Quick Summary: 📝
onWatch is an open-source CLI tool and background agent that monitors AI API quota usage across multiple providers like Synthetic, Z.ai, Anthropic, Codex, GitHub Copilot, and Antigravity in real time. It stores historical data locally in SQLite and provides a Material Design 3 web dashboard for easy visualization, ensuring all data remains on the user's machine with zero telemetry.
Key Takeaways: 💡
✅ onWatch offers real-time API quota tracking for major AI services like GitHub Copilot, Anthropic, and Codex.
✅ It provides a local, historical usage dashboard with powerful analytics, filling the gap between snapshots and deep insights.
✅ The tool is lightweight, open-source, and ensures privacy with zero telemetry; all data stays on your machine.
✅ Compatible with any tool using the supported APIs, offering broad utility for developers.
✅ Helps developers manage AI spending, optimize usage, and gain transparency into their AI tool consumption.
Project Statistics: 📊
- ⭐ Stars: 151
- 🍴 Forks: 10
- ❗ Open Issues: 2
Tech Stack: 💻
- ✅ Go
Ever found yourself wondering exactly how much you're tapping into those powerful AI APIs? Whether it's GitHub Copilot assisting your code, Claude helping with a complex problem, or other AI-powered tools, keeping track of your quota usage can feel like a guessing game. That's where onWatch steps in, and trust me, it's a game-changer for any developer leveraging AI in their workflow. This fantastic, free, and open-source CLI tool brings much-needed transparency to your AI API consumption.
onWatch's core purpose is elegantly simple: it tracks your API quota usage in real-time. It supports a wide array of popular AI services including Synthetic, Z.ai, Anthropic (think Claude Code), Codex, GitHub Copilot, and Antigravity. This means no more surprises when you hit a usage limit or wonder where your credits went. It runs as a super lightweight background agent, typically consuming less than 50 MB of RAM even when polling all six providers simultaneously, so you won't even notice it's there.
The real magic happens with its integrated web dashboard. This isn't just a static display; it's a dynamic Material Design 3 interface, complete with dark and light modes, that visualizes your historical usage data. onWatch stores all this valuable information locally in an SQLite database. This means you get comprehensive historical, per-cycle, and cross-session intelligence, filling a crucial gap between a simple current snapshot and the deep insights developers truly need to manage their AI tool usage effectively. You can see trends, identify peak usage times, and understand your consumption patterns over days, weeks, or months.
One of the most compelling aspects of onWatch is its commitment to privacy and developer freedom. It boasts zero telemetry, meaning absolutely no data leaves your machine. Everything stays local, giving you complete control and peace of mind. It's delivered as a single binary, making installation incredibly straightforward across macOS, Linux, and Windows. Furthermore, onWatch is designed to be compatible with any tool that uses the supported API keys, including popular ones like Cline, Roo Code, Kilo Code, Claude Code, Codex CLI, Cursor, and Antigravity. This broad compatibility ensures that no matter your preferred AI-powered coding environment, onWatch can provide the insights you need.
For developers, onWatch isn't just a monitoring tool; it's an empowerment tool. It helps you optimize your AI spending by giving you a clear picture of where your resources are going. It allows for better budgeting, prevents unexpected overages, and provides valuable data for making informed decisions about your AI tool stack. If you're serious about integrating AI into your development process and want to maintain control and visibility over your API usage, onWatch is an absolute must-have in your toolkit. It transforms the opaque world of AI API costs into a transparent, manageable landscape.
Learn More: 🔗
🌟 Stay Connected with GitHub Open Source!
📱 Join us on Telegram
Get daily updates on the best open-source projects
GitHub Open Source👥 Follow us on Facebook
Connect with our community and never miss a discovery
GitHub Open Source
Top comments (0)