Tokenxiety - AI Usage Monitor

Unofficial new tab dashboard for your own AI chat rate-limit usage. Not affiliated with Anthropic or OpenAI.

As of June 2026, Tokenxiety - AI Usage Monitor has 2 users in the Developer Tools category.

Usersno change0%
2
2
Ratingno change0%
— reviews
Reviewsno change0%
Version
0.33.0
Manifest V3
90-day change · In the last 90 days this extension 3 version updates.

History

7 snapshots

Tracking since May 7, 2026.

3.1620.8399999999999999May 7, 2026Jun 13, 2026
View as table
DateUsersRatingReviewsVersion
May 7, 20260.28.0
May 11, 20260.28.0
May 17, 202610.28.0
May 23, 202610.29.0
May 30, 202610.32.1
Jun 5, 202630.32.1
Jun 13, 202620.32.1
Now20.33.0

Changelog

  • Jun 13, 2026
    description
    Tokenxiety is an INDEPENDENT, OPEN-SOURCE new tab dashboard. It is NOT
    affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or any
    other AI service provider. "Claude" is a trademark of Anthropic.
    "ChatGPT" and "Codex" are trademarks of OpenAI. Those names are used
    here solely to describe interoperability — what services this tool
    reads when you are already signed in on them — under nominative fair
    use.
    
    WHAT IT DOES
    
    Tokenxiety reads your OWN rate-limit data from the AI chat services
    you are already signed in to and displays it on your new tab page so
    you can see, at a glance:
    
      * how close you are to your 5-hour and 7-day caps
      * when each cap resets
      * a burn-projection sparkline based on your own observed usage
      * a per-bucket breakdown (one row per limit your account exposes)
    
    PRIVACY
    
      * All data is stored LOCALLY in IndexedDB in your browser.
      * Nothing is ever sent to any server we control.
      * No analytics, no telemetry, no third-party network calls.
      * Source code is publicly auditable on GitHub.
    
    HOW IT WORKS
    
    When you open a new tab, Tokenxiety reuses the cookies in your own
    browser session (via the requested host_permissions on claude.ai and
    chatgpt.com) to call each service's own rate-limit endpoint. The
    response is parsed into a small set of utilization numbers and
    rendered. No API key, no sign-in, no configuration required.
    
    OPEN SOURCE
    
    MIT-licensed. Source: https://github.com/pratikgajjar/tokenxiety
    Privacy policy: https://github.com/pratikgajjar/tokenxiety/blob/main/PRIVACY.md
    
    NOT AFFILIATED with Anthropic, OpenAI, Google, or any other
    third party.
    Tokenxiety is an INDEPENDENT, OPEN-SOURCE new tab dashboard. It is NOT
    affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or any
    other AI service provider. "Claude" is a trademark of Anthropic.
    "ChatGPT" and "Codex" are trademarks of OpenAI. Those names are used
    here solely to describe interoperability what services this tool
    reads when you are already signed in on them under nominative fair
    use.
    
    WHAT IT DOES
    
    Tokenxiety reads your OWN rate-limit data from the AI chat services
    you are already signed in to and displays it on your new tab page so
    you can see, at a glance:
    
      * how close you are to your 5-hour and 7-day caps
      * when each cap resets
      * a burn-projection sparkline based on your own observed usage
      * a per-bucket breakdown (one row per limit your account exposes)
    
    PRIVACY
    
      * All data is stored LOCALLY in IndexedDB in your browser.
      * Nothing is ever sent to any server we control.
      * No analytics, no telemetry, no third-party network calls.
      * Source code is publicly auditable on GitHub.
    
    HOW IT WORKS
    
    When you open a new tab, Tokenxiety reuses the cookies in your own
    browser session (via the requested host_permissions on claude.ai and
    chatgpt.com) to call each service's own rate-limit endpoint. The
    response is parsed into a small set of utilization numbers and
    rendered. No API key, no sign-in, no configuration required.
    
    OPEN SOURCE
    
    MIT-licensed. Source: https://github.com/pratikgajjar/tokenxiety
    Privacy policy: https://github.com/pratikgajjar/tokenxiety/blob/main/PRIVACY.md
    
    NOT AFFILIATED with Anthropic, OpenAI, Google, or any other
    third party.
  • Jun 13, 2026
    name
    Tokenxiety — Unofficial AI Usage Monitor
    Tokenxiety - AI Usage Monitor
  • May 23, 2026
    description
    Tokenxiety replaces your new tab page with a tactical dashboard of your live
       usage limits across Claude (Anthropic) and Codex / ChatGPT (OpenAI).
    
       WHAT IT SHOWS
    
         • Claude — current session (5-hour), all-models 7-day, Sonnet only,
           Opus only, Claude Design, Co-work, OAuth apps, top-up credits.
         • Codex / ChatGPT — primary 5-hour and secondary 7-day windows for
           every metered feature your account exposes (e.g. Codex Spark).
    
       For each window you see:
    
         • Remaining percent (large, color-coded by severity)
         • Used / cap with threshold markers at 50% and 80%
         • Burn-projection sparkline with a NOW marker and 6-hour extrapolation
         • Live countdown to the next reset
         • The actual reset timestamp from the provider
         • A 53-week activity heatmap derived from your own polling history
    
       WHY NO API KEY
    
       Claude and ChatGPT do not expose stable public quota APIs. Tokenxiety
       makes the same requests your browser already makes when you visit the
       providers' usage pages, using the cookies you're already logged in with.
       There is nothing to copy, paste, or configure. If you're signed in to the
       provider, the dashboard works.
    
