software · Picked by us
A lifetime of photos, sorted without leaving your machine
A dry-run-first organizer for large photo and video archives: index by city, person or event with local ML, review the plan, then apply — with a journal and one-command undo.
By 
Vladimir Karataev @shinKatana0
The maker’s GitHub profile
Public repository with install steps; MIT
What it does
Clean up tens of thousands of photos and videos without uploading them — and without a one-way door: every move is planned, journaled and reversible.
Who it helps
People with large personal media archives who want them organized locally.
How it was made
- Models
- Claude Code · creator-reported
- Tools
- Claude Code · Primary build agent under human architectureLocal ML models · On-device indexing; optional GPU tiers
- Everything runs locally: media is indexed with on-device machine learning, hashed, and never uploaded.
- The default run is a dry run; real moves are journaled and reversible with a single command, with duplicate review and recycle-bin deletion.
- The maker reports testing on about 380 GB and 38,000 files, with Claude Code and other agents writing a large share under his architecture and review.
What the person did
Vladimir Karataev set the architecture, safety rules and review bar; the repository documents him as the operator of the agent workflow that produced it.
What we know
Creator-reported: A usable public repository, the maker’s profile naming the project, and a build account that documents the division of labour.
Access checked — 2026-09-27 · Opened the repository and the creator profile on 2026-09-27; the scout dossier verified the same links the previous day.
Can you use it?
The repository is MIT and carries a synthetic demo image; we link rather than host captures. The cover is an original Made With Models illustration, not a screenshot of the tool.
About this project
Picked by Made With Models. Added 2026-09-27. Updated 2026-09-27.