CUStats is a usage monitoring application designed to track Claude and OpenAI Codex consumption across multiple platforms. The primary purpose is to provide real-time visibility into AI usage limits, helping users manage their Claude 5-hour and 7-day windows plus OpenAI Codex usage without surprises.

The application offers pace prediction with smart weekly projections showing estimated end-of-week usage through color-coded indicators (Healthy/Risky/Over). It supports multiple Claude and OpenAI Codex accounts in one app, allowing seamless switching between personal and work accounts. Real-time monitoring tracks Claude's 5-hour and 7-day usage limits plus OpenAI Codex usage with color-coded progress bars that update instantly. Historical views provide Day, Week, and Month perspectives with GitHub-style activity charts to visualize usage patterns. Session insights display peak usage, average consumption, and detailed statistics for each session window.

The application works by securely connecting to user accounts through session tokens for Claude and OAuth credentials for OpenAI Codex. Users download the app from their respective app stores, enter their credentials in Settings (which are securely encrypted), and can immediately monitor usage through the menubar on macOS or mobile interface on iOS/Android. The system maintains privacy through App Sandbox implementation and AES-GCM encryption with zero telemetry.

Benefits include avoiding unexpected AI limit hits through proactive monitoring and notifications. Use cases include managing multiple AI accounts simultaneously, tracking consumption patterns over time, and receiving alerts when approaching usage thresholds. The pace prediction feature helps users forecast weekly consumption to stay within their limits.

The target audience includes developers, AI researchers, product managers, data scientists, and anyone using Claude or OpenAI Codex regularly. The application integrates with Claude through session tokens and OpenAI Codex through OAuth authentication. Technical details include native macOS and mobile experiences with local-first privacy architecture where all data remains on-device.