caveman

Caveman strips the fluff from Claude Code responses. Install it with one command, activate with /caveman, and your AI assistant drops the pleasantries, hedging, and filler words while keeping full technical accuracy. Average savings: 65% fewer output tokens.

Multiple intensity levels: Lite stays professional but terse, Full drops articles and uses fragments, Ultra goes telegraphic, and Wenyan variants compress into classical Chinese. Code blocks, error messages, git commits, and technical terms pass through untouched. Version 2 added a compression engine that squeezes model input as well: tool outputs, logs, and JSON get compacted before they hit your context window, and a companion tool rewrites your CLAUDE.md and memory files to cut input tokens too.

It works across 30+ AI coding agents, not just Claude Code. Cursor, Copilot, Windsurf, Cline, Codex, all supported. Heavy token users will feel the difference in both speed and cost.

The catch: it started as a meme but the benchmarks are real, backed by a real 2026 research paper. Ultra mode can be hard to read. And v2 split the licensing: the skill, CLI, and SDKs stay MIT, while the engine, proxy, and platform components moved to BSL-1.1, free to self-host including production, only blocking resale of Caveman as a service. The split is per-component, so the LICENSE file in each package is the authority.