logo

steipete/CodexBar

Show usage stats for OpenAI Codex and Claude Code, without having to login.

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

steipete/CodexBar has 22k+ stars and 2k+ forks on GitHub, is written in Swift, and was last pushed on Oct 15, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 36 minutes ago
Type:ApplicationCategory(s):AI Coding AgentsAI Agents & LLM Apps
Added to GitGenius on February 1st, 2026
Created on November 16th, 2025
Open Issues & Pull Requests: 59 (+1)
GitHub issues: Enabled
Number of forks: 2,113
Total Stargazers: 22,502 (+12)
Total Subscribers: 58 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 13.0 hours
Mean response time: 6.3 days
90th percentile: 17.1 days
Tracked items: 1,444

Most active contributors

Sign in to see contributor activity.
Sign in

Related repositories by overlapping contributors

Maintainer activity

2 people 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 11, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits.

How this project is maintained

Practically every issue opened in the past year has drawn a reply. 97% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "P2" is answered fastest, typically in about 11 hours, while "issue-rating: 🌊 off-meta tidepool" waits about 2 days. 98% of issues opened in the past year have since been closed. Three people close 90% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 36
New in 7 days: 64
Closed in 7 days: 53
Avg open age: 16 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 45
Closed in 7 days: 47
Comments in 7 days: 127
Events in 7 days: 542

Top labels

  • clawsweeper:no-new-fix-pr (613)
  • clawsweeper:needs-maintainer-review (512)
  • P2 (495)
  • clawsweeper:needs-product-decision (416)
  • clawsweeper:source-repro (327)
  • issue-rating: 🦞 diamond lobster (327)
  • impact:ux-friction (317)
  • P3 (287)

Most active issues this week

Sign in to see which issues are moving.
Sign in
Explore full issue details

Detailed Description

CodexBar is a macOS menu bar utility that displays usage limits and reset windows for AI coding providers without requiring login.

The tool solves the problem of tracking rate limits and quota resets across multiple AI coding services by consolidating them into a single menu bar interface. It monitors session, weekly, and monthly reset windows for providers including OpenAI Codex, Claude, Cursor, Gemini, Copilot, and many others, showing countdowns to the next reset. The approach reuses existing authentication methods—OAuth, device flow, API keys, browser cookies, and local files—rather than storing passwords, making it privacy-first. It displays credit balances, spending information, and cost estimates where available, and surfaces provider status incidents through badge indicators.

Developers managing multiple AI coding tools should choose this tool if they want to avoid guessing whether they have quota remaining before starting long tasks. It suits anyone actively using several coding AI providers and wanting consolidated visibility without a separate login flow. The tool runs with no Dock icon and minimal UI overhead, offering either individual status items per provider or a merged icon mode with a provider switcher. Installation requires macOS 14 or later and is available through GitHub releases, Homebrew, or CLI tarballs for macOS and Linux.

The project maintains a substantial base of real-world adopters, with almost all open issues raised by outside users rather than the core team. Maintainers typically respond to new issues and pull requests within a day.