rtk

CLI proxy that reduces LLM token consumption through smart caching

brewmacoslinux
Try with needOr install directly
Source

About

CLI proxy to minimize LLM token consumption

Commands

rtk

Examples

Proxy an API request to minimize token usage$ rtk proxy --model gpt-4 --cache
Check token usage statistics for cached requests$ rtk stats
Clear the token cache to reset usage tracking$ rtk cache clear