# Mr. Usage documentation

Learn how to track Claude Code, Codex and OpenCode usage on macOS: installation, plan limits, token accounting, estimated API costs and privacy.

Source: https://usage.beffa.xyz/docs

## An AI usage tracker for your Mac’s menu bar

Mr. Usage is a free, open-source macOS menu bar app for people working with Claude and OpenAI. It puts plan limits, reset countdowns, token counts and estimated API-equivalent costs in a small desktop panel, so you can check usage without leaving your coding workflow.

It supports Claude Code, Codex and OpenCode. The app reuses existing provider logins rather than asking you to create a separate Mr. Usage account. It runs on macOS 13 or later, with downloads for Apple Silicon and Intel Macs.

Use the Limits tab to understand your remaining plan allowance and the Tokens tab to explore activity and model breakdowns. Optional community sharing is separate from local tracking and is off by default.



## Choose a guide

Start with installation if you are new to the app. The provider guides explain exactly where usage comes from and which activity is covered. The cost guide explains why token counts, API-equivalent value, subscription fees and credit balances are different measurements. The privacy guide describes local data access and optional public sharing.

- Getting started: download, existing logins, first usage and automatic updates.
- Claude usage: Claude Code limits, local transcripts and OpenCode activity.
- OpenAI usage: Codex limits, credits, This Mac and All devices.
- Tokens and costs: cached context, reasoning output and API estimates.
- Privacy and sharing: what stays local, what is public and how to opt out.

## When a menu bar tracker is useful

If you switch between Claude Code and Codex, separate provider dashboards can make it difficult to see when an allowance will reset or which model accounts for your token activity. Mr. Usage gives those measurements a consistent place on your Mac while preserving the distinction between provider-reported limits and locally counted tokens.

It is a monitoring tool, not a billing authority or a way to increase your subscription limits. Large token totals are not evidence of productivity, and API-equivalent values are not verified savings. Provider dashboards and invoices remain the source of truth for allowances and charges.



## Related documentation

- [Install and set up Mr. Usage on macOS](https://usage.beffa.xyz/docs/getting-started)
- [Track Claude Code usage, limits and tokens on macOS](https://usage.beffa.xyz/docs/claude-usage)
- [Track Codex and OpenAI usage across devices](https://usage.beffa.xyz/docs/openai-usage)
- [AI token counts, cached input and API cost estimates](https://usage.beffa.xyz/docs/tokens-and-costs)
- [Mr. Usage privacy and optional leaderboard sharing](https://usage.beffa.xyz/docs/privacy-and-sharing)

[App source and releases](https://github.com/t1llo/mr-usage)