Claude FinOps

Claude FinOps is a local dashboard for your own Claude Code usage. It reads the transcripts Claude Code has already written on your machine and answers, in a few clicks:

What I used → what it cost → why it cost that much → whether it was efficient → what is likely to happen next → and what I should change.

npx claude-finops

One command, with no API key, no account and no config file. It runs on 127.0.0.1 using only the Python standard library, and your data stays on your machine.

What it gives you

⚡ Act now

One-click fixes on the overview: compact a heavy session, turn a repeated command into a skill, move a repeated instruction into CLAUDE.md.

Context hygiene

Shows how much of your spend happened at large context sizes, which is the biggest driver of most Claude Code bills.

Why so many tokens?

Explains where your tokens went and gives you a prompt to paste back into Claude Code.

Drill-down & Resume

Project → session → prompt, with Resume on every session row and Compact on running ones.

Waste & anomalies

Seven waste rules and anomaly detection, each showing the exact prompts or sessions it flagged.

Peak hours & plan limits

A weekday × hour heatmap in your local time, and your 5-hour and weekly plan-limit history.

Forecast & budgets

Conservative, expected and high forecasts, compared against budgets you set.

Claude desktop too

Also reads the Claude desktop app’s Cowork sessions when it is installed.

Where to go next

Getting startedRun it in 60 seconds.

Feature tourEvery view, explained.

Accuracy contractWhat is measured, what is estimated.

What's newAct now, peak hours, Cowork sessions and more.