Add token tracking and api call backoff when token per/minute usage too high for api

deedy / mac_computer_use

A fork of Anthropic Computer Use that you can run on Mac computers to give Claude and other AI models autonomous access to your computer.

https://x.com/deedydas/status/1849481225041559910

642 stars 98 forks source link

Add token tracking and api call backoff when token per/minute usage too high for api #4

Open medright opened 1 month ago

medright commented 1 month ago

Added a token tracking feature to intelligently calculate token usage and display in the ui, it also backs off api requests if the current per/minute rate would be exceeded.

here's what that looks like: