English
Sign in Start free
Agent Builder Why Governance Demo Pricing Cloud Coverage Your machine Self-hosted Device Docs Blog Showcase Roadmap Enterprise NemoClaw OpenInfer GitHub
Sample data. Three synthetic sessions written for this page — not a real customer, not a real machine. The signals below are produced by the same detectors that run on your own sessions.

Inspect a sample agent session

This is the question ClawMetry exists to answer: an agent has been running for forty minutes and made a lot of tool calls — is it working, or is it stuck? Pick a session. One of these three is looping; the other two are fine, and one of those is longer than the broken one. No account, nothing to install.

Run this on your own agents. ClawMetry reads the session files your runtimes already write — no SDK, no code change. The same three sessions ship in the package, so you can land on this exact screen before you have data of your own:

pip install clawmetry && clawmetry --sample

Drop --sample to watch your real agents. OpenClaw, NVIDIA NemoClaw and Goose are free in the open-source package; the other 30 runtimes need a plan. Runtimes expose different data — the compatibility matrix records exactly what each one can and cannot show.

Cookie preferences