Headroom 是一个实时仪表盘,可监控多个 Claude 和 Codex 订阅的容量,在达到限制时自动切换账户,且检查用量不消耗任何令牌。

Stars

93

7 天增长

暂无数据

Fork 数

11

开放 Issue

1

开源协议

MIT

最近更新

2026-07-18

AI 仓库情报摘要
FR-AI / ANALYSIS

为什么值得关注

它解决了拥有多个 AI 订阅账户用户的痛点:在一个页面上查看所有账户的实时容量,当某个账户达到上限时自动轮换到下一个,并采用“故障关闭”设计,绝不会将流量路由到可能耗尽的账户。

适合谁使用

  • 拥有多个 Claude 或 Codex 订阅(个人、工作、团队)的开发者
  • 频繁触及使用上限的 AI 编程助手重度用户
  • 共享多个 AI 订阅并需要协调用量的团队
  • 希望实现 Claude Code 会话自动交接、无需手动切换登录的用户

典型使用场景

  • 在单一实时仪表盘中查看所有 Claude/Codex 账户的剩余容量
  • 当某个订阅达到限制时自动轮换到下一个可用账户
  • 在拥有最多余量的账户上启动 Claude Code,并可设置预留百分比以避免在接近上限时开始新会话
  • 通过 /rotator 技能或自动交接功能,在账户间无缝延续 Claude Code 对话

项目优势

  • 直接从提供商 API(Anthropic OAuth、Codex app-server)读取用量,不消耗任何令牌
  • 故障关闭架构:绝不会将流量路由到数据过时、身份无法验证或边缘情况的账户,并明确显示原因
  • 实时仪表盘提供五种主题、零依赖(仅需 Python 标准库),无需额外安装包
  • 自动会话交接需通过三重独立证据检查后方可执行,并设有循环防护防止无限制轮换

使用前须知

  • Windows 支持不完整(无监督自动交接、无菜单栏应用;系统托盘客户端为实验性功能)
  • 自动交接及部分功能仍处于实验阶段(v0.2),已知限制已在仓库文档中列出
  • 需要 Python 3.9+ 且已安装 Claude/Codex CLI;多机场景下无中央协调器

README 快速开始

headroom

A live dashboard for every Claude and Codex subscription you own — read straight from the providers without spending a single token — that rotates you to the next account with headroom the moment one hits a limit.

The heart of headroom is a live web dashboard you run locally. Run headroom serve, open http://127.0.0.1:8377, and every account's 5-hour, weekly, and model-scoped capacity is on one page, updating in real time. It's an ordinary local web page, so it works in any browser on any OS — you're not tied to one machine. A menu-bar app and pinnable desktop widgets are optional extras layered on the same data, for a glance without opening a tab.

https://github.com/user-attachments/assets/71e8ec51-8f0f-4ec2-806f-221b9eb6571f

Five built-in themes (Midnight, Minimal, Chrome, Paper, Terminal), switchable live from the dashboard. The setup wizard asks how you want it to look.

All five themes (static)

MidnightMinimal
ChromeTerminal

Why this exists

If you run more than one Claude or ChatGPT subscription (work + personal + team), you know the drill: a session dies with "you've hit your limit", you have no idea how much is left on the other accounts, and you burn ten minutes logging in and out to find out.

headroom fixes all three problems:

  1. See — every account's 5-hour, weekly, and model-scoped windows on one page, color-coded by what's left, not what's used.
  2. Read for free — usage comes live from the same reads your CLIs already use (Anthropic's OAuth usage API; the Codex app-server's rate-limits read). Checking your limits never consumes them.
  3. Rotateheadroom claude launches on the first account in your preference order with proven headroom. When a limit hits, headroom rotate (or the /rotator skill inside Claude Code) cools that login down until its window resets and hands you the next one. Set a reserve (e.g. 10%) and it skips any account already below that much headroom, so a session starts fresh instead of hitting a wall mid-task.

New in v0.2: automatic Claude conversation handoff

Automatic handoff is on by default — uninterrupted continuation is the point of headroom. headroom claude stays resident around an interactive Claude process. If that exact session reaches a subscription cap, headroom req

项目描述

Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.

相关仓库与替代方案

根据分类、Topic 和编程语言匹配的相似项目。

0xwilliamortiz
精选
0xwilliamortiz GitHub avatar

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI 与机器学习大语言模型
577
S40911120
精选
S40911120 GitHub avatar

recensa

Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.

AI 与机器学习大语言模型
67
7-e1even
精选
7-e1even GitHub avatar

learn-agent

A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.

AI 与机器学习大语言模型
218