Save money by shortening AI responses
Caveman is a capability package developed for Claude Code that reduces token consumption by 65 percent by simplifying the language use of the artificial intelligence model. This tool aims to reduce processing costs by reducing complex commands to a primitive language structure.
Updates
- September 15, 2026: Stars 103,279 → 105,664, latest release v2.7.0 (September 15, 2026).
- September 4, 2026: Stars 102,818 → 103,279, latest release bin-v1.1.6 (September 4, 2026).
- September 3, 2026: Stars 102,006 → 102,818, latest release bin-v1.1.5 (September 2, 2026).
- August 31, 2026: Stars 100,541 → 102,006, latest release v2.4.0 (August 29, 2026).
What you get
- Saves up to 65% tokens on AI responses.
- Eliminates unnecessary words without sacrificing technical accuracy.
- It reduces transaction costs and increases response speed.
Installation
curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bashirm https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.ps1 | iexRunning it
/cavemanIf you don't write code
From now on, give your answers in Caveman mode. Remove unnecessary filler words, keep only the concise information and technical details. Compose your answers in short, concise and fragmented sentences; but continue to convey complete and precise code blocks, commands and error messages.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-03: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.