A new macOS application provides AI-powered search capabilities for local photo and video libraries. This tool operates entirely on the user's machine, eliminating the need for cloud accounts, uploads, or internet connectivity after initial setup. Inference runs locally, ensuring user privacy.
The application allows users to search their media using natural language descriptions. It segments video scenes to pinpoint specific moments, rather than just files. Additionally, it incorporates Optical Character Recognition (OCR) for visible text within media and utilizes Whisper for searching spoken dialogue.
Features include self-maintaining libraries with auto-import from watched folders, content hashing for deduplication, and background re-embedding when models are switched. The tool emphasizes privacy, stating that media never leaves the user's machine. Model weights are downloaded once and then operate offline.
The application is built for macOS and uses Bun as its package manager and runner. Installation is available via Homebrew, which handles macOS Gatekeeper requirements automatically. The project also provides commands for development and building the application.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
A new macOS application offers local-first AI search for photos and videos, allowing users to query media using natural language. The tool processes content on-device, including OCR for text and Whisper for spoken dialogue, without cloud uploads.