Dev uses Claude Opus to build and open-source Orchard, a fully local semantic photo search app
chaseleantj · x · 2026-10-19
Developer chaseleantj open-sourced Orchard, a photo search app he had Claude Opus build for him after getting fed up with 10k+ photos scattered across directories.
Key features, all running fully locally:
- Semantic, multilingual search — find any photo by describing it
- Drag & drop to find similar photos
- Choose any/all folders
- Map view to visualize where photos were taken
The project (orchard-photos on GitHub, MIT licensed) positions itself as a local Google Photos alternative. It's also a striking vibe-coding case study: a one-line pain point handed to a model came back as a working product.
Related event: Dev Builds Open-Source Local Photo Search App Orchard with Claude Opus(4 posts)→
More from coding & agent
- PE portfolio lessons: faster AI coding doesn't automatically mean higher EBITDA — alex_verem · 2026-10-20
- Keyfleet Launches: AI Agents Get Shared Chat, Workspaces and an Onchain Treasury — seanwbren · 2026-10-20
- HBR: How to Turn Vibe-Coded Prototypes Into Tools Your Company Can Actually Use — rseroter · 2026-10-20
- AI Agents Reinvent Minecraft Piston Doors From Scratch, One Block Off World Record — Vjeux · 2026-10-20
- Wabi 2.0 launches: a multiplayer personal agent built around shared threads — Scobleizer · 2026-10-20
- ego lite brings agent-ready Chromium browser with shared logins to Windows — alex_verem · 2026-10-20