# 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.

Repository: https://github.com/xiufengsun/TokenTracker
Canonical: https://ross.abutalabs.com/products/tokentracker
Homepage: https://www.tokentracker.cc
Language: JavaScript
License: MIT
License Family: permissive
Topics: claude-code, cli, codex-cli, cost-tracker, cursor, gemini-cli, local-first, privacy-first, token-tracker, antigravity, ai-tools, dashboard, developer-tools, observability, ai-coding-tools, desktop-pet, desktop-widget, macos-app, usage-tracker, windows-app
Last push: 2026-08-26T12:06:31+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 10
- inputs: {"age_days": 150, "days_push": 7, "days_rel": 8, "gap_med": 0, "n_releases_24m": 170}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1429, forks 147 (observed 2026-08-28T04:04:42.258490+00:00)

## What it is
TokenTracker is a local-first, privacy-first dashboard that tracks AI token usage and cost across 34 AI coding tools like Claude Code, Codex, Cursor, and Gemini CLI. It includes a CLI installer, native macOS and Windows apps, desktop widgets, a desktop pet, and achievement tracks, all running entirely on your machine without reading prompts.

## Use cases
- track token usage and cost across AI coding tools locally
- monitor Claude Code and Codex token spend
- see per-model cost analysis for 2200+ models
- check AI subscription rate limits and quotas
- visualize AI coding activity with widgets and a desktop pet
- keep AI usage data private without cloud accounts

## When to choose
- you use multiple AI coding CLIs and want unified token/cost tracking
- you need local-only, privacy-first usage monitoring that never reads prompts
- you want native macOS/Windows apps and widgets for usage visibility

## When to avoid
- you need cloud-based team usage aggregation or billing integration
- you want to track AI usage in tools outside its supported list
- you need prompt or conversation content analysis

## Facets
- artifact type: application
- maturity: active
- function: monitoring, analytics, cli, developer-tools, data-visualization
- domain: developer-tools, analytics, privacy
- platform: windows, cli, cross-platform
- tags: token-tracker, cost-tracking, local-first, privacy-first, ai-coding-tools, claude-code, codex-cli, cursor, gemini-cli, desktop-pet, desktop-widgets, usage-dashboard, observability, command-line, macos, linux, nodejs

## Member repositories
- xiufengsun/TokenTracker (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:42.258490+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:37:17.445442+00:00, confidence not recorded.
  - readme: https://github.com/xiufengsun/TokenTracker (fetched 2026-08-28T04:04:42.258490+00:00, sha 29ad47e8214e)
  - homepage: https://www.tokentracker.cc (fetched 2026-08-29T11:49:04.233476+00:00, sha 63ff62367eff)
- Data as of 2026-08-30T08:39:29.467469+00:00.