# Javis603/token-monitor

Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, and OpenClaw—with multi-device sync.

Repository: https://github.com/Javis603/token-monitor
Canonical: https://ross.abutalabs.com/products/token-monitor
Homepage: http://javis-ai.com/token-monitor/
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai-tools, claude-code, codex, llm, local-first, self-hosted, token-tracker, token-usage, cursor, openclaw, opencode, ai, linux, macos, windows, hermes-agent, antigravity, deepseek, deepseek-harness, dsh
Last push: 2026-08-26T17:18:52+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 7
- inputs: {"age_days": 106, "days_push": 7, "days_rel": 7, "gap_med": 1, "n_releases_24m": 60}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1742, forks 162 (observed 2026-08-28T04:05:30.045594+00:00)

## What it is
A local-first desktop widget that tracks token usage, costs, and account limits across 32+ AI coding tools such as Claude Code, Codex, Cursor, and OpenCode by reading their local data files. It provides real-time multi-device sync, historical usage trends, and breakdowns by tool, device, model, session, or project.

## Use cases
- track token usage across claude code and codex
- monitor ai coding costs in one dashboard
- see when my claude pro or codex quota resets
- check llm api spend and balances per provider
- view token usage per model, session, or project
- sync ai usage stats across multiple machines
- get alerts before hitting ai tool rate limits

## When to choose
- you use multiple AI coding tools and want a single usage dashboard
- you want local-first tracking without sending data to a cloud service
- you need to monitor quota windows and provider balances before hitting limits
- you want historical trends and per-session token breakdowns

## When to avoid
- you need server-side or team-wide centralized usage reporting
- you use AI tools not among the supported list
- you only need a single tool's built-in usage stats
- you require a web-based or mobile-only interface

## Facets
- artifact type: application
- maturity: active
- function: monitoring, analytics, developer-tools, gui
- domain: developer-tools, large-language-models, analytics
- platform: windows
- tags: token-tracker, ai-coding-tools, local-first, usage-dashboard, cost-tracking, multi-device-sync, claude-code, codex, cursor, linux, macos, desktop

## Member repositories
- Javis603/token-monitor (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:30.045594+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 2026-08-30T03:29:54.711745+00:00, confidence not recorded.
  - readme: https://github.com/Javis603/token-monitor (fetched 2026-08-28T04:05:30.045594+00:00, sha af6758a15051)
  - homepage: http://javis-ai.com/token-monitor/ (fetched 2026-08-29T11:07:37.042457+00:00, sha 2fd7bd4f712d)
- Data as of 2026-08-30T08:39:29.467469+00:00.