A free open-source Mac app called SCM lets users search every photo and every frame of their videos by describing what they're looking for, with all processing done locally.
→ It can find images by description, jump to video moments by timecode, read text in images and search spoken words
→ It uses local vision models, Tesseract for text and Whisper for speech, with an optional local chatbot
→ After a one-time download of about 435MB of model weights, it works fully offline with no accounts
→ The project drew 146 points on Hacker News
Source: