why use many token when few do trick
One command wraps Claude Code, Codex, Hermes, and more with a local proxy that compresses logs, tool output, and files before every provider call. In a pinned 54-run benchmark: 33.2% fewer input tokens with 18/18 correctness checks. Caveman can also run any existing agent skill with ~70% fewer tokens by loading text as images. Built on an open-source ecosystem with 97K+ GitHub stars.
Caveman launched on Product Hunt on 2026-08-13 and has 125 upvotes and 7 comments so far.
This tool is open source.