Tokenxiety - AI Usage Monitor

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.