xiufengsun/TokenTracker

Local-first AI token usage & cost tracker for 31 coding tools incl. Claude Code, Codex, Cursor, Gemini & DeepSeek Harness—with native apps. Never reads prompts.

What it solves

TokenTracker provides a local-first way to monitor token usage and costs across a wide variety of AI coding tools. It eliminates the need for multiple accounts or API keys to track spending, offering a unified dashboard for developers who use various AI assistants and agents.

How it works

The tool operates by parsing local logs and databases (such as SQLite files or JSONL logs) from 41 different AI coding tools installed on the user's machine. It uses auto-detected hooks to sync data without requiring cloud accounts. For cost estimation, it integrates a cost engine based on LiteLLM pricing for over 2,200 models, with daily refreshes and offline snapshots for accuracy.

Who it’s for

It is designed for developers and power users of AI coding assistants who want to track their token burn, monitor costs, and visualize their activity trends across different platforms and models.

Highlights

  • Broad Compatibility: Supports 41 AI tools including Claude Code, Cursor, GitHub Copilot, and Gemini CLI.
  • Local-First Privacy: Parses logs locally; prompts and completions never leave the machine.
  • Zero Configuration: Hooks are auto-installed on the first run for a fast setup.
  • Gamified Experience: Includes a desktop pet that reacts to coding activity, 15 achievement tracks, and a global leaderboard.
  • Native Integration: Offers a macOS menu bar app, Windows system tray app, and Linux AppImage with desktop widgets for real-time usage tracking.

Related

  • 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.

  • 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
    soulduse/ai-token-monitor

    A system tray application for macOS and Windows that tracks real-time token usage and costs for AI coding tools by parsing local session logs.

  • 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
    getagentseal/codeburn

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