, categories, descriptions and prices, one item at a time. It’s slow, boring, and easy to get wrong.

So I asked myself: what if the shopkeeper just took a photo of the product and the first draft of the listing wrote itself?

What DukaanAI does

You upload a picture of a product. The app suggests a name, a category and a short description. You check and fix anything that looks off, add your own price and stock count, and save it. That’s the whole loop.

Right now the MVP can:

Take a product photo and generate a draft listing
Let you edit every AI-suggested field before saving
Store price and quantity that you enter yourself
Search and delete items in your inventory
Export the full catalogue as a CSV file

The AI only proposes. The shopkeeper always has the final say.

Under the hood
Frontend: React + Vite
Backend: Node.js + Express, with Multer handling image uploads
AI: Gemma 3 (4B) running locally through Ollama
Storage: the browser’s localStorage, so everything stays on the device
Export: plain JavaScript to build the CSV

The backend forwards the image to the local model, which replies with structured JSON. The UI turns that JSON into an editable form.

Why I went with an open-weight model

For small businesses, every rupee of recurring cost matters. A hosted AI API charges per request and sends every photo to someone else’s server. Running Gemma locally avoids both, and it also lets me tune prompts and swap models freely.

It isn’t free of trade-offs. You need a reasonably capable machine, responses can be slower than a cloud API, and the model sometimes gets things wrong. That’s exactly why every suggestion is reviewed by a human before it is saved.

What building this taught me

Getting a model to describe an image is the easy part. The hard part is making the result fit into how a shopkeeper actually works, and making it accurate enough that they trust it instead of retyping everything.

Where this could go

My first users would be independent grocery stores and small retailers. Before anything else, I want to put the tool in front of real shopkeepers, compare manual entry against AI-assisted entry, and see how much time it really saves. A monthly subscription is one possible model, but I won’t pick a price until people tell me they’d actually pay.

Ideas for later: cloud sync, shop accounts, barcode scanning, low-stock alerts, and billing-software integration.

Check it out
GitHub: https://github.com/MohdOves/Dev-Weekeend-Challenge-2
Over to you

If you run or know a small shop: would listing products from photos save you time? What would need to be true before you’d use something like this?

Built for the Hacktoberfest Open-Source AI Challenge, Week 2: Side Hustle.

Outside Hours

Mohammad Oves — Sat, 10 Oct 2026 18:03:55 +0000

Outside Hours: Make Room for Outside

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass.

What I Built

Outside Hours is a small, screen-light idea generator for anyone who wants a nudge to step away from their screen. Ask for an idea or choose a prompt such as “I have 10 minutes” or “I want to spot birds,” and the page suggests a random outdoor activity: take a short walk, listen for birds, find a sunny spot, or explore a nearby green space.

The goal is to make the screen the shortest part of the experience. The suggestions are intentionally simple and can be done at your own pace. They are general inspiration, not location-aware recommendations or safety advice.

Demo

outsidehour.netlify.app

Code

The source is in the Outside Hours GitHub repository.

The page is built with plain HTML, CSS, and JavaScript. The JavaScript picks a random suggestion from a local list and avoids repeating the previous suggestion.

How I Built It

an agent harness, or local inference.
That makes this a UI prototype for an outdoor-inspiration idea, but it does not yet meet the challenge requirement that open-source AI be at the core of the project. I don't want to claim an AI integration that isn't there.

Why Does Open Innovation Matter?

I have integrated open-source AI into this version, so I can claim benefits such as offline model inference, data staying on-device, or the freedom to swap or fine-tune models. Those are the parts I would want to explore in a future version—for example, using a small open-weight model locally to turn a broad prompt into a fresh, practical outdoor suggestion without sending the user's question to a closed API.

For now, the prototype itself runs locally in a browser and sends no questions to a server, because it has no AI service or backend at all.

My Agent Session

Not included.

Prize Categories

No partner prize category is claimed. This prototype does not currently integrate a partner product or open-source AI tool.

Friends Gather

Mohammad Oves — Sat, 03 Oct 2026 19:22:56 +0000

Gather — Good food, shared

My submission for the Hacktoberfest Weekend Challenge: Build for a Friend.

What I Built

Gather is a responsive meal planner made for a friend sharing a kitchen with a roommate who has food allergies. It helps make planning dinner together easier and more thoughtful.

Choose the roommate’s allergies and Gather filters out recipes marked with those allergens. Generate a week of dinner ideas, swap a meal, browse the allergy-aware recipe box, and add a recipe to a chosen day. The allergy profile and weekly plan are saved in the browser, so they’re still there when you come back.

Recipes are sample suggestions, not medical advice. Always check ingredient labels and cross-contamination risks, especially when cooking for someone with an allergy.

Demo

Live demo: gather-meal-planner.onrender.com

Code

GitHub repository: MohdOves/Dev-Weekeend-Challenge-1

The app is built with vanilla HTML, CSS, and JavaScript. It has no build step or runtime service dependency.

How I Built It

I built Gather with HTML, CSS, and plain JavaScript. The interface adapts to mobile and desktop screens, and browser localStorage keeps the food profile and meal plan between visits.

I used GitHub Copilot in VS Code as an AI coding assistant while building the project. The app itself does not call an AI model or an external AI API: its recipe suggestions are selected from a small, built-in collection and filtered against each recipe’s listed allergens. I did not use an open-weight model in the app.

Deploy

I Deploy these app on render and the app is live on render

Why Does Open Innovation Matter?

Food preferences and allergies are personal. Keeping the recipe list, allergen labels, and filtering logic visible in the code makes it easier for someone to review, adapt, and improve them for their own household. Because the app runs in the browser without a closed recipe or AI API, it can be tried and extended without an account, API key, or service subscription.

That simplicity also comes with a limitation: this is a small demo, not a verified medical or nutrition database. Open code makes it possible for others to inspect and contribute improvements, but recipe labels still need careful review before anyone relies on them.

Prize Categories

Render->Use Render as your project's AI runtime, to host an agent's front end.
Github ->Build with Copilot's coding agent, the Copilot CLI, or the new Copilot app, automate my project with GitHub Actions, or review contributors' PRs with Copilot.

hii

Mohammad Oves — Fri, 02 Oct 2026 12:00:13 +0000

hello everyone