akitaonrails/ai-usagebar

What it solves

ai-usagebar provides a centralized way to monitor usage quotas and credit balances across a wide variety of AI coding services and LLM providers (such as Claude, ChatGPT, GitHub Copilot, DeepSeek, and others) directly from your desktop environment. It eliminates the need to manually check multiple provider dashboards to see how many credits or tokens you have left before hitting a limit.

How it works

The tool acts as a monitoring layer that fetches usage data from various provider APIs or by reading local authentication files created by official CLIs. It offers multiple frontend integrations to display this data:

• System Widgets: Native panels for Omarchy Quattro, Waybar modules for Wayland, and a system-tray popover for Windows.
• TUI: A tabbed Terminal User Interface (ai-usagebar-tui) for a compact provider overview.
• Desktop Integrations: Support for GNOME Shell, KDE Plasma 6, and macOS.

It uses atomic caches and file locking to prevent redundant network requests and implements rate-limiting logic (e.g., waiting five minutes after an HTTP 429 error) to avoid being blocked by providers.

Who it’s for

Developers and power users who utilize multiple AI coding assistants or LLM APIs and want a real-time, glanceable view of their remaining quotas, reset timers, and spending without leaving their workflow.

Highlights

• Broad Provider Support: Integrates with Claude, Codex, GitHub Copilot, Z.AI, OpenRouter, DeepSeek, DeepInfra, Kimi, Nous Research, and many more.
• Multi-Platform: Available for Linux (Nix, Arch, etc.), macOS, and Windows.
• Flexible Display: Supports Waybar, Omarchy Quattro, a TUI, and a Windows system tray.
• Smart Notifications: Sends desktop alerts when quotas cross a configurable threshold (e.g., 97%).
• Credential Reuse: Leverages existing OAuth tokens from official CLIs (like claude, gh, or codex) to avoid redundant logins.