Threadwise: A Local-First AI Closet That Makes Getting Dressed Easier

Description and use

Threadwise is a local-first wardrobe app that lets users photograph garments, remove backgrounds in-browser, store data in IndexedDB, and optionally receive outfit suggestions from a locally running Ollama model.

Problem

I wanted one simple place to remember what is in my wardrobe and make it easier to reuse those pieces.

Outcome

Threadwise reduces repetitive dressing decisions by providing a local, privacy-preserving wardrobe management and outfit planning tool, with optional AI styling that does not require external data transmission.

Workflow

• Add a clothing photo from camera or library
• Remove background in-browser with @imgly/background-removal
• Save garment to local IndexedDB wardrobe
• Filter wardrobe by category
• Select pieces to create a look manually or request AI suggestions via local Ollama Qwen3 model
• Create a trip packing list, enter destination, and mark selected pieces as packed

Evidence

Threadwise uses an open-weight model through local Ollama inference; your photos stay in the browser.

Source

Background removal runs in the browser, before the transparent image is saved to IndexedDB.

Source

The photo-processing model assets are fetched by the browser when needed, but garment photos and wardrobe records are stored in that browser's IndexedDB.

Source