bounce12340 GitHub avatar

ai-usage-monitor

bounce12340

A Windows desktop widget that displays real-time AI coding quotas from Claude Code, Codex CLI, and Ollama, with color warnings before rate limits are hit.

Stars

6

7-day growth

No data

Forks

1

Open issues

0

License

MIT

Last updated

2026-07-27

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides live, always-on-top visibility into official usage quotas that are normally hidden behind command-line commands, using purely local data and vendor APIs without telemetry.

Who it is for

  • Developers using Claude Code CLI
  • Developers using Codex CLI
  • Ollama users tracking local and cloud usage

Use cases

  • Monitor remaining Claude Code session and weekly quotas to avoid mid-task interruptions
  • Track Codex account usage and credits without opening the dashboard
  • Keep an eye on Ollama local model VRAM and request counts in real time
  • Estimate API-equivalent cost of Claude Code usage for budget awareness

Strengths

  • Displays the same official quota numbers as Claude Code's /usage and Codex's account dashboard, refreshed live
  • Lightweight: background thread collection, incremental log parsing, near-zero idle CPU
  • Mini bar mode collapses all data into a single pill for minimal desktop footprint
  • Privacy-focused: all data read locally, OAuth tokens only sent to official vendor endpoints

Considerations

  • Windows-only (tested on Windows 11); no macOS or Linux support mentioned
  • Relies on undocumented endpoints from Anthropic and Codex that may change without notice (graceful fallback to local logs)
  • Requires manual configuration of pricing rates for the cost estimate; some features depend on browser cookies for Ollama Cloud

README quick start

Quick start (from source)

Description

Always-on-top desktop widget showing your real Claude Code & Codex usage quotas (5-hour / weekly windows) live on screen. Windows, PySide6.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482