Caveman
Viral skill and proxy that forces coding agents to spend fewer tokens
AI Agents / Coding Agents · Apache-2.0 · 114k
Reviewed 2026-09-20 · last push 2026-10-18 · repo checked 2026-10-19
What's Good
MIT skill packaging (JuliusBrussee/caveman) with install paths across many agent hosts, plus middleware/CLI wrappers that rewrite verbose agent chatter into short caveman-style output. Independent writeups (including JetBrains and an Adobe Research CAVEWOMAN paper cited in-repo) treat the compression as real cost leverage, not only a meme.
The Catch
Engine-linked runtime directories (engine/, proxy/, rewriter/, and related) are Business Source License 1.1, not MIT — see LICENSING.md / LICENSE.BSL before embedding or offering a hosted Caveman runtime. Vs LiteLLM: Caveman is output/style compression for agent hosts, not a multi-provider model gateway. Terse output can hide nuance; keep quality checks on hard tasks.
Verdict
MIT skill surface with BSL engine bits. Use to cut coding-agent token spend; read the BSL boundary before productizing the runtime.
Embed
Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.
Markdown
[](https://stackgems.com/gems/caveman)
HTML
<a href="https://stackgems.com/gems/caveman"><img src="https://stackgems.com/badge/caveman.svg" alt="Caveman reviewed on Stack Gems" height="20"></a>