DishReactions is a free, offline app that records customer reactions per order and shows a live chart of which dish gets the best reviews.

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

What I Built

DishReactions — a local-first app for small restaurants that records customer reaction on every order and shows a live chart of which dish gets the best reviews.

Problem: Restaurants guess popularity from sales alone. Sales don't tell you if customers actually loved the dish or just ordered it because it was cheap.

*Solution: After each order, staff records in 10 seconds: Dish + Order # + 1-5 Stars + Emoji Reaction (😍 Loved it / 😋 Tasty / 😐 Okay / 😕 Not good / 🤢 Bad) + optional comment.

The app instantly updates a ranked bar chart, a 🏆 Winner badge, recent reactions table, and a downloadable CSV report.

*Who would pay? Small restaurants, dhabas, and cafes. They would pay Rs. 2,000-5,000/month to know in 7 days which dish to promote and which dish to fix, instead of guessing.

Demo

Live Demo: Open index.html in any browser — no install, no signup, works offline.
file:///C:/Users/AK/Documents/hecktoberfest/hustle.index.html

Code

https://github.com/eshaal-wq/rating-tracker-/tree/main
*Key logic:

• Data stored in localStorage — no server
• Average rating calculated per dish: sum(stars) / count
• Chart.js renders sorted bar chart (best → worst)
• CSV export for weekly owner report

How I Built It

Built around open-source, not closed APIs:

• Chart.js (MIT Open Source): For the live best-dish chart. Free, runs locally, no API key.
• Vanilla JS + HTML/CSS: No framework lock-in, no build step. Just open index.html.
• Browser localStorage: For local inference/storage — data never leaves the device.
• *Local-first design: Designed to later plug in a local open-weight model (Llama / Qwen via Ollama) to auto-summarize comments like "Customers love spice, hate wait time" — without sending data to a closed API.

No OpenAI, no paid API, no cloud server. The open pieces are the product.

Why Does Open Innovation Matter?

Open innovation made this business actually work:

1. Privacy: Customer feedback never leaves the restaurant's laptop. No cloud server, no tracking. A closed tool would send every customer's opinion to someone else's server.

2. Cost = Zero: A closed AI API at $0.01-0.05 per review would cost a busy restaurant $60-300/month in API fees alone. With open-source, running cost is $0, so I can charge Rs. 2,000/month and still be profitable.

3. Works Offline: Many local restaurants have bad internet. This runs on a laptop with no internet. A closed cloud-only tool would fail there.

4. Freedom to Customize: Owner can change dishes, language (Urdu/English), branding, and swap models. A closed API would lock them into someone else's pricing and rules.

Open didn't just save money — it made privacy, offline use, and a viable price possible.

My First User

Who: A small restaurant owner near Safoora, Gulistan-e-Jauhar, Karachi.

What happened: Installed it on their counter tablet. Staff recorded reactions for 1 week.

What they said: "I always thought Karahi was our best dish because it sells. Your chart showed Biryani is 4.8⭐ and Karahi is 3.1⭐. Now I know what to promote."

Did they pay? Started with 1-week free trial, asked to continue for monthly report. Next step: Convert to Rs. 2,000/month paid plan.

What they asked for next: Urdu version + QR code so customers can rate directly from their table.

Prize Categories

• Side Hustle
• Open-Source AI / Local-First