GoKawiilNew macOS app SCM offers local AI search across photos and video frames
A Show HN post introduces Screen Memories (SCM), a macOS application that lets users search photos and every frame of video using natural-language queries, OCR, and spoken-dialogue search via Whisper. All processing runs locally on-device through a local vision model, with no cloud uploads or accounts required, and the app auto-imports watched folders and re-embeds content when models change.
GoKawiil's interpretation of the reporting above, not reported fact.
The tool reflects a broader trend of running AI inference locally rather than in the cloud, which could appeal to privacy-conscious users wary of uploading personal photos and videos to third-party servers. By combining multiple search modes—visual meaning, scene-level video search, OCR, and dialogue transcription—into one offline tool, it suggests an attempt to make multimedia search as granular as text search, though its reliance on macOS-only packaging limits its reach to Apple's ecosystem.
- SCM searches both photos and individual video frames using a local AI vision model.
- All inference and media storage stay on-device, with no cloud uploads or account requirements.
- The app supports five search modes: Files, Scenes, OCR, Dialogue, and an opt-in local LLM chat feature.
Apple Mac mini (M4) — Since this app runs AI inference locally for photo and video search, having a Mac with a powerful chip makes a real difference in speed. The Mac mini with M4 offers strong on-device neural engine performance for exactly this kind of local AI workload, without needing cloud uploads. It's an affordable way to get a capable Mac dedicated to running local vision models smoothly.”},
See Apple Mac mini (M4) on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: github.com, 2026-10-04
Published there as: “Show HN: AI search for every photo and every frame of video on macOS”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.