SellCraft AI: a listing writer that runs on the seller's laptop, not my server

Description and use

SellCraft AI cuts listing creation time for crafters to about a minute, runs entirely locally, and avoids subscription costs.

Problem

Handmade sellers spend an evening photographing items and another evening writing listings, delaying sales and increasing workload.

Outcome

SellCraft reduces listing creation time from an evening to about a minute per item, eliminates subscription costs, and keeps all data on the seller’s machine.

Workflow

• 1. Pull Gemma4 model via Ollama (one‑time).
• 2. Run sellcraft.py to launch local web UI.
• 3. Upload up to four product photos and enter seller facts (materials, size, price).
• 4. Select platform (Etsy or eBay) and tone.
• 5. Receive generated title, description, and tags in the browser.
• 6. Review and copy or export listings; optionally revise by providing new instructions.

Evidence

SellCraft turns each listing into about a minute of work — and it doesn't sound like a template, because it writes from the photos and the seller's own words instead of from a blank prompt box.

Source

The app talks to Ollama on 127.0.0.1:11434 and runs Gemma's vision model.

Source

The repo ships three sample photos (a mug, soap bars, earrings), so you can go from clone to a finished listing in about a minute without hunting for product photos.

Source