Tokentracker
Tokentracker tracks token usage across 22 AI coding tools (Claude Code, Codex, Cursor, Gemini, Roo Code, Zed Agent, Goose, and more) — local-first, zero-config, with a beautiful dashboard, native macOS menu bar app, and 4 desktop widgets.
Last verified:
What is Tokentracker?
Tokentracker is a free, open-source, local-first dashboard that automatically tracks token usage across 13 AI coding agent CLIs in one place. It supports Claude Code, Codex CLI, Cursor IDE, Gemini CLI, OpenCode, OpenClaw, Every Code, Kiro, Hermes Agent, GitHub Copilot, Kimi Code, oh-my-pi (omp), and CodeBuddy. The tool focuses on minimal data collection, auditable metrics, and clear visibility into model and project usage, tracking only token counts — never prompts or conversation content.
Key features include a unified usage dashboard showing input, output, cached, and cache-creation tokens across all 13 AI coding tools; cost analysis with per-model pricing breakdown across 70+ models; usage limits view with live rate-limit and subscription status for Claude Pro, ChatGPT plans, Cursor, Gemini, Kiro, and Antigravity; project attribution to see which repository consumed which tokens; activity heatmap and trend charts with GitHub-style contribution calendar; skills browser for discovering agent skills; and a macOS menu bar app with desktop widgets for at-a-glance usage.
Tokentracker is built for developers, founders, and engineering teams who rely on multiple AI coding assistants and need a single place to understand token consumption. Instead of checking each tool separately, users can compare usage trends by model, project, and time window in one dashboard. Teams use it to answer practical questions like which model is consuming the most budget, whether a new workflow increases cost, how a Pro plan is tracking against rate limits, and how token usage shifts over days or weeks.
Tokentracker pricing
Pricing model: Freemium
Token Tracker is completely free and open-source. There are no paid plans or subscription tiers. The tool is available as an npm package (tokentracker-cli) via npx tokentracker-cli, and macOS users can install the native menu bar app via brew install --cask mm7894215/tokentracker/tokentracker. Source code is available on GitHub at github.com/mm7894215/TokenTracker. Cloud sync is optional and only powers the public leaderboard — all core functionality works entirely offline with no account required.
Tokentracker pros
- Free and open-source with no paid plans
- Supports 13 AI coding agent CLIs out of the box
- Local-first design — data stays on your machine
- Privacy by design — never collects prompts or conversations
- Zero manual configuration — auto-detects AI tools
- Install in one command with npx tokentracker-cli
- Unified dashboard for all token usage in one place
- Cost analysis across 70+ models with per-model pricing
- Live rate-limit and subscription status tracking
- Project attribution shows which repo used tokens
- GitHub-style activity heatmap and trend charts
- macOS menu bar app available via Homebrew
- Desktop widgets for at-a-glance usage monitoring
- Works entirely offline without cloud account
- Tracks input, output, cached, and cache-creation tokens
Tokentracker cons
- Only supports 13 specific AI coding CLIs
- macOS menu bar app only available for macOS
- Cloud sync is optional and only for public leaderboard
- Dashboard runs on localhost requiring local access
- No mobile app for iOS or Android
- No built-in team collaboration features
- No alerting or notification system for usage limits
- Cost analysis requires manual pricing setup for some models
Frequently asked questions about Tokentracker
How do I install Token Tracker?
Run npx tokentracker-cli. The CLI auto-detects your AI coding tools, installs the appropriate hooks (SessionEnd hooks, TOML notify arrays, plugins, or passive log readers depending on the tool), and opens the dashboard at http://localhost:7680.
Which AI coding CLIs does Token Tracker support?
Token Tracker supports 13 AI coding agent CLIs: Claude Code, Codex CLI, Cursor IDE, Gemini CLI, OpenCode, OpenClaw, Every Code, Kiro, Hermes Agent, GitHub Copilot, Kimi Code, oh-my-pi (omp), and CodeBuddy.
Is Token Tracker free and open source?
Yes. Token Tracker is free and open-source. The source code is available on GitHub at github.com/mm7894215/TokenTracker, and the npm package is called tokentracker-cli.
Does Token Tracker collect my prompts or conversations?
No. Only token counts, model names, timestamps, and project attribution are recorded. Prompts and completions are never read or uploaded, ensuring privacy by design.
What does Token Tracker track?
Token Tracker tracks input, output, cached, and cache-creation tokens per model, project, and time window. It also surfaces rate limits and subscription status for Claude Pro, ChatGPT plans, Cursor, Gemini, Kiro, and Antigravity.
Does Token Tracker work offline?
Yes. Token Tracker is local-first. All parsing, aggregation, and dashboard rendering happen on your machine. Cloud sync is optional and powers only the public leaderboard.
How does Token Tracker collect usage data from different tools?
Each supported tool emits usage data when a session ends. Token Tracker's parser normalizes 9 distinct log formats into a unified schema using half-hour UTC buckets keyed by source, model, and hour_start. Integration methods include SessionEnd hooks, TOML notify arrays, plugins, SQLite readers, and passive JSONL log readers depending on the tool.
Can I use Token Tracker on Windows or Linux?
Yes, the CLI works on Windows, macOS, and Linux via npx tokentracker-cli. However, the native menu bar app is only available for macOS via brew install --cask mm7894215/tokentracker/tokentracker.
What views and features are available in the dashboard?
The dashboard at http://localhost:7680 includes: unified usage dashboard, cost analysis, usage limits view, project attribution, activity heatmap and trend charts, skills browser, and macOS menu bar app and desktop widget previews. None require an account.
Who should use Token Tracker?
Token Tracker is built for developers, founders, and engineering teams who rely on multiple AI coding assistants and need a single place to understand token consumption. It helps teams answer practical questions about budget usage, workflow costs, rate limit tracking, and usage trends over time.