Skip to content
HomeNewsConceptsGuidesToolbox
AboutSubscribeUA
Subscribe

AI Today Brief

The daily AI-engineering brief. Built in public. EN · UA.

XTelegramLinkedInYouTubeRSS

Follow AI Today Brief on LinkedIn for daily AI-engineering updates and the weekly “5 shifts that changed how developers work” PDF.

Explore

NewsDigestsConceptsGuides

Company

SubscribeAdvertiseAbout

Legal

Editorial policyAI disclosurePrivacyTerms

© 2026 AI Today Brief. All rights reserved.

  1. Home/
  2. News/
  3. Token & cost optimization/
  4. AI Usage Monitor Tracks Claude Code and ChatGPT Limits in macOS Menu Bar
Token & cost optimization

AI Usage Monitor Tracks Claude Code and ChatGPT Limits in macOS Menu Bar

AI Usage Monitor is an open-source macOS menu bar utility that displays live usage percentages and reset countdowns for Claude Code and Codex CLI. It prevents unexpected workflow interruptions by alerting developers when usage reaches 90%.

August 20, 2026· 4 min read
OKCurated by Oleksandr Kuzmenko, AI Product Engineer·Updated August 20, 2026·Sources cited on every story
AI-assisted · editor-reviewed·How we use AI
AI Usage Monitor Tracks Claude Code and ChatGPT Limits in macOS Menu Bar

Impact: Medium

Why it matters

Developers can monitor 5-hour session buckets, weekly caps, and credit balances directly from their menu bar without manually running status commands in the terminal.

TL;DR

  • 01Install AI Usage Monitor on macOS to track Claude Code and Codex limits in real time.
  • 02Get notified at 90% usage threshold to manage session switching before hitting hard caps.

Key facts

10 minutesDefault Refresh Interval
90%Default Alert Threshold
Apache-2.0License
Platform
macOS
Supported Tools
Claude Code, ChatGPT, Codex CLI
Default Refresh Interval
10 minutes
Default Alert Threshold
90%
License
Apache-2.0

Real-Time Monitoring for Agentic IDEs

Developers relying on Claude Code and Codex CLI frequently hit rate limits mid-task. ai-usage-monitor brings status awareness directly to the macOS menu bar, rendering /usage and /status metrics continuously.

Authentication and Data Privacy

The app requires no external API keys or login screens. It leverages existing local credentials:

  • Claude Code: Reads Claude Code-credentials from macOS Keychain.
  • ChatGPT / Codex: Reads ~/.codex/auth.json or custom CODEX_HOME paths.

Metric Tracking and Threshold Alerts

The menu bar displays live usage percentages and countdowns to the next reset window. Key monitored metrics include:

  • Claude Code 5-hour session window and 7-day weekly bucket.
  • Per-model weekly quotas and pay-as-you-go spend limits.
  • ChatGPT primary/secondary rate-limit windows and code review quotas.
  • Automated desktop notifications when any usage bucket crosses the 90% threshold.

Try it in 2 minutes

git clone https://github.com/stavrop/ai-usage-monitor.git && cd ai-usage-monitor && ./build.sh

bash

✓ When to use

  • Monitoring Claude Code and Codex usage limits on macOS
  • Preventing unexpected rate-limit pauses during vibe-coding sessions

✕ When NOT to use

  • Linux or Windows operating systems
  • Setups using only raw API keys without Claude Code or Codex desktop logins

What to do today

  • →Download AI Usage Monitor binary or build from source.
  • →Grant Keychain read permission on first launch for Claude Code tracking.
#Claude Code#ChatGPT#Codex#macOS

Sources

  • ai-usage-monitor Repository
ShareShare on XShare on LinkedIn
← Previous storyClaude Code Feature Request Urges Adoption of Universal AGENTS.md StandardNext story →Google Search Integrates Generative UI, Notebooks, and Custom Document Generation

Related stories

  • Token & cost optimizationSemiAnalysis AgentX Benchmarks Real-World Agentic AI Token Consumption and Serving Efficiency
  • Token & cost optimizationOpenAI Cuts GPT-5.6 Sol API and Codex Credit Pricing by 20%
  • Token & cost optimizationNative Bedrock Codex missing explicit prompt cache controls causes high write spend
  • Token & cost optimizationHugging Face Reveals Benchmark Overfitting and Fake Transcripts in Top Speech Models

Email digest

Get the morning AI brief

One email a day — the stories that matter for engineers, founders and tech leads. Human-edited, with links to primary sources.

  • ✓120+ sources scanned daily
  • ✓Edited by a human
  • ✓1 email per day
  • ✓EN + UA

By subscribing you agree to the privacy policy.