Hit the shortcut.
Cairn captures the screen, runs OCR on what's visible, and starts listening — all in one move. No app to open, no window to focus.
Cairn captures a screenshot together with a voice tag. Later, type how you'd describe it — "the postgres lock thing Ivan sent me" — and Cairn finds it. Voice runs through Whisper on-device. Nothing leaves your Mac.
Twenty a week. Stack traces, Linear tickets, Figma frames, Slack threads, PR diffs. They land in ~/Desktop with the most useless filenames ever invented.
Screenshot 2026-05-18 at 14.22.07.png812 KBScreenshot 2026-05-18 at 14.31.49.png1.1 MBScreenshot 2026-05-15 at 09.14.02.png644 KBScreenshot 2026-05-13 at 11.42.13.png901 KBScreenshot 2026-05-12 at 17.05.58.png733 KB1,279 more files—Now find the one with the lock thing Ivan sent on Tuesday.
One shortcut. A quick voice note. A search bar that understands the way you actually talk about things.
Cairn captures the screen, runs OCR on what's visible, and starts listening — all in one move. No app to open, no window to focus.
Say it out loud. "Postgres lock thing from Ivan." Cairn transcribes it on-device with Whisper and stores it next to the image. Don't feel like talking? Type it on the same shortcut.
You don't have to remember your exact words. Cairn matches on meaning, not on string equality — across your voice tag, the on-screen text, and AI-generated context. Said "postgres lock from ivan"? Searching "that db deadlock thing Ivan sent" still finds it. Misspellings are fine. Phrasing is fine. Yesterday is fine. Last quarter is fine.
So don't. The same shortcut takes voice or text — whatever the moment is for. Open-plan office, headphones in, AirPods in a meeting, kid asleep in the next room. Cairn doesn't care which mode you used; the tag is the tag.
No accounts. No cloud transcription. No cloud embeddings. No telemetry. The app runs inside the macOS sandbox and only writes to its own container. You can verify it with Little Snitch.
AI outputs (transcripts and image tags) are model-generated and can be inaccurate. See the Privacy Policy for details.
ScreenCaptureKit.all-MiniLM-L6-v2 embeddings, 384-dim, stored in sqlite-vec. Voice-tag weight bumped at query time.Requires macOS 14 Sonoma or later. Apple Silicon. ~280 MB on disk plus your screenshots.