caveman: a content-type-aware compression proxy reporting 33.2% fewer provider-billed input tokens in Claude Code

JuliusBrussee/caveman·high signalXBlueskyLinkedInCopy link

Now at 98.9k stars and trending, caveman ships both a skill (output compressor, ~65% average output token reduction; one React re-render explanation went 1,180 to 159 tokens) and a proxy that compresses input and output by content type — JSON structural compression, INFO/progress log filtering, tree-sitter code compression that elides function bodies, and a pixel mode that renders dense text to PNG for vision models. Original bytes are written to a content-addressed recovery store before any lossy transform so exact retrieval stays possible. Its benchmark claim is 33.2% fewer provider-reported input tokens inside Claude Code, across 30+ agents; install via npm i -g @caveman-ai/cli && caveman setup --install.