Headroom at 77,253 Stars: 300 Log Lines Compressed to Zero, and Four Different Savings Numbers for the Same Tool

Thu, 22 Oct 2026 00:00:00 +0000

Headroom compresses what your agent reads before the model sees it. The GitHub description states the pitch in one line: “20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers.” The PyPI page says “Cut costs by 50-90%”. The README proof table says 21%, 57%, 42% and 30%.

Those are four different claims on four surfaces the same team controls. This article measures what the library actually does to seven kinds of payload, and then compares every published number against every other published number, because the compression tool’s own repository contains the evidence that its front-page figures were not reproducible — “by anyone, including us”, in the words of a script it ships.

Prompt Caching on SoloSoft

Headroom at 77,253 Stars: 300 Log Lines Compressed to Zero, and Four Different Savings Numbers for the Same Tool