I built my sister a personal stylist that lives on my laptop

Description and use

ClosetCue helps the sister choose outfits, avoid repeats, and reduce decision fatigue using a local Gemma model, keeping all data on the laptop.

Problem

Choosing outfits for school mornings and for going out is hard, not repeating outfits is a big worry, and choosing what to wear is stressful, leading to decision fatigue.

Outcome

ClosetCue reduced decision fatigue, prevented outfit repeats within 14 days, and kept all data local on the user’s laptop, ensuring privacy and no external API usage.

Workflow

• Photograph all clothes
• Local AI (Gemma via Ollama) reads photos and generates captions (category, type, colour, pattern, style, season)
• User corrects any errors
• User selects preferred styles and moods
• AI proposes four outfits
• Code filters out invalid or recently worn outfits
• Code ranks remaining outfits by freshness and style preference
• App displays best outfit with option to "Wear this" or "Try another"
• Worn outfits are archived for future reference

Evidence

She photographs the clothes she already owns. A local AI model reads each photo and writes a caption: category, type, colour, pattern, style, season.

Source

The AI proposes four outfits. Then code throws out anything invalid or recently worn, ranks what's left (pieces she hasn't worn lately and her chosen styles score higher), and shows the best one.

Source

ClosetCue runs an open-weight Gemma model on my own laptop through Ollama. It costs nothing to run, needs no account or paid API, and her photos are read on the same machine that stores them.

Source