Compared

ccusage alternative: the window, not the spend

ccusage reads the session files your agent leaves on disk and tells you what you spent. Noveriq tells you how much of your subscription window is left, in the notch, without running anything. Those sound like the same feature and they are not, so this page draws the line before you buy the wrong one.

The short version

The questionccusageNoveriq
What did I spend?Yes, by day, session and modelNo
How many tokens, what cost?YesNo
How much of my window is left?Estimated from local filesRead from the provider's own endpoint
Where does it live?A command you runA strip in the notch, always on screen
Which sessions need me right now?NoYes, and you answer them from there
CostFree, open source$9.99 once

What ccusage does well

Coding agents write their own session records to disk as they work. ccusage reads those records and reports them back: what each day cost, which session was expensive, which model you actually used. Nothing leaves your machine and there is no account involved.

If you are trying to work out where the money went, that is the tool, and Noveriq is not a substitute for it. Noveriq counts no tokens, reports no dollar figure, and keeps no history at all.

Where the numbers come from, and why it matters

Any tool that reads local session files is reconstructing your usage from the trail your agent left. That is accurate for counting tokens, because the tokens are in the trail. It is a weaker basis for answering how close am I to being cut off, because your plan's limits live with your provider, not on your disk.

Noveriq answers that second question from the source. For Claude Code it calls Anthropic's own usage endpoint with the login Claude Code already uses, so the percentage in your notch is the figure Anthropic itself holds. For Codex it reads the Codex CLI's own rate limit reporting. The session window and the weekly window both show a percentage used and a countdown to 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 Noveriq

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

Noveriq 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 ever coming forward. A destructive shell command is flagged before you press. 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 wanted a spend report in a nicer wrapper, that is not this. If you searched because you keep discovering, twenty minutes late, that something was waiting on you, that is exactly this.

Running both

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

The window, and the sessions waiting on you

Noveriq puts both in the notch. No token counts, no cost report, by design.

Get Noveriq for Mac

$9.99 once · macOS 15 or later · 30 days, money back