Javis603/token-monitor

Local-first desktop widget for tracking token usage, costs, limits, and session activity across 46+ AI coding tools—including Claude Code, Codex, Cursor,...

View on GitHub ↗Jump to charts ↓Open shareable report →

Javis603/token-monitor has 3k+ stars and 300+ forks on GitHub, is written in JavaScript, and was last pushed on Oct 18, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 1 minute ago
Added to GitGenius on October 13th, 2026
Created on May 19th, 2026
Open Issues & Pull Requests: 122 (+0)
GitHub issues: Enabled
Number of forks: 304
Total Stargazers: 3,184 (+1)
Total Subscribers: 6 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 13.3 hours
Mean response time: 3.6 days
90th percentile: 7.4 days
Tracked items: 345

Maintainer activity

1 person did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

About 7% of issues opened in the past year have never received a reply. 98% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "upstream" is answered fastest, typically in about 3 hours, while "tool-support" waits about 3 days. Almost all tracked open issues have seen activity in the last three months. 82% of issues opened in the past year have been closed, leaving a working backlog.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 65
New in 7 days: 31
Closed in 7 days: 30
Avg open age: 32 days
Stale 30+ days: 26
Stale 90+ days: 3

Recent activity

Opened in 7 days: 28
Closed in 7 days: 30
Comments in 7 days: 22
Events in 7 days: 53

Top labels

  • enhancement (53)
  • tool-support (28)
  • bug (24)
  • needs-info (22)
  • upstream (21)
  • windows (4)
  • macos (3)
  • performance (3)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Token Monitor is a desktop widget that tracks token usage, costs, limits, and session activity across multiple AI coding tools with multi-device synchronization.

The tool solves the problem of fragmented visibility into token consumption across dozens of AI coding assistants. Developers using multiple tools like Claude Code, Cursor, Codex, and others lack a unified view of their usage and spending. Token Monitor aggregates this data into a single dashboard, displaying real-time token counts, account limits, historical trends, and breakdowns organized by tool, device, model, session, or project. The widget runs locally on the user's machine and syncs data across devices, maintaining a local-first architecture.

The tool suits developers who actively use multiple AI coding assistants and need to monitor consumption patterns and costs in one place. It works across Windows, macOS, and Linux. Anyone adopting it should understand that it provides consolidated visibility rather than cost optimization or usage controls—it is fundamentally a monitoring and tracking solution for understanding what is being consumed and where.

The project shows consistent development activity with regular updates and maintenance. The codebase is written in JavaScript and actively maintained with releases published to support the user base. The tool has established community engagement through a dedicated Discord channel for user discussion and support.