DEV Community: Honey B33

The Lazy Fridge-to-Grocery Helper: Automating My Kitchen Inventory with Open-Source AI 🥬

Honey B33 — Tue, 20 Oct 2026 16:15:52 +0000

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

What I Built

For Week 3 of the Hacktoberfest Open-Source AI Challenge, I built The Lazy Fridge-to-Grocery Helper 🥬.

This app completely eliminates the mental fatigue and daily dread of standing in front of an open fridge trying to figure out what ingredients we are running out of. Instead of manual inventory tracking, you simply snap a photo of your fridge contents, upload it, and let AI analyze what's missing to automatically generate a clean, categorized shopping list. It lets me (and anyone else in the house) be a whole lot lazier and efficient with meal planning!

Demo

Live app [ Https://fridge-grocery-helper.onrender.com]

Code

https://github.com/yasmeenvrk23-beep/fridge-grocery-helper

How I Built It

To bring this project to life entirely from a mobile device, I used a lightweight stack:

Frontend and UI: Built using Python and Streamlit to provide a seamless, interactive mobile web interface.

Deployment: Hosted and deployed live on Render via a connected GitHub repository.

AI Approach: Designed around open-source concepts and open-weight model architectures, such as Google's Gemma ecosystem, to handle visual image parsing and text categorization efficiently.

Why Does Open Innovation Matter?

Open innovation is critical for tools dealing with personal, everyday environments like home kitchens and fridge contents. Using open-weight models means my personal home photos and private inventory data do not have to be locked into or exposed on proprietary servers that I don't control. It provides the freedom to run models, adapt workflows, and customize logic locally or via flexible cloud runtimes without hitting rigid restrictions or high per-request closed API fees.

The Lazy Payoff

Before building this, checking what groceries we needed meant opening the fridge doors multiple times, forgetting items, and scribbling messy notes. Now, a single photo upload does all the thinking in seconds. This week, it saved me multiple trips to the grocery store and completely streamlined my weekly meal prep with zero effort!

Prize Categories

Best Use of Render
Best Use of Gemma

SnapInvoice: My AI-Powered Receipt Sorter for Freelancers

Honey B33 — Fri, 16 Oct 2026 02:15:54 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

I built SnapInvoice, a lightweight, mobile-first web app designed for freelancers, independent contractors, and small business owners.
Every tax season, freelancers waste hours manually sorting through stacks of paper receipts, fuel bills, and vendor invoices to log them into spreadsheets. SnapInvoice solves this by allowing users to instantly snap a photo of any receipt using their mobile phone camera, parsing out the merchant name, date, amount, and tax category automatically. Freelancers and micro-entrepreneurs who hate tedious bookkeeping would gladly pay a small subscription fee to save hours of manual data entry every month.

Demo

https://github.com/yasmeenvrk23-beep

Code

https://yasmeenvrk23-beep.github.io/snap-invoice/

How I Built It

To make this project fully functional and lightweight enough to build, test, and run directly from a mobile device, I structured it using:

Frontend: Built with responsive HTML5, Tailwind CSS for a sleek mobile UI, and native browser file inputs with capture="environment" to trigger the phone camera directly.

Open-Source AI Approach: Designed with a local-first architecture pattern to support local open-weight model inference and client-side processing, ensuring that document parsing hooks directly into open tooling rather than relying on heavy proprietary vendor locks.

Why Does Open Innovation Matter?

Open innovation is the absolute core of why SnapInvoice works. Financial receipts and invoices contain highly sensitive data—credit card snippets, personal client names, exact spending habits, and private business transactions.
If this app relied on a standard closed-source enterprise API, a user's raw financial data would have to be uploaded and stored on a third-party corporate server outside of their control. By utilizing an open, local-first approach, the user's private data stays strictly secure and compliant with privacy expectations, while keeping hosting and inference costs down to absolute zero so the side hustle remains profitable

My First User

I tested SnapInvoice live on my phone with a local freelance graphic designer friend who constantly complains about managing monthly tax receipts.
They used their phone camera to snap a photo of an actual equipment receipt right on the spot. After seeing it instantly extract the vendor, date, and amount without having to type anything manually, they said they would happily pay $5/month for a production-ready version. Their biggest piece of feedback for the next iteration was adding an export button to download all sorted records directly as a CSV file!

Prize Categories

Best Use of a .tech Domain

TrailLens - Post-Adventure Outdoor Logbook

Honey B33 — Sat, 10 Oct 2026 06:20:27 +0000

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

What I Built

Traillens is a lightweight, responsive digital outdoor logbook and post-adventure journal built for the Hacktoberfest 2026 "Touch Grass" challenge. Instead of keeping users glued to their screens, Traillens is designed to be used after your trip—when you return from a hike, park walk, or nature exploration, and want a clean, minimalist space to log your location, memories, and trail experiences.

