soulduse/ai-token-monitor

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

What it solves

AI Token Monitor provides a way for developers to track the actual cost and token usage of various AI coding tools (like Claude Code, Codex, and OpenCode) in real-time. It eliminates the need for manual calculations or API key proxies by reading local session logs that these tools already generate.

How it works

The application runs as a lightweight system tray app for macOS and Windows. It uses a Rust-based engine to watch local JSONL session logs, parse the data, and apply per-model pricing (including cache reads) locally on the user's machine. It then displays the current spend in the menu bar and provides a detailed dashboard with analytics and charts.

Who it’s for

Developers who use AI-powered CLI coding agents and want to monitor their spending, track usage trends, and stay within their plan limits without compromising privacy.

Highlights

  • Zero Setup: Works immediately by reading existing local logs without requiring API keys or proxies.
  • Real-time Tracking: Displays today's cost directly in the system tray/menu bar.
  • Detailed Analytics: Includes 7/30-day charts, GitHub-style activity heatmaps, and model breakdown visualizations.
  • 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.
  • Broad Tool Support: Compatible with a wide range of AI tools including Claude Code, Codex, OpenCode, Gemini CLI, Grok, and others.

Related

  • Project
    Javis603/token-monitor

    A desktop widget that provides a live, synced dashboard for tracking token usage, costs, and account limits across 43+ AI coding tools.

  • Project
    xiufengsun/TokenTracker

    A local-first token usage and cost dashboard for 41 AI coding tools that tracks token burn and costs without requiring API keys or cloud accounts.

  • Project
    getagentseal/codeburn

    A tool for developers to track and optimize AI coding spend by analyzing local session files from over 40 AI coding agents.

  • Project
    VasiHemanth/tokentelemetry

    A local observability dashboard that tracks token usage, LLM costs, and session traces for AI coding and autonomous agents by reading local log files.

  • Project
    stormzhang/token-tracker

    Token Tracker (tt) is a Python‑based CLI tool that reads local logs from Claude Code, Codex, and Kimi Code, aggregates token usage, estimates cost, and displays the data via status‑line widgets, a live sidebar pane, and daily/weekly/monthly reports. It works entirely locally, offers theme support, and includes setup/uninstall commands.