0xwilliamortiz
Featured
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 repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It solves a real pain point for users with multiple AI subscription accounts by providing a single-pane view of all capacity, automatic account rotation on limit hit, and fail-closed design that never routes to a possibly exhausted account.
Who it is for
- Developers who run multiple Claude or Codex subscriptions (personal + work + team)
- Power users of AI coding assistants who frequently hit usage caps
- Teams sharing a pool of AI subscriptions and need to coordinate usage
- Users who want to automate Claude Code session handoffs without manual login switching
Use cases
- Monitor remaining capacity across all Claude/Codex accounts from a single live dashboard
- Automatically rotate to the next available account when a subscription limit is reached
- Launch Claude Code on the account with the most headroom, using a reserve percentage to avoid starting near a cap
- Integrate with Claude Code via the /rotator skill or automatic handoff to continue conversations across accounts
Strengths
- Reads usage directly from provider APIs (Anthropic OAuth, Codex app-server) without consuming any tokens
- Fail-closed architecture: never routes to accounts with stale, unverified, or borderline data; always shows reason for holding
- Live dashboard with five themes, real-time updates, and zero dependency on Python packages (stdlib only)
- Automatic conversation handoff with three independent proof checks before acting, plus loop guard to prevent runaway rotation
Considerations
- Windows support is incomplete (no supervised auto-handoff, no menu-bar app; experimental tray client)
- Automatic handoff and some features are still experimental (v0.2) and have known limits documented in the repo
- Requires Python 3.9+ and the Claude/Codex CLI already installed; no central coordinator for multi-machine setups
README quick start
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)
| Midnight | Minimal |
|---|---|
| Chrome | Terminal |
|---|---|
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:
- See — every account's 5-hour, weekly, and model-scoped windows on one page, color-coded by what's left, not what's used.
- 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.
- Rotate —
headroom claudelaunches on the first account in your preference order with proven headroom. When a limit hits,headroom rotate(or the/rotatorskill 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
Description
Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.
Related repositories
Similar projects matched by category, topics, and programming language.
S40911120
Featured
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.
7-e1even
Featured
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.