Compared

ccusage alternative: the window, not the spend

CrewTower is a ccusage alternative for the question that matters mid-task: how much of your Claude Code or Codex window is left, and when it resets. It keeps that on screen in the notch, read from the provider's own figure, next to the sessions that are waiting on you. ccusage answers a different question, what your agents spent, from the session files on disk.

ccusage's side checked on its own site and repository on 19 October 2026. Sources.

What CrewTower does differently: where the number comes from

ccusage builds Claude Code's 5-hour blocks from the project logs on your disk: a block starts with your first message and lasts five hours, and the limit it measures against is one you set, or your highest previous block. That is accurate for counting tokens, because the tokens are in the logs. It is a weaker basis for how close am I to being cut off, because your plan's limits live with your provider, and work from another machine or from claude.ai is not in those logs.

CrewTower answers that second question from the source. For Claude Code it calls Anthropic's usage endpoint with the login Claude Code already uses, about every five minutes, so the percentage in your notch is Anthropic's own figure rather than a reconstruction. For Codex it reads Codex's own rate limit reporting. Each window shows the percentage used and a countdown to the reset.

The usage meter is optional. It is on by default and can be switched off in settings, and it is one of only three things in the app that make a network request at all. The privacy page lists all three, including exactly which credential is read and which URL is called.

The other half of CrewTower

The usage strip is one line at the bottom of the panel. The rest of CrewTower is about a different problem: an agent runs unattended until it needs a human, and then it stops in a terminal tab you are not looking at.

CrewTower brings that moment into the notch with the command on the card, and you approve, deny or answer from there. The agent's hook is blocking on a local socket and your decision travels back down it, so the prompt resolves in place without your terminal coming forward. When you do want to be in the terminal, Jump lands on the exact tab or split pane.

If you searched for a ccusage alternative because you keep discovering, twenty minutes late, that something was waiting on you, CrewTower is built for exactly that.

CrewTower vs ccusage

The questionCrewTowerccusage
How much of my window is left?Claude Code's session and weekly windows and Codex's windows, each read from the provider's own reportingClaude Code's 5-hour blocks, rebuilt from local logs
While I workA strip in the notch, always on screenA command you run; the blocks --live monitor was removed in version 18, and statusline feeds Claude Code's status line
Which sessions need me right now?Yes, and you answer them from thereNot published
What did I spend?NoYes, by day, week, month and session
How many tokens, what cost?No history; with the beta Tell Claude plugin, the current Claude Code session's cost so farYes
Which agents?Usage for Claude Code and Codex18, Claude Code and Codex among them
Runs onmacOS 15 or laterAny system, from the command line
Cost$9.99 onceFree, open source

The rows ccusage wins, and what CrewTower does there

Spend. ccusage reports what you spent, by day, week, month and session, with the models you used and Claude Code's 5-hour blocks; CrewTower shows how much of the window is left and, with the beta Tell Claude plugin on, what the current Claude Code session has cost so far.

Agents. ccusage reads eighteen agents' logs; CrewTower's usage meter covers Claude Code and Codex, and its notch shows every session of twenty-six agents.

Price and platforms. ccusage is free under the MIT license and runs from npx on any system with a terminal; CrewTower is a native Mac app, $9.99 once, that keeps the window on screen with no terminal open.

Your own tools. ccusage prints JSON for scripts and, with ccusage statusline, feeds Claude Code's own status line; CrewTower puts the window in the notch, always in view.

Running both

Nothing conflicts. ccusage is a command you run when you want the breakdown; CrewTower watches sessions, answers prompts over the hook socket and keeps the window on screen. Plenty of people keep both, and the honest reason is that neither one answers the other's question.

Which one to pick

CrewTower if the question is how much is left and which session is waiting on you.

ccusage if the question is what you spent, on which project and which model.

Nine meters and spend reports for Claude Code are side by side in the usage monitors compared.

Questions

Is there a ccusage for Codex?

For how much of your Codex window is left, CrewTower reads Codex's own rate limit reporting and keeps each window Codex reports in the notch, Codex full resets included. For what was spent, ccusage itself now reads Codex's local logs as well as Claude Code's (checked October 2026).

Sources

Read on 19 October 2026: github.com/ccusage/ccusage for the reports, the eighteen sources, the MIT license and the release (20.0.37, 19 October 2026); ccusage.com/guide/claude for the local logs; the blocks guide for the 5-hour blocks and their limit; the live monitoring page for its removal in version 18; the statusline guide; the JSON output guide.

The window, and the sessions waiting on you

CrewTower puts both in the notch. No token or cost history, by design.

Get CrewTower for Mac

Free for 3 days, no card · then $9.99 once · macOS 15 or later