AI & Agents

Ferrow

Last updated 2026-08-17 · benchmark measured 2026-08-17 — deterministic & reproducible

Ferrow is a local-first AI hub with optional hosted relay and managed model access.

Is Ferrow production-ready?

Legit.Show scores Ferrow 94 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Ferrow (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 99/100
• Accessibility — 100/100
• Security — 80/100
• Privacy — 100/100
• Reliability — 100/100
• Standards — 94/100
• Discoverability — 85/100

What we measured

• Security headers present: CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
• No HSTS.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 86 ms to first byte.
• Returns a proper 404 for unknown routes.
• 3 of 3 sampled routes reachable.
• Has a reachable privacy policy.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

developers · knowledge workers · AI users · teams · individuals

Pricing

Free locally; $20/month (Private plan) or $20/month + usage (Managed plan); $180/year; $149.99 lifetime

Visit Ferrow → · Alternatives to Ferrow → · How this was measured →