headroomlabs-ai/headroom

把工具输出、日志、文件与 RAG chunk 在送入 LLM 前先压缩，同答案下大幅省 token，可作库/代理/MCP 服务。

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.