GitHub repo

headroomlabs-ai/headroom

Python Tracked since 2026-01-07 Updated 2026-07-16 View source ↗

#30 of 783 by Stars among GitHub repos

59.4k Stars

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

About

██╗ ██╗███████╗ █████╗ ██████╗ ██████╗ ██████╗ ██████╗ ███╗ ███╗ ██║ ██║██╔════╝██╔══██╗██╔══██╗██╔══██╗██╔═══██╗██╔═══██╗████╗ ████║ ███████║█████╗ ███████║██║ ██║██████╔╝██║ ██║██║ ██║██╔████╔██║ ██╔══██║██╔══╝ ██╔══██║██║ ██║██╔══██╗██║ ██║██║ ██║██║╚██╔╝██║ ██║ ██║███████╗██║ ██║██████╔╝██║ ██║╚██████╔╝╚██████╔╝██║ ╚═╝ ██║ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝╚═════╝ ╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚═╝ ╚═╝ The context compression layer for AI agents

AI agents / LLMs: read /llms.txt here, or fetch the live index / full docs blob.

Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. Same answers, fraction of the…

Excerpted from github.com/headroomlabs-ai/headroom

Latest metrics

Stars 59.4k 2026-07-16
Forks 4.4k 2026-07-16
Commits 2.3k 2026-07-16
Releases 161 2026-07-16
Watchers 178 2026-07-16
Open issues 239 2026-07-16
Open PRs 175 2026-07-16