Caveman is fun, but the real tool you want to reduce token usage is headroom

https://github.com/gglucass/headroom-desktop (mac app)

https://github.com/chopratejas/headroom (cli)

Different positionning - headroom compress inputs and open source project - caveman is output and open source - edgee more corporate offer

Headroom looks great for client-side trimming. If you want to tackle this at the infrastructure level, we built Edgee (https://www.edgee.ai) as an AI Gateway that handles context compression, caching, and token budgeting across requests, so you're not relying on each client to do the right thing.

(I work at Edgee, so biased, but happy to answer questions.)

I tried to use rtk for the same, and my agent session would just loop the same tool call over and over again. Does headroom work better?