macOS 13+

Your mind has a
context window.
Start measuring it.

Human Token tracks your daily cognitive load as weighted tokens — mirroring how LLMs process context.

Download for Mac
v1.1 · macOS 13+
Human Token app screenshot
Zero config.
All on your Mac.
Forever free for personal use.
What it does

Six things Human Token
does for you.

It sits in your menu bar, watches which apps you use, and turns that into three numbers that tell you how your day is going — mentally.

Tracks what you're doing

Every app you use gets counted — coding, writing, meetings, browsing, AI tools. No setup. It just works in the background from the moment you open it.

Temperature — are you in the zone?

Shows how varied your work is today. Stuck in one app all day? Low temperature. Mixing coding, writing and research? Higher. The sweet spot is somewhere in the middle.

Saturation — how full is your tank?

Think of it like a fuel gauge for your brain. The average person can do about 4 hours of real deep work per day. Saturation tells you how much of that you've already used.

Breaks actually count

Walk away for 10+ minutes and your token count goes down. Real rest genuinely restores your mental capacity — Human Token tracks that too, not just the work.

See when you're sharpest

The live velocity chart shows your token rate hour by hour. You'll quickly spot when you do your best work — and stop scheduling meetings there.

Your full history, always

Every day is saved on your Mac. Come back a month later and see exactly how you've been spending your mental energy — no account, no subscription, no cloud.

Not all thinking
costs the same.

Human Token weights different cognitive activities differently — just like transformer attention weights some tokens more than others.

×3.0
Reasoning
Deep cognitive work that requires sustained attention and original thought. The most expensive mode.
Xcode VSCode Figma Sketch Terminal DaVinci Resolve
×2.5
AI Collaboration
Working with AI tools is uniquely intense — you're directing, evaluating, and integrating simultaneously.
Claude ChatGPT Cursor Perplexity GitHub Copilot Gemini
×2.0
Output
Producing written content, messages, plans. Heavy on working memory and language production.
Notion Slack Obsidian Linear Todoist Outlook
×1.0
Input
Consuming information — browsing, reading, video calls. Cognitively lighter but still tracked.
Chrome Zoom Safari Kindle Reeder Firefox
Research references behind the numbers

Temperature

Mark (2023) Attention Span — average on-screen attention is now 47 seconds. Varied cognitive modes signal healthier focus patterns.

Ophir, Nass & Wagner (2009) PNAS — measurable cognitive impairment even at moderate switching rates.

Saturation

Wiehler et al. (2022) Current Biology — glutamate builds up in prefrontal cortex across the day, degrading decisions.

Newport (2016) Deep Work — ~4 hours/day is the ceiling for high-quality cognitive work.

Fragmentation

Ophir, Nass & Wagner (2009) — 8+ app switches/hour causes measurable impairment. Severe fragmentation (15+/hr) cuts effective output by ~40%.

Session Context Multipliers

Human Token detects your current cognitive mode from the running app stack — no setup required.

×1.4

Deep Work

IDE + Terminal running

×1.2

AI Session

AI tool in foreground

×1.1

Meeting

Zoom / FaceTime active

×1.0

Writing / Browsing

Standard activity

×0.8

Switching

8–14 app switches/hour

×0.6

Fragmented

15+ app switches/hour

Metrics

Three numbers
that change how you work.

Each metric surfaces a different dimension of your cognitive state — in real time, from your Mac.

Temperature

How varied is your thinking today? Low means you've been stuck in one mode all day. High means you've mixed different types of work. Both extremes are fine sometimes — this just tells you where you are.

hover a slice
0–25%One mode all day
25–55%Good variety
55–80%Creative mix
80–100%Very high flux

Context Saturation

How much of your daily mental budget have you spent? Research consistently shows the brain can sustain about 4 hours of real deep work per day. 100% means that tank is empty.

hover a slice
0–40%Still fresh
40–70%Loading up
70–90%Getting full
90–100%Tank empty

Break Recovery

Rest genuinely frees cognitive context. Wiehler et al. (2022) showed brief pauses don't reduce prefrontal glutamate — recovery requires at least 10 minutes of real disengagement.

BreakRecovery
< 10 minNone
10–30 minUp to 600 tokens
30–120 minUp to 1,800 tokens
> 2 hoursEnd of day

Everything stays
on your Mac.

No account, no cloud, no telemetry. Here's exactly what the app reads — and what it never touches.

Asks once

Browser tab URL

Reads only the domain of your active tab every 30 seconds — to detect AI tools and web meetings. Never page content, never other tabs. You can decline and the app still works.

No permission

Running apps

Reads which app is in the foreground — only its name and bundle ID. Used to classify your cognitive mode and token type. Nothing else.

No permission

File saves

Uses Spotlight to detect code saves in the last 45 seconds. Only reads the file extension (e.g. .swift) — never file contents.

No permission

Idle detection

Checks seconds since the last keyboard or mouse event. No keystrokes captured, no clicks recorded. Used only to detect breaks.

No permission

Git commits

Runs git diff --shortstat to count lines changed. Never reads commit messages or file contents.

Never

What we never touch

No microphone, camera, contacts, or screen. No keylogger. No internet calls — ever. All data lives only in your Mac's local storage.

Free download

Your context window
is waiting to be measured.

No account. No setup. Just open and it works.

Download Human Token
macOS 13 Ventura or later · Apple Silicon & Intel · Free