WearScout: open-source browser agent finds lookalike clothing from a single photo
HowDevelop · x · 2026-09-26
WearScout is an open-source project that turns a clothing photo into cross-shop product search: upload a photo, review the generated description, then watch a real Chrome browser hunt for similar items across multiple stores.
Key pieces:
- Image understanding handled by Nebius vision models
- TypeSafe Jev (Browser Use's Jev Ultrafast) picks browser actions and judges product relevance
- Titles, images, prices and links come straight from observed shop pages, with product-page verification
It's adapted from Nancy Chauhan's multi-site rental-search demo "Hearth", with a photo-led UI following Hallmark and Impeccable design guidance.
Related event: WearScout: Open-Source Agent Finds Outfits Across Shops From One Photo(2 posts)→
More from coding & agent
- He replaced a $5,000/month ghostwriter with 11 Claude Skills and earned $47,000 from one post — aryanXmahajan · 2026-11-11
- Refero Styles ships 2,000+ DESIGN.md files to give Claude Code real design taste — bbssppllvv · 2026-11-11
- Agent circuit breaker: openclaw shorts bot halts itself after 3 failed experiments — Rich_Standard_1724 · 2026-11-11
- The next AI vendor lock-in won't be the model API, it'll be the harness — Arindam_1729 · 2026-11-11
- Stop burning tokens: a Claude Code orchestrator prompt that routes tasks to cheaper models — TawohAwa · 2026-11-11
- Amazon paper: multi-agent setups burn 1.4-4.7x tokens for small gains; single agent is the default — rohanpaul_ai · 2026-11-11