Developer Tools
agent-inspect
Last updated 2026-08-05 · benchmark measured 2026-08-05 — deterministic & reproducible
TypeScript tool for debugging and regression-testing AI agents from local execution traces.
79/100
Legit Benchmark — the simple average of 7 measured frames. Frames we could not measure are left out of the average, never counted as zero. Every frame is shown below with its evidence.
Is agent-inspect production-ready?
Legit.Show scores agent-inspect 79 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on agent-inspect (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Performance; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 100/100
- Accessibility — 93/100
- Security — 45/100
- Privacy — 25/100
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 100/100
What we measured
- Security headers present: HSTS.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 134 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
TypeScript developers · AI agent builders · Platform teams · QA engineers · LangGraph users