Skip to content

About TokenBar

TokenBar is a macOS 14+ menu bar app for watching AI usage, credits, and reset timing across Claude, Codex, Cursor, Gemini, and Copilot, with a spending overview. Built on CodexBar, the MIT-licensed open-source project by Peter Steinberger. Free download; Pro $15 once or Basic $5/month.

Who it is for
Developers and heavy AI users on Mac who use Claude, Codex, Cursor, Gemini or Copilot.
Problem it solves
AI usage limits, credits and reset times are spread across several tools, which makes it hard to see how much you have left or are spending.
The solution
TokenBar sits in the macOS menu bar and shows your AI usage, credits and reset timing for Claude, Codex, Cursor, Gemini and Copilot, plus a spending overview, so you can see what is left at a glance.
What makes it unique
It shows usage, credits and reset timing for five AI providers in one menu bar app, with a spending overview. It is built on the MIT-licensed CodexBar project.

Features

  • Pixel Agents: a local pixel art office for supported coding-agent sessions

  • Light and dark appearances with an adjustable Pixel Agents room background

  • Live AI usage visibility that stays easy to check

  • Notifications when usage changes in ways you may want to notice

  • Local-first monitoring on macOS where possible

  • Your agents.A little more alive.

    A little office for your coding agents. See who’s working, who’s finished, and who needs your attention, right inside TokenBar.

Details

Platforms
  • macOS
Pricing
  • One-time purchase
  • Freemium
Built for

Developers and heavy AI users on Mac who use Claude, Codex, Cursor, Gemini or Copilot.

Building since

2026

Technology

TokenBar product screenshot

1 / 1

Website performance

Recorded mobile lab measurements and finalized weekly standings from IndieTools Speed.

TokenBar website speed overview

97
Performance scoreGood

In IndieTools' mobile lab test on November 18, 2026, the TokenBar website scored 97 out of 100 (good). Largest Contentful Paint took 1.53 s, rated good.

Measured (UTC)

LCPLargest Contentful Paint
1.53 s
Good
TBTTotal Blocking Time
61 ms
Good
CLSCumulative Layout Shift
0.000
Good
FCPFirst Contentful Paint
1.53 s
Good

Not ranked in a finalized week yet.

Stored lab observations from controlled test runs, not real-user Core Web Vitals or a guarantee of search rankings. Weekly standings remain attached to their finalized edition.Method psi-mobile-two-sample-mean-v1, 2 samples per reading. Lab results can vary between runs.

DR4 (primary model)
0

First DR4 reading

DR3
6

First DR3 reading

Model difference−6. DR4 is 6 points lower than DR3.

Measured · tokenbar.site

What do DR4, DR3 and the model difference mean?
DR4:
Ahrefs' newer model. It gives more weight to links from sites with organic search traffic and rates a subdomain on its own links.
DR3:
The previous model, shown in the Ahrefs app until 1 December 2026.
Model difference:
DR4 minus DR3 for the same domain. The models calculate differently, so this is not growth or a drop; the “since” lines compare each model with itself.

Related products

Others in the same categories.

Managed DBA and database reliability engineering services for MySQL, PostgreSQL, MongoDB and 20+ other engines.