Get the weekly radar
One short email with the freshest products, every week.
Grounded in available product and source data
Meterbility gives developers X-ray vision into AI agent runs. It captures every step from Claude Code, Codex, Cursor, or any custom agent, then lets you inspect the exact context each model call saw. You can track token costs per step, compare two runs to see where they diverged, and fork a run from any step to test what-if changes. A Live Probe lets you pause a running agent, inject a message, and resume it. It is local-first and open source, so your traces never leave your machine.
