Introduction

What is ccpool?

Anthropic tells you the account is at 60%. ccpool tells you who got it there.

When a group shares one Claude subscription (Pro or Max), everyone collides on the same limits: someone burns the 5-hour window by noon, someone quietly eats the weekly cap, and nobody finds out until it’s gone. ccpool gives the group a live, shared view of the account’s usage broken down by person, so fair use becomes something you can see and negotiate instead of guess at.

It runs as a terminal dashboard (ccpool tui), a one-shot snapshot (ccpool status), and a Claude Code statusline (ccpool statusline).

What you get

• Live usage bars for all three limits — the 5-hour window, the weekly cap, and the weekly Opus cap — with a countdown to each reset. These are pulled from Anthropic’s own usage endpoint, so they match what the account actually enforces.
• A per-person breakdown — each member’s share of each limit, their token count, and whether they’re coding right now.
• A Claude Code statusline, so you can watch the shared limits without leaving your editor.

Usage that ccpool can’t tie to a person (someone using claude.ai in the browser, for example) shows up as unknown.

How it works

Everyone in the group runs ccpool on their own machine and joins one shared ledger. A small background daemon on each machine checks Anthropic’s usage endpoint for the account-wide limits, watches your local Claude Code activity to figure out which part of that usage is yours, and writes both to the ledger under your name. Put everyone’s entries together and you get one set of account-wide bars, split by person.

The ledger lives on a ccpool server. By default that’s the hosted one, so there’s nothing to deploy — but the server is open source and a group can run its own.

For the full pipeline — how the tank is polled, how the per-person split is reconstructed, and how the server stays cheap — see How it works.

What ccpool is (and isn’t)

ccpool observes and reports. It is a read-only observer plus a shared ledger:

• It never proxies your requests and never sits in the request path.
• It never touches your login — it reads the token Claude Code already saved and the transcripts already on your disk.
• It only counts activity from the moment you start the daemon, not your history.
• It has no budgets or quotas and can’t raise your limits or block anyone. It makes the sharing visible and leaves fair use to the group.

Ready to set it up? Head to Installation.