WearScout: AI agent drives a real browser to find lookalike outfits across stores
HowDevelop · x · 2026-09-26
Developer menhguin built WearScout: give it a reference outfit photo, and it uses DeepSeek v4.1 Flash (via Nebius) to describe the look, then an agent drives a real browser with browseruse to search similar pieces across stores, vet product pages, and return a shortlist with prices and links. The author demoed it on a Tom Cruise outfit.
It's adapted from @nancychauhan's Hearth project, where one prompt had the agent crawl 4 rental sites in 1m16s — 32 pages, 76 browser actions, 60 clicks, 112 model calls, 21 listings — for $0.0454. The author also notes he took down his first demo over a privacy misjudgment and swapped the example.
Related event: WearScout: Open-Source Agent Finds Outfits Across Shops From One Photo(2 posts)→
More from coding & agent
- OpenRouter open-sources Jev Router, a cache-aware router that picks the best model per request — markjeffrey · 2026-09-26
- 4B model mines an iron pickaxe in Minecraft in 23 decisions, generating zero tokens — Top-Evidence174 · 2026-09-26
- Open-source Jev router cuts LLM token costs ~9x by routing Claude Code and Codex traffic — airesearch12 · 2026-09-26
- Mica v0.1 4B: Open Decision Model Runs on 8GB GPU, Trained for Under $30 — Top-Evidence174 · 2026-09-26
- Solo builder wins $500,000 Gemini XPRIZE beating 26,000 entrants with agent-built Polyfork — Scobleizer · 2026-09-26
- NetHack run used a self-built harness with moves logged on a remote server — gleech · 2026-09-26