DEV Community: Ishpreet

4

Ishpreet — Thu, 29 Oct 2026 12:49:15 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Spirit of It

Prize Categories

hzisoalskd
Bsjwosnchfiep
Nahdielwla
Ndjeism

3

Ishpreet — Tue, 20 Oct 2026 07:45:50 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

Build something with open-source AI at its core.

That can mean running an open-weight model, building on an open-source agent harness or framework, running inference locally, or all three. Whatever you pick, the open pieces should be what makes your project work.

In your post, tell us why open innovation matters for what you built. Does it run on a laptop with no internet? Keep someone's data off a server they don't control? Let you fine-tune, swap models, or change how your agent behaves? Cost nothing to run? Tell us where your open-based approach worked better than a closed one.

This Week's Theme: Slow and Steady
Build something with open-weight models or open-source AI that rewards laziness.

Tomorrow, October 20, is International Sloth Day, and we think sloths have it figured out. They move at their own pace, conserve their energy, and even help moderate our website. This week, we want you to channel your inner sloth and build something that does the work so you don't have to.

Your build could help someone relax, automate a task they dread, or just make life a little easier. A few ideas to get you going:

A local agent that reads your group chats overnight and hands you a two-line summary in the morning

A wind-down companion that generates a calming bedtime story or ambient soundscape, running entirely offline

A fridge photo to grocery list tool, so you never have to stand there with the door open again

A file and inbox tidier that automatically sorts, renames, and archives the clutter you keep putting off

Week 2

Ishpreet — Fri, 16 Oct 2026 12:49:15 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

My First User

Prize Categories

Side Hustle
Build something with open-source AI at its core.

This Week's Theme: Side Hustle
Build something with open-weight models or open-source AI that someone would actually pay for.

Think small, specific, and useful. The best builds here solve a real problem for a real person, whether that's a freelancer, a small business owner, a niche hobby community, or your friend who keeps complaining about the same tedious task. A few ideas to get you going:

An invoice and receipt sorter for freelancers that runs locally, so client data never leaves their laptop
A listing writer for Etsy or eBay sellers that turns a few product photos into a polished description
A menu translator for a local restaurant that handles their specific dishes better than a generic tool
In your post, tell us why open innovation matters for what you built. Does running your own model keep costs low enough that the business actually works? Keep your customers' data private? Let you fine-tune for a niche that a general-purpose API handles poorly? Avoid getting locked into someone else's pricing? Tell us where your open-based approach worked better than a closed one.

Bonus points if you land your first user. Get it in front of someone, let them use it, and tell us how it went. Did they pay? Would they? What did they ask for next?

Since you're a complete beginner using only your Android phone, I recommend building a small AI tool for local shopkeepers rather than something complicated. You can make a working prototype first, then show it to a real shop owner for the Side Hustle challenge.

My recommended project: DukaanAI 🛍️
Meesho's AI system PRISM now influences over three-quarters of all orders, signalling a shift in Indian e-commerce discovery | Noah Intelligence

Add to Favorites
noah-news
An AI assistant that helps small businesses create product advertisements in seconds.

Imagine a clothing shop owner uploads a photo of a kurti. DukaanAI helps create a product description, a WhatsApp promotional message, and an Instagram caption.

What will your project do? Aramya | Premium Cotton Kurtas & Ethnic Wear for Women

Step 1 — Add a product

The shopkeeper enters the product name, price, and a few details.

ListingLens - Product listing drafts from photos

Step 2 — Generate content with AI

The tool creates a product listing, an advertisement, and a short customer message.

Best Instagram Automation Tools India 2026: Small Business | QuickDM

Step 3 — Copy and use

The owner copies the content and posts it on WhatsApp or Instagram.

How does it meet the open-source AI challenge? Requirement

Your approach

Open-source AI at the core

Use an open-weight language model through an open-source inference tool such as Ollama, or a hosted open-model service for the prototype.

Real problem

Small businesses need promotional content regularly.

Potential customers

Clothing shops, gift shops, home bakers and resellers.

Revenue idea

Offer a free trial, then test a small monthly subscription.

