soulduse/ai-token-monitor

macOS menu bar app for tracking Claude Code token usage and costs

What it solves

AI Token Monitor addresses the lack of visibility into the actual costs and token usage of various AI coding tools. Many AI CLIs and agents write local logs, but they don't provide a real-time, aggregated view of spending across different providers, making it difficult for developers to track budgets or avoid hitting plan limits.

How it works

The application is a lightweight system tray app built with Tauri (Rust) and React. It works by monitoring local session logs (JSONL files) generated by AI tools like Claude Code, Codex, OpenCode, Grok, and others. A Rust-based engine parses these logs, deduplicates entries, and applies per-model pricing (including cache reads) locally on the user's machine. This data is then visualized in a dashboard and a real-time cost ticker in the macOS menu bar or Windows system tray.

Who it’s for

It is designed for developers who use multiple AI coding assistants and want to track their daily, weekly, and monthly spending, monitor their token usage ratios, and stay within their plan limits without needing to actually configure API keys or proxies.

Highlights

  • Zero Setup: Automatically detects and reads local logs from supported AI tools without requiring API keys.
  • Real-time Tracking: Displays current daily spend directly in the system tray/menu bar.
  • Budget Alerts: Provides live session and weekly plan limit bars, with optional notifications via Discord, Slack, or Telegram.
  • Privacy-First: Operates 100% offline by default; social features like the leaderboard and chat are strictly opt-in.
  • Detailed Analytics: Includes activity heatmaps, model breakdown charts, and cache efficiency visualizations.
  • Social Integration: Opt-in leaderboard to compare usage with other developers and a community chat with AI-powered translation.

Related

  • Project
    stormzhang/token-tracker

    A local token consumption and cost tracking tool for AI agents like Claude Code, Codex, and Kimi Code, featuring real-time status bars and detailed usage reports.

  • Project
    xiufengsun/TokenTracker

    A local-first token usage and cost dashboard for 31 AI coding tools, featuring a desktop pet and native widgets for real-time monitoring.

  • Project
    getagentseal/codeburn

    A local-first tool that tracks AI coding token usage and costs across 40 tools and agents, providing detailed breakdowns by task, project, and model to help developers reduce waste.

  • Project
    junhoyeo/tokscale

    A high-performance CLI tool and visualization dashboard for tracking token usage and costs across multiple AI coding agents.

  • Project
    Javis603/token-monitor

    A desktop widget that provides a live, multi-device synced dashboard for tracking token usage, costs, and account limits across 32+ AI coding tools.