Listing Writer: a private AI that writes product listings for small sellers
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built Listing Writer is a small web app that turns a few product facts into a ready-to-post online listing. You type the product name, a few key details (materials, size, colour, what makes it special), t

Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission 💸
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle
Listing Writer is a small web app that turns a few product facts into a ready-to-post online listing.
You type the product name, a few key details (materials, size, colour, what makes it special), the price, where you'll post it (Etsy, eBay, Instagram or WhatsApp Business), and the tone you want. It returns a title, a description of about 100 words, six tags, and a short caption with the price.
Who would pay for it? Small sellers: home bakers, craft makers, boutique owners and anyone selling on Instagram or WhatsApp. They know their products well but spend a lot of time writing descriptions, and many are not confident writing in English. A tool that does this in seconds saves them time and makes their listings look more professional.
The app is told to use only the facts you give it. It must not invent materials, sizes or discounts, so the seller never ends up promising something that isn't true.
Watch the demo here: https://drive.google.com/file/d/1oc-JS8zHFYSKIUqPVGMfTGDnTDO86xX1/view?usp=sharing
# Listing Writer A tiny local web app that turns a few product facts into a polished online listing (title, description, tags and a short caption) for small sellers. Powered by the open-weight Gemma model running locally through Ollama. No cloud, no API key, no per-listing cost, and product details never leave the seller's computer. ## Run it 1. Install Ollama: https://ollama.com 2. `ollama pull gemma3:4b` (or `gemma3:1b` for a smaller PC) 3. `python app.py` 4. Open http://localhost:8002 Use a different model (PowerShell): `$env:MODEL="gemma3:1b"; python app.py` View on GitHub How I Built It I'm just starting out, so I kept it small on purpose.
The prompt does the main work. It gives the model the product facts and the platform, then asks for a fixed format: a title under 80 characters, a description of 80 to 120 words, six tags and a short caption. It also tells the model never to add facts that weren't provided.
A side business only works if the tool costs almost nothing to run. Because Gemma runs locally through Ollama, there is no per-listing fee and no subscription. A seller can write as many listings as they like without watching an API bill.
It is also private. A seller's new products, prices and supplier details stay on their own computer instead of going to someone else's server, which matters when a launch is meant to be a surprise.
It works without an internet connection once the model is downloaded, and I can swap in a smaller or bigger model by changing one setting, which let me match the model to my laptop. With a closed API I would be paying per request and depending on someone else's pricing.
One honest limit: a small local model can make mistakes or write something that doesn't sound quite right, so a seller should always read the listing before posting it.
Best Use of Gemma: Gemma 3 runs locally through Ollama and is the entire AI core of Listing Writer. It writes every listing on my own computer.