回到 Skill 榜单

headroomlabs-ai/headroom

LLM 上下文压缩库:压缩工具输出、日志、RAG 段,为 coding agent 节省 20% token,JSON 节约 60-95% 且答案不变。提供 library / proxy / MCP server。

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.

75,321 5,846MCPPython

Quick Assessment

适合谁MCP server 开发者、agent 整合者
活跃度最近推送:2026/10/13 · 开放 issues:440
成熟度分162.9
近 7 天增长+14628 stars
LicenseApache-2.0

安装方式

uv tool install --python 3.13 "headroom-ai[all]" # CLI as a global tool in a self-contained virtual env

来自 README,安装前请自行确认。

上榜徽章

Scoutari Skill Radar badge for headroomlabs-ai/headroom[![Scoutari Skill Radar](https://scoutari.com/api/badge/headroomlabs-ai/headroom)](https://scoutari.com/skills/headroomlabs-ai/headroom)

贴进 README 即可展示排名,并连回本页评估。