Displays every reported usage limit
Shows the 5-hour session window, all-models weekly limit, and any per-model weekly limits Anthropic reports on your account, with new limit types appearing automatically by name if Anthropic adds them.
LimitBar
LimitBar is a macOS menu bar app for Claude Code users that shows Anthropic usage limits, including session and weekly quotas, without opening the usage wheel or running /usage. It is built for local installation, uses no model calls, and supports configurable display and warning thresholds.
What LimitBar does
LimitBar is a macOS menu bar app for Claude Code users on a Pro or Max plan. It keeps Anthropic-reported usage limits visible at all times, so you can see your remaining session and weekly capacity without opening the usage wheel or running /usage.
The app is built for quick status checks rather than interaction with the model itself. It reads Anthropic's usage metadata endpoint, updates on a configurable interval, and can show either used or remaining percentages for each limit. The source code is included, the installer compiles locally on your Mac, and the app is designed to stay lightweight and unobtrusive.
Features
Flexible display and warning colors
Lets you choose percent used or percent remaining, and color-codes limits with configurable warning thresholds, including orange past 75% used and red past 90% by default.
Detailed status menu
Provides a dropdown with exact percentages, reset times, last update time, a manual refresh control, and access to settings.
Menu bar configuration
Exposes settings from the menu bar for poll interval, color thresholds, label overrides, show/hide controls, and used-versus-remaining display.
Rate-limit resilience
Handles short outages quietly, backs off during sustained 429 responses, and keeps showing the last good values instead of going blank.
Local build and lightweight runtime
Ships with source code and a local installer that compiles on the machine, using native Swift/AppKit rather than Electron, Node, or Python.
Use cases
Track limits during active coding sessions
Useful when you want to glance at your remaining Claude session and weekly limits while planning work, instead of opening the usage wheel repeatedly.
Watch for approaching limits
Helpful if you want a menu-bar indicator that changes color as limits approach configured thresholds, making it easier to avoid surprises before a reset.
Prefer a local, inspectable installer
Fits users who prefer a locally compiled utility with source code included, so they can inspect how the app works before installing it.
Run a small background status app
Appropriate for people who want a lightweight background utility that starts at login, restores itself after crashes, and stays out of the way.
Monitor usage without model calls
Works for users who need visibility into Anthropic-reported limits but do not want to spend tokens or credits just to monitor them.
Pros and Cons
Pros
- Keeps Claude usage limits visible in the menu bar without opening the usage wheel or running /usage.
- Shows multiple limit types, including the 5-hour session window, all-models weekly limit, and per-model weekly limits.
- Offers configurable thresholds, display preferences, and menu-bar controls.
- Includes source code and compiles locally on the user's Mac.
- Uses no model calls, so it does not spend tokens or credits.
Cons
- It is unofficial and depends on Anthropic's usage endpoint, so API changes could require an update.
- It only works with Claude Code logins; plain API keys, Bedrock, and Vertex are not supported.
- It is macOS only.
FAQ
Is LimitBar an official Anthropic product?
No. LimitBar is not affiliated with, endorsed by, or made by Anthropic. It is an independent utility that works with Claude Code on macOS.
Does it spend my tokens or credits?
No. LimitBar reads Anthropic’s usage metadata endpoint, the same source used by the usage wheel and /usage. It never invokes a model, so it does not spend tokens or credits.
What does it need access to?
LimitBar uses your Claude Code CLI login from macOS Keychain. Automatic token refresh is optional at install time, and there is also a long-lived token file option if you prefer not to rely on the Keychain.
Does it work on Windows or Linux?
LimitBar is macOS only and requires macOS 13 Ventura or newer. It does not support Windows or Linux.
Can I see what it is doing?
Yes. The source code is included in the download, and the installer compiles it locally on your Mac so nothing opaque runs on your machine.
FAQ
Is LimitBar an official Anthropic product?
No. LimitBar is not affiliated with, endorsed by, or made by Anthropic. It is an independent tool that works with Claude Code usage data.
Does LimitBar spend tokens or credits?
No. It reads Anthropic's usage metadata endpoint, the same source used by the usage wheel and /usage, and it does not invoke a model.
What does LimitBar need access to?
LimitBar uses your existing Claude Code login from the macOS Keychain. Optional token auto-refresh can be enabled during installation, or you can use a long-lived token file instead.
Does LimitBar work on Windows or Linux?
No. LimitBar is macOS only and requires macOS 13 Ventura or newer.
Can I inspect what it runs on my machine?
Yes. The source code is included in the download, and the installer compiles it locally on your Mac before running it.
Quick Facts
- Product type
- macOS menu bar app
- Platform
- macOS 13 Ventura or newer
- Primary workflow
- Monitor Claude usage limits from the menu bar
- Compatible account type
- Claude Pro or Max via Claude Code
- Source domain
- mikaweiss6.gumroad.com
- Distribution
- Source code included; installer builds locally on the Mac
Quick Facts
- Category
- Developer Tool
- Platform
- macOS 13 Ventura or newer
- Primary users
- Claude Code users on Pro or Max plans
- Source domain
- mikaweiss6.gumroad.com
- Runtime
- Native Swift and AppKit
- Install flow
- Local installer or Claude Code-assisted setup
Alternatives à LimitBar
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Goldfish
Goldfish is an AI memory app for macOS that helps you reply, write, summarize, and continue using the context already on your Mac. It stores memory locally and writes in your tone.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
Biji
Biji est une plateforme polyvalente conçue pour améliorer la productivité grâce à des outils et des fonctionnalités innovants.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Ably Chat
Ably Chat is a chat API platform for building custom realtime chat applications. It supports room-based messaging, typing indicators, presence, reactions, and message updates, with usage-based pricing options for different deployment stages.