Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
headroomlabs-ai/headroom
在数据喂给大模型前压缩,帮AI agent省token,答案不变。A local compression tool that reduces token usage for AI agents and LLM apps without changing answers.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
压缩输入内容,节省token开销
压缩JSON数据,减少60-95%用量
压缩代码和文本,保持答案质量
通过代理直接压缩,无需改代码
自动学习优化,持续节省token
Compress JSON payloads by 60–95%.
Reduce coding helpers tokens by 20%.
Run as a local proxy with zero code changes.
Wrap Claude Code or Cursor in one command.
Monitor live savings with a dashboard.
上手GET STARTED
pip install headroom-ai选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh && rustup default stable
02读取 API KeyReads an API keyreadme
**Platform support.** macOS auth reuse through Copilot CLI Keychain storage and
静态扫描发现两项风险:一是安装过程会执行远程脚本(curl ... | sh),属于高风险;二是文档提到会读取 API Key(通过 Copilot CLI 的 Keychain 存储)。其他未命中项不代表没有风险。The installer runs a remote script to set up Rust (curl | sh), which is a security risk. The tool also reads API keys from your system keychain on macOS.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+7.9%+7.9%
74k → 80k stars · 49 个快照74k → 80k stars · 49 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
质量 B+Quality B+
近 7 天有 144 次提交,开发非常活跃。74,416 GitHub stars and 144 commits in the last week show active development and community trust.
HN_STORY · 10 points · 2 comments
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "codex",
"evidence": "readme: …| Oh My Pi | ✅ | Anthropic + OpenAI/Codex · injects config · starts pro…"
},
{
"agent": "cursor",
"evidence": "readme: …roxy and prints base URLs for Cursor settings | | Aider | ✅ | starts proxy…"
},
{
"agent": "cline",
"evidence": "readme: …copilot|cursor|aider|opencode|cline|continue|goose|openhands|open…"
},
{
"agent": "vscode",
"evidence": "readme: …| starts proxy + launches | | VS Code Copilot | ✅ | transparent pro…"
},
{
"agent": "opencode",
"evidence": "readme: …Code, Codex, Cursor, Copilot, OpenCode, Aider): ```bash uv tool ins…"
},
{
"agent": "copilot",
"evidence": "readme: …path. <details> <summary><b>GitHub Copilot CLI subscription mode</b></su…"
}
],
"apiKey": "ker and CI, pass an explicit `GITHUB_COPILOT_TOKEN` or `GITHUB_COPILOT_GITHUB_TOKEN` inste",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 11,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 8,
"productivity": 9
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "─────────┐ │ Headroom (runs locally — your data stays here) │ │ ─────",
"skillMdTotal": 2,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 3,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "2 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "server.json (MCP registry manifest)",
"weight": 0.85
},
{
"signal": "python dependency on mcp / fastmcp + MCP framing",
"weight": 0.8
},
{
"signal": "skills/ directory with 1 markdown files",
"weight": 0.75
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"plugins/headroom-skill/skills/headroom/SKILL.md",
"skills/headroom/SKILL.md"
],
"skillMdFetched": 2
}