headroomlabs-ai/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.

10 best points · 2 comments · 3 Hacker News posts · 79,044 GitHub stars · View on GitHub

Hacker News discussions

• Headroom - compress AI agent input for reduced token usage w/out harming output (10 points, 2 comments, by andsoitis, 2026-07-21)
• Headroom – The context compression layer for AI agents (3 points, 0 comments, by sibellavia, 2026-06-22)
• Headroom: Save Tokens from Reversible Compression (1 points, 0 comments, by ghostoftiber, 2026-09-04)