Photo Tagger is a command-line helper that asks a vision-language model to analyze your photos and writes Lightroom-compatible metadata. By default it keeps your originals untouched by creating XMP sidecar files, but it can embed the updates directly into each photo with --embed-in-photo.

It requires a running Ollama or LM Studio server that hosts a vision-language model, and the ExifTool binary available on PATH. The optional photo-tagger-gui package adds a PySide6 desktop frontend (the photo-tagger gui command).