Stello Trace · Powered by Stello
No timers. No timesheets.
Your workday writes itself.
Stello Trace sits quietly in your menu bar, recording your Mac work trail — and every evening, AI turns it into a daily report you can actually read. Your data stays on your machine.
- macOS 13+
- Local-first storage
- Screenshots optional
- DeepSeek / OpenAI / local Ollama
How it works
Three steps from scattered hours to one readable story
Fully automatic — you do the work, it does the remembering.
Silent capture
Foreground apps, window titles, browser URLs and optional low-frequency screenshots flow into a database on your machine. No interruptions, no check-ins.
AI synthesis
A language model clusters raw events into work sessions: which project you pushed forward, which meetings you sat through, what interrupted you and for how long.
Narrative report
Daily and weekly reports aren't pie charts — they're prose you can paste straight into a standup or status update.
The morning went to the billing-module refactor: heavy switching between Xcode and GitHub from 9:40 to 11:35, two PRs merged. The 11:40 product sync ran 50 minutes, followed by a Slack backlog sweep. The afternoon's main thread was the quarterly review deck, interrupted three times by support tickets — about 40 minutes total.
Features
Built to answer “what did I actually do today?”
Not another timer — an automatic writer for your working memory.
Narrative daily & weekly reports
Readable paragraphs, not dashboards. Quote them in standups, status updates and reviews.
Calendar-aware
Meetings from your system calendar (and Lark/Feishu) land in the report automatically — work blocks and meeting blocks never blur.
Bring your own model
DeepSeek by default (light use ≈ a coffee per month), any OpenAI-compatible cloud API — or local Ollama, fully offline.
Native menu-bar app
Written in Swift. Light, fast, battery-friendly. Works offline — events persist locally and sync analysis later.
Privacy
First, the straight answer: where your data goes
A tool that records your screen has to earn trust. Here is the Stello Trace data ledger, line by line.
| Data | Stored | Leaves your machine? |
|---|---|---|
| App & window events | Local SQLite on your Mac | Text summaries only, sent to the model provider you configured — nothing else |
| Screenshots | Local only, for your own review | Never uploaded; can be disabled entirely in settings |
| Calendar events | Local cache | Meeting titles join the text summary for report generation |
| Telemetry / analytics | — | None. No telemetry in the app, no analytics script on this site |
With local Ollama, the entire pipeline runs offline — analysis included. Exclusion rules let you block specific apps and sites (password managers, private browsing). Read the full privacy notes.
For teams & organizations
A person sees a day.
An organization sees the loops.
The hours lost to copy-paste, cross-system shuffling and manual reconciliation show up as repeating patterns in work trails. Find the loops, and you've found where AI automation starts.
Stello's forward-deployed engineers (FDE) embed in your business and turn those loops into running automation — delivering a capability, not a one-off tool.
FAQ
You probably want to ask
Is it watching my screen?
It records foreground app names, window titles, browser URLs and timestamps. Screenshots are low-frequency, local-only, and can be switched off entirely. Everything sits in a local database you can open, inspect and delete.
Is it free? Will it stay free?
The app is free. AI analysis runs on your own API key (DeepSeek ≈ a coffee per month for light use) or local Ollama at zero cost. Organization-level automation diagnosis and delivery are Stello services, scoped separately.
Why bring my own API key?
Because there's no relay server. Your work data never touches our infrastructure — it goes straight from your Mac to the provider you chose. That's a privacy decision, not a shortcut.
How is this different from RescueTime, Rize or Timing?
They chart where time went; the output is a graph. Stello Trace writes what you got done; the output is prose — for standups, updates and honest self-review.
Windows version?
Planned. macOS 13+ first.
Can I export my data? Am I locked in?
Everything is standard SQLite on your own disk. Take the file anywhere, open it with any tool. Uninstalling leaves no cloud residue — there was never a cloud copy to begin with.
Download
See tonight's report about today
Free download, two-minute setup. Work today, read it tonight.
macOS 13 Ventura or later · Notarized by Apple · Privacy notes