Observed arrival · 2026-11-04
Omni Monitor’s local AI-spend cockpit
A planned desktop app for metering AI API calls through a local proxy, estimating subscription usage, and keeping coding-agent limits in view.
- For
- Developers and agent users managing AI API spend
- Worth noticing
- With caps enabled, requests are forwarded only when their worst-case cost can be bounded within the remaining budget.
Field notes
The page separates three kinds of readings: proxy-measured API usage, browser-derived estimates for ChatGPT, Claude, and Gemini subscriptions, and limits read locally from Codex or Claude Code sessions. It describes caps that can be monthly or scoped by provider, model, or project, along with a PIN kill switch and alerts before a limit. Screenshots are explicitly labeled simulated; macOS and Windows are listed as planned platforms, and downloads and purchases are not open.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue