Meterbility image

Meterbility

The debugger for AI agents

Meterbility product image

Overview

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.

Weekly digest

Discover launches like Meterbility every week

One short email with the week's newest SaaS launches, hand-curated. Be first to the next great tool.

One email a week. New launches only. Unsubscribe anytime.