Open innovation

You can change models, customize prompts, and potentially run the model locally for greater privacy and control.

Important: If you use a hosted model, it is not automatically private or free. For the final project, document the actual model, its license, hosting costs, and what happens to customer data.

How you can build it using only your phone Create the basic website. Build a simple form with product name, price, description, and a Generate button.

Connect an open-weight model. Send the product details to the model and receive the generated marketing text.

Add useful features. Include Hindi and English output, different tones, and a Copy button.

Test it with a real shopkeeper. Ask them to generate three advertisements and give you feedback.

Document the results. Explain what worked, what you changed, and whether the shopkeeper would pay for it.

You can start with a mobile browser and a cloud coding environment; running a large model directly on your phone is not necessary for the first prototype.

How could you earn money? These are starting prices to test with potential customers, not established market rates.

Free trial

10 product descriptions

₹0
Starter

For a small shop

₹99/month
Business

More generations and languages

₹199/month
Before charging anyone, check your actual model-hosting and operating costs. Your first challenge goal should be getting one person to test it, not building a complicated payment

Grasss

Ishpreet — Sun, 11 Oct 2026 05:55:39 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

building something that is genuinely useful outdoors but simple enough

The key is that this isn't just a normal website with an AI chatbot. An open-weight model or open-source AI component should actually power the project, and the screen should help people get outside faster.

My project recommendation: TouchGrass AI 🌿
Smartphones and artificial intelligence help detect ecological change

Add to Favorites
Audubon’s Climate Watch, Now a Decade Old, Has Tracked Shifts in Bird Ranges as Temperatures Rise | Audubon

Mutual Aid Networks: How Communities Build Their Own Safety | Science Array

Build a personal outdoor adventure generator that turns someone's free time into a real-world activity.

For example, someone opens the app, selects that they have 30 minutes, and gets a mini nature adventure near home. They might have to find three different leaf shapes, observe a bird, or identify five things in nature that they have never noticed before.

The app generates the activity using an open-weight language model, then gives the user a checklist and encourages them to put their phone away.

What the finished project will do Wallpaper Green Leaf in Macro Photography, Background - Download Free Image

Step 1 — Choose your adventure

Select your available time: 10, 30, or 60 minutes.

Natural Resources Management Plan — Forest Park Forever

Step 2 — Get an AI-generated mission

An open-weight model creates an outdoor activity suited to your time and interests.

Aplik�cia na ur�ovanie rastl�n -

2017 - FLORA.sk ( KVETY - Z�HRADA - CHALUPA - LIFESTYLE - ZDRAVIE )

Step 3 — Explore and record

Complete the mission, optionally take a photo, and save what you discovered.

Technology we'll use Component

Technology

Purpose

Frontend

React + Vite

Build the website

AI model

Qwen2.5 or another compatible open-weight model

Generate nature missions

Local inference

Ollama

Run the model on your computer

Storage

Browser local storage

Save completed adventures

Styling

CSS

Make the interface attractive

We'll start with AI-generated missions rather than complicated image recognition. Once the basic project works, we can add photo-based plant or nature identification.

Your first practical step If you have a computer, we'll build and test the project locally first.

Beginner setup checklist

Install Node.js (LTS version).

Install Visual Studio Code.

Install Ollama.

Open a terminal and check that Node.js works with node -v.
Official downloads:

Node.js

Visual Studio Code

Ollama

We will then create the React app, connect it to the local model, and build the mission generator one file at a time.

What makes this a strong open-source AI entry? Privacy: Your prompts can stay on your own computer instead of being sent to a hosted AI provider.

Offline potential: The model can generate missions without an internet connection after setup and model download. Maps and online services would still need connectivity.

Freedom to experiment: You can replace the model, customize its instructions, and modify the application.

Real-world impact: The app measures completed outdoor missions, not time spent chatting with AI.

One important distinction: Ollama is a local model runner, and the model you choose must have suitable open weights and licensing. We'll document the actual model and license in the project README.

Our plan is:

🌱 Build a simple website first.

🤖 Connect an open-source AI model.

🌳 Make it generate outdoor missions.

🧪 Test it and prepare your project for submission.