DEV Community: eshaal-wq

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

eshaal-wq — Sun, 18 Oct 2026 08:02:26 +0000

*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:

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

little tales-touch the grass

eshaal-wq — Sat, 10 Oct 2026 19:33:00 +0000

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

What I Built

'Little Tales - Touch Grass Edition' for Pre-1 Blue (5-year-olds).

Kids type a word like 'kitty, bunny, leaf, bird, rainbow' for 10 seconds. The app generates a short 5-line story in very simple English and always ends with an OUTDOOR MISSION like:

🌿 OUTDOOR MISSION: Go outside and find 3 different color leaves like Lily!

So the screen time is the shortest part - 10 seconds to generate, 10 minutes outside to actually do the mission. It's built for classrooms where kids need to move, touch grass, smell flowers, hop like bunnies.

Who is it for? Pre-1 to Grade 1 teachers and parents who want stories that get kids OFF the tablet and into the garden.

Demo

https://github.com/eshaal-wq/Little-Tales/tree/main

It works 100% offline after first load. Turn off WiFi and it still generates.

Code

https://github.com/eshaal-wq/Little-Tales/tree/main

Main file is single 'index.html' - no backend, no build. Just open in Chrome.

Fallback offline story DB included for instant use if network is slow.

How I Built It

Open-source AI at core:

Open-weight model: Llama 3.2 1B Instruct (Meta open weights) + SmolLM2-135M for fast demo - both run locally
Local inference harness: @mlc-ai/web-llm 0.2.79 - runs WebGPU inference in browser, no server
No closed API: No OpenAI key, no cloud. First visit caches ∼800MB weights, after that fully offline.

The entire app is built around local inference. Prompt is tuned for Pre-1 vocabulary (<80 words, happy, simple). If I used closed API, it wouldn't work in my school.

Why Does Open Innovation Matter?

Closed AI fails for my classroom in Karachi: no stable WiFi, no budget for API, and I cannot send 5-year-olds' data to a cloud.

Open made this possible:

Private & Offline: Kids data never leaves the laptop - critical for schools
Free & Accessible: Any teacher can open index.html on an old laptop, no payment
Swappable & Customizable: I can swap Llama for SmolLM or Phi-3 for even smaller devices, and change prompts for Urdu/English vocab without asking a vendor
Touch Grass by design: Because it runs locally, I can take the laptop to the garden itself.

Open innovation turned AI from a cloud service into a classroom tool that gets kids outside.

My Agent Session

Built with Meta AI assistance for debugging WebLLM loading and optimizing for offline fallback.

Prize Categories

Touch Grass - Getting people off screen
For Good / Education

My Doctor Appointments - Built for a Friend who never remembers appointments (Hacktoberfest)

eshaal-wq — Sun, 04 Oct 2026 12:12:45 +0000

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

What I Built

I built "My Doctor Appointments" a simple, private & offline appointment tracker.
I built it for my friend who keeps forgetting her doctor appointments. She didn't want to use complicated apps that need login, internet, or store her medical data on someone else's server.

3.Problem it solves:

No more missed appointments
Keeps doctor name, date, time, and reason/hospital notes in one place
Works completely offline - all data stays in her own browser (local Storage)
No login, no tracking, no privacy worry
Super light , just one HTML file

Demo

Live Website:https://eshaal-wq.github.io/Appointment-tracker

My Doctor Appointments App:https://eshaalwq.github.io/Appointment-tracker

You can add a doctor name, date, time, and notes/hospital name and it saves instantly. I have added Dr.Eman (dermatologist) as an example.

Code

https://github.com/eshaal-wq/Appointment-tracker

It's a single 'index.html' file - zero dependencies, zero backend. Just open and it works. Fully responsive for mobile.

How I Built It

I wanted it to be as simple as possible, so I built it with pure HTML, CSS, and Vanilla JavaScript.

Frontend: Single HTML file with modern CSS (glass morphism UI) and JS for local Storage
AI Help: I used Meta AI as my coding buddy to debug GitHub Pages deployment.
No Frameworks: No React, no database, no build step. This was intentional so my friend can even save the file on her phone and open it offline.

Why Does Open Innovation Matter?

Open innovation matters because my friend doesn't need another closed, ad-filled medical app selling her health data.

Because the code is open:

She can see exactly what it does - no hidden tracking.
Anyone can fork it and build for their own family - change it to a medicine tracker, class tracker, etc.
I didn't need to pay for a closed API or backend. Open web standards (local storage, HTML5) made it possible to build something private and free forever.
A closed API would have made this impossible offline. Open innovation lets us build for privacy-first, not profit-first.

My Agent Session

I built and deployed this with help from Meta AI, from fixing file names to making it live on GitHub Pages. Session was conversational debugging.

Prize Categories

Best Personal / For a Friend Build
Best No-Backend / Offline-First App