Demo

https://traillnes-app.netlify.app/

Code

https://github.com/yasmeenvrk23-beep/traillens#traillens

How I Built It

I built TrailLens as a lightweight, lightning-fast single-file web application (index.html) centered around the Hacktoberfest 2026 "Touch Grass" theme.

Frontend Interface: Designed a responsive, clean dashboard using custom modern CSS with dark mode aesthetics.

State Management & Persistence: Integrated vanilla JavaScript with the browser's localStorage API so users can save, track, and retain their post-adventure trail logs permanently across sessions.

Deployment: Pushed the code directly to GitHub (yasmeenvrk23-beep/traillens) and deployed it live instantly via Netlify (https://traillnes-app.netlify.app

Why Does Open Innovation Matter?

Open innovation and open-source web paradigms make it possible to build decentralized, lightweight utility tools that run entirely on the client side without needing heavy server infrastructure or paid cloud APIs. For an outdoor logging app like Traillens, using open standards ensures complete user privacy—all adventure notes and check-ins stay locally secure on the user's browser, cost nothing to run, and load instantaneously even with low connectivity on the go

My Agent Session

Live Project Demo: https://traillnes-app.netlify.app
GitHub Repository: https://github.com/yasmeenvrk23-beep/traillens#traillens

Prize Categories

GitHub

SafeBite AI: An Offline Ingredient Safety Companion Built for Ananya

Honey B33 — Sun, 04 Oct 2026 13:38:31 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend*

What I Built

I built SafeBite AI for my close friend and roommate, Ananya.
Ananya lives with severe peanut allergies and acute lactose intolerance, and she follows a strict Pure Vegetarian (Eggless) diet. Shopping for packaged snacks in local Indian grocery stores is a daily gamble for her. Ingredient lists are printed in microscopic font on shiny plastic packaging, hiding severe allergens behind complex terms (milk solids, peanut derivatives) or vague additive numbers (INS 322, E120).
She routinely spends minutes staring at labels under her phone light, terrified of an accidental allergic reaction or consuming non-veg additives. Commercial scanner apps require constant internet access (which fails inside grocery basements), charge subscriptions, and sell health data.
SafeBite AI is a lightweight, local AI assistant that scans ingredient lists and instantly gives an unambiguous SAFE, WARNING, or UNSAFE verdict tailored specifically to Ananya's profile.

Demo

==================================================

SafeBite AI - Scanning Label for Ananya

Input: Refined Wheat Flour (Maida), Sugar, Palm Oil, Peanut Oil, Milk Solids, INS 322.

VERDICT: 🛑 UNSAFE FOR ANANYA

ANALYSIS & REASONS:

Peanut Oil Detected — High risk for severe peanut allergy.
Milk Solids Detected — Triggers lactose intolerance.
INS 322 (Soy Lecithin) — Safe, but product remains marked UNSAFE due to allergen triggers.

RECOMMENDATION: Do not consume. Pick a dairy-free, nut-free alternative.

Code

https://github.com/yasmeenvrk23-beep/Safebite/blob/main/README.md

How I Built It

•Open-Weight AI Engine: Powered by Google's Gemma 2 open-weight model running locally via the Ollama framework.

•Language & Environment: Built with Python 3.10 and executed entirely locally.

•Custom System Prompting: Configured with a dedicated rule-engine prompt that parses messy, comma-separated food packaging text against severe allergy and dietary constraint flags.

Why Does Open ``Innovation Matter?

Using open-weight AI models and open-source tooling was non-negotiable for this project:

•Supermarket Basement Reliability: Grocery store basements in India frequently suffer from zero cellular signal. Running an open-weight model locally (Gemma) means Ananya can check safety offline with zero network latency or connectivity drops.

•Absolute Health Privacy: Ananya's medical conditions, allergy severity, and personal dietary restrictions stay entirely on her local device rather than being logged on remote servers.

•Zero Maintenance Costs: As students, using open weights locally removes expensive cloud API token fees, enabling a completely free tool for daily life.

My Agent Session

Built using direct terminal/Google Colab local execution sessions with Gemma 2

Prize Categories

•Best Use of Gemma ($200): Uses Google's Gemma open-weight model to perform fast, private, and offline label scanning.

•Best Use of GitHub ($100): Built, version-controlled, and publicly documented open-source on GitHub.

New to the community

Honey B33 — Fri, 02 Oct 2026 14:54:31 +0000

Hii I'm new bee!!!