headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95…
Live
Open / InstallLast updated July 27, 2026
Description
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. An open-source AI framework/SDK by headroomlabs-ai, hosted on GitHub.
Author
headroomlabs-ai
Platform
api
Pricing model
free
Categories
AI Frameworks
Tags
agent
ai
anthropic
claude-code
compression
context-engineering
context-window
cursor
github
Capabilities
- 62,653 stars
- Python