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.
Headroom is a library, proxy, and MCP server that compresses tool outputs, logs, files, retrieval chunks, and conversation history before they reach a language model. It helps coding agents use fewer context tokens while keeping the original content available locally when needed. Its catalogue add-ons support using Headroom with agent workflows.
Latest release v0.41.0 — Release v0.41.0 · 14 Oct 2026
1 file for GitHub Copilot: headroom copilot-instructions.md — 138 tokens loaded in every session.
.github/copilot-instructions.md A 138 tok These files are headroomlabs-ai/headroom's own configuration — they tell GitHub Copilot how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.