AI product Open source
SCM is a local-first macOS application for searching photos and videos by visual content, visible text, and spoken dialogue. It indexes whole files with local vision models, segments videos into scenes so searches can jump to a timecode, runs Tesseract OCR for literal text matching, and uses Whisper transcripts for exact spoken-word searches. An optional local LLM can answer questions over extracted dialogue, OCR, and filename evidence with citations.
The app imports files through manual selection, drag-and-drop, or watched folders. It content-hashes files for rename-proof deduplication, stores embeddings and media metadata locally, and can re-embed a library when the selected vision model changes. Model weights and language packs download once; subsequent inference runs offline, with no accounts, uploads, or telemetry. SCM is distributed as an Electron application for macOS, including a Homebrew cask and packaged DMG/ZIP builds.
1 use taken from transcripts — each links to the moment in the video.
Makes photos and videos in Mac folders searchable by their visual content, on-screen text, and dialogue. Watched folders keep the library current while models run locally after their initial download.
1 in the library.