Skip to content

Smart time tracking without surrendering your raw day.

drifty automatically captures your Mac activity and turns it into useful focus and drift patterns. The complete timeline stays on this Mac by default, while Local AI, remote AI, and Device Sync remain separate choices.

Privacy is an architecture choice.

A privacy policy can explain how uploaded data is handled. The more practical question is whether the source record needed to leave your Mac at all. drifty keeps automatic capture local first, then makes every remote path visible and optional.

  • Automatically capture apps, sites, windows, and sessions into a local Mac timeline.
  • Classify with Local AI without sending a classification request off the Mac.
  • Choose drifty Cloud, OpenRouter with your own API key, or a custom endpoint only when that route fits.
  • Keep Device Sync off, or enable it per Mac and purge its private remote copy in the app.
  • Publish only optional profile fields and aggregate focus totals, never the raw timeline behind them.

What stays. What leaves. You decide.

“Cloud” is not one switch in drifty. Capture, classification, sync, analytics, and public sharing have separate boundaries.

SurfaceDefault locationLeaves your Mac whenYour control
Complete activity timelineLocal SQLite database on this MacYou explicitly enable the paid Device Sync PreviewEnable per Mac; pause or purge the private remote copy in the app
Local AIInference runs on this MacNever for the classification requestChoose Local AI as the classification route
drifty CloudLocal timeline remains the sourceYou choose Cloud classification; selected, minimized fields go to the hosted provider routeChange route and field-level AI privacy settings
OpenRouter (your key)Local timeline remains the sourceYou choose your OpenRouter account for classificationYour key, model, quota, and route choice
Custom endpointLocal timeline remains the sourceYou configure and choose that endpointYou select the endpoint and its operator
Product analyticsOn by default; raw timeline is excludedLimited named events and bounded aggregates are sent while analytics is enabledDisable future product analytics in Settings → Privacy
Profile and leaderboardPrivate until you opt inYou publish selected profile fields and aggregate focus totalsChoose what to publish or keep the surfaces private

Read the full Privacy & Data Boundaries documentation.

How common privacy architectures differ.

These products optimize for different jobs. This compares capture, interpretation, and the documented default data boundary—not vague “privacy-first” badges.

ToolCapture and interpretationDocumented data boundaryBest fit
driftyAutomatic Mac capture with context-aware AI classificationComplete timeline local by default; Local AI sends no classification request; remote AI and sync are explicit choicesSmart personal review with a selectable processing boundary
TimingAutomatic app, document, and domain capture with project review and optional AI summariesLocal database by default; Timing Sync merges tracking data into its sync account, and optional AI summaries process some Mac-usage data with OpenAIMature Mac time accounting and billing workflows
ActivityWatchAutomatic local capture with user-authored regular-expression category rulesIts privacy documentation says usage data is stored locally and is not transmitted to external serversOpen-source local history and self-managed categorization
RizeAutomatic capture with AI client, project, and task taggingIts policy defines tracked activity as User Data and retains activity data while subscribed; optional Screen Text can send an image to Vertex AI in Cloud mode, while Rize says it does not store that imageCloud-backed project attribution and team reporting

Sources checked September 13, 2026: drifty data boundaries; Timing FAQ, Sync, and AI summaries; ActivityWatch privacy and categorization; Rize privacy policy and automatic tracking.

Useful insight without one mandatory cloud.

Local-first does not have to mean raw logs with no interpretation.

Automatic capture

Build a continuous Mac timeline without relying on start-and-stop timer memory.

Context-aware classification

Turn activity into focus and drift patterns instead of stopping at an unstructured event archive.

Route-level control

Keep inference local or deliberately choose the remote route whose convenience and tradeoffs you accept.

Private time tracker FAQ.

  • Does drifty upload my raw activity history?

    Not by default. The complete app, site, window, and session timeline stays in the local Mac database. If you explicitly enable the paid Device Sync Preview, raw activity segments are copied into private, account-scoped sync storage so your own Macs can merge them.

  • What does Local AI keep on my Mac?

    With Local AI, no classification request leaves your Mac. The model download and memory use depend on the model, while the complete activity timeline remains the local source of truth.

  • What leaves my Mac when I choose remote AI?

    The chosen provider receives selected, minimized fields for that classification request, such as app name, domain, duration, and optional privacy-controlled context. drifty excludes a replayable raw timeline, document or message bodies, screenshots, passwords, secrets, and provider keys.

  • Is drifty 100% private?

    No internet-connected software should promise absolute security. drifty makes a narrower, verifiable promise: the complete timeline stays local by default, Local AI sends no classification request, and remote AI or device sync require an explicit choice.

  • Is drifty a screen recorder?

    No. drifty analyzes activity information needed for time review, but it is not a continuous screen recording app.

  • What gets shared publicly?

    Public leaderboard and profile surfaces are optional and use aggregate focus totals, not raw app, site, window, or session history.

Keep the source record close.

Get automatic capture and meaningful AI classification without making the cloud your only option.

Download for Mac