       PRIVACY
    
         • Host access is restricted to claude.ai, chatgpt.com, chat.openai.com.
         • All storage is local in IndexedDB. No server, no analytics, no telemetry.
         • Cookies and session tokens are never read, copied, or transmitted by
           the extension — they're attached to requests by your browser, exactly
           as on a normal page visit.
         • Only sanitized utilization numbers (percent used, reset times, plan
           name, the email each provider exposes on its own usage endpoint) are
           stored, locally only.
         • Open source under the MIT license. Source: https://github.com/pratikgajjar/tokenxiety
         • Privacy policy: https://github.com/pratikgajjar/tokenxiety/blob/main/PRIVACY.md
    
       PERMISSIONS
    
         • storage — remember your refresh interval and provider toggles.
         • alarms — schedule the background poll so usage history accumulates
           while you work, not only when you happen to open a new tab.
         • declarativeNetRequestWithHostAccess — rewrite Origin / Sec-Fetch-Site
           headers on the extension's own outgoing requests so Anthropic accepts
           them. Affects only requests initiated by the extension itself.
         • Host permissions for claude.ai, chatgpt.com, chat.openai.com.
    
       REMOVE EVERYTHING
    
       Open the Settings page → "Clear cache" wipes the local IndexedDB, or
       remove the extension and your data goes with it. There is no remote copy.
    Tokenxiety is an INDEPENDENT, OPEN-SOURCE new tab dashboard. It is NOT
    affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or any
    other AI service provider. "Claude" is a trademark of Anthropic.
    "ChatGPT" and "Codex" are trademarks of OpenAI. Those names are used
    here solely to describe interoperability — what services this tool
    reads when you are already signed in on them — under nominative fair
    use.
    
    WHAT IT DOES
    
    Tokenxiety reads your OWN rate-limit data from the AI chat services
    you are already signed in to and displays it on your new tab page so
    you can see, at a glance:
    
      * how close you are to your 5-hour and 7-day caps
      * when each cap resets
      * a burn-projection sparkline based on your own observed usage
      * a per-bucket breakdown (one row per limit your account exposes)
    
    PRIVACY
    
      * All data is stored LOCALLY in IndexedDB in your browser.
      * Nothing is ever sent to any server we control.
      * No analytics, no telemetry, no third-party network calls.
      * Source code is publicly auditable on GitHub.
    
    HOW IT WORKS
    
    When you open a new tab, Tokenxiety reuses the cookies in your own
    browser session (via the requested host_permissions on claude.ai and
    chatgpt.com) to call each service's own rate-limit endpoint. The
    response is parsed into a small set of utilization numbers and
    rendered. No API key, no sign-in, no configuration required.
    
    OPEN SOURCE
    
    MIT-licensed. Source: https://github.com/pratikgajjar/tokenxiety
    Privacy policy: https://github.com/pratikgajjar/tokenxiety/blob/main/PRIVACY.md
    
    NOT AFFILIATED with Anthropic, OpenAI, Google, or any other
    third party.
  • May 23, 2026
    short_description
    New tab dashboard for Claude and Codex usage limits.
    Unofficial new tab dashboard for your own AI chat rate-limit usage. Not affiliated with Anthropic or OpenAI.
  • May 23, 2026
    name
    Tokenxiety
    Tokenxiety — Unofficial AI Usage Monitor

Permissions & access

Permissions
storagealarms
Host access
https://claude.ai/*, https://chatgpt.com/*, https://chat.openai.com/*

Screenshots

Tokenxiety - AI Usage Monitor screenshot 1

About

Tokenxiety is an INDEPENDENT, OPEN-SOURCE new tab dashboard. It is NOT
affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or any
other AI service provider. "Claude" is a trademark of Anthropic.
"ChatGPT" and "Codex" are trademarks of OpenAI. Those names are used
here solely to describe interoperability what services this tool
reads when you are already signed in on them under nominative fair
use.

WHAT IT DOES

Tokenxiety reads your OWN rate-limit data from the AI chat services
you are already signed in to and displays it on your new tab page so
you can see, at a glance:

  * how close you are to your 5-hour and 7-day caps
  * when each cap resets
  * a burn-projection sparkline based on your own observed usage
  * a per-bucket breakdown (one row per limit your account exposes)

PRIVACY

  * All data is stored LOCALLY in IndexedDB in your browser.
  * Nothing is ever sent to any server we control.
  * No analytics, no telemetry, no third-party network calls.
  * Source code is publicly auditable on GitHub.

HOW IT WORKS

When you open a new tab, Tokenxiety reuses the cookies in your own
browser session (via the requested host_permissions on claude.ai and
chatgpt.com) to call each service's own rate-limit endpoint. The
response is parsed into a small set of utilization numbers and
rendered. No API key, no sign-in, no configuration required.

OPEN SOURCE

MIT-licensed. Source: https://github.com/pratikgajjar/tokenxiety
Privacy policy: https://github.com/pratikgajjar/tokenxiety/blob/main/PRIVACY.md

NOT AFFILIATED with Anthropic, OpenAI, Google, or any other
third party.

Technical

Version
0.33.0
Manifest
V3
Size
516KiB
Min Chrome
88
Languages
1
Featured
No

Metadata

ID
oipknkakhhnnmpabjcpacjdpegjaclii
Developer ID
u2a43f1b4749bb391e8b6a0b8b40ec0e8
Developer Email
[email protected]
Created
May 6, 2026
Last Updated (Store)
Jun 9, 2026
Last Scraped
Jun 13, 2026
Website

Data sourced from the Chrome Web Store · last verified Jun 13, 2026.