Show HN: AI search for every photo and every frame of video on macOS
- ID
- 32168
- Status
- summarized
- Published
- 04 Oct 2026, 5:24 PM
- Fetched
- 06 Oct 2026, 3:15 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://github.com/allenv0/SCM
- Source URL
- https://hnrss.org/best
Summary
- Score
- 6.5
- Created
- 06 Oct 2026, 3:16 PM
- Tags
- Audience
- developersvibe_codersai_ml_learnersai_agent_users
What happened
SCM (Screen Memories) is an open-source macOS app that does local-first AI search over every photo and every frame of video in any folder, with no accounts, cloud, or uploads. It has five search modes—Files (CLIP vision), Scenes (timecoded video shots), OCR (Tesseract with eng + 35 language toggles), Dialogue (Whisper exact spoken-line search), and opt-in LLM chat over extracted dialogue/OCR/filenames—plus watched-folder auto-import, content-hash dedupe, and background re-embedding. It installs via Homebrew on Apple Silicon macOS 12+, downloads about 435MB for the default CLIP model on first use, and the HN thread has 165 points/73 comments; the repo shows 385 stars, 25 forks, and 9 commits.
Why it matters
If you build local AI search, agent memory, or media tooling, this is a concrete reference for combining CLIP scene embeddings, Whisper, Tesseract, and background re-indexing without a cloud API. The practical decision is whether to brew install and test it on your own Apple Silicon Mac now, or wait: it is early (9 commits), macOS-only, and not a production-backed service. No Malaysian or SEA policy/funding angle appears in the text.
Discussion angle
Walk through the five search modes and ask which pieces are reusable for an agent-memory or company media library—especially scene-level video embedding, hash dedupe, and background re-embedding—and which are Electron/macOS-specific packaging choices.