AI & ML

headroom

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.

headroomlabs-ai

Maintainer

64.9k stars

Go to website ↗View on GitHub

About this project

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. Maintained by headroomlabs-ai on GitHub, where it has earned 64,851 stars from the community.

It's actively developed around agent, ai, anthropic, and is a solid reference for anyone building with these tools.