AI & Agents
Argentic
Last updated 2026-08-21 · benchmark measured 2026-08-21 — deterministic & reproducible
A Bitcoin Lightning toll booth that lets AI agents pay per session to access the web.
Is Argentic production-ready?
Legit.Show scores Argentic 49 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Argentic (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Performance; its weakest is Discoverability. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 94/100
- Accessibility — 81/100
- Security — 25/100
- Privacy — 25/100
- Reliability — 47/100
- Standards — 70/100
- Discoverability — 0/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 163 ms to first byte.
- Returns a proper 404 for unknown routes.
- 0 of 0 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
AI agents · Machine-to-machine systems · Web automation services · AI applications
Pricing
10 satoshis per session (~$0.001 USD); one payment for 1 hour unrestricted access; no subscriptions
Visit Argentic → · Alternatives to Argentic → · How this was measured →