AI & Agents
KelvinAI
Last updated 2026-09-14 · benchmark measured 2026-09-14 — deterministic & reproducible
Local-first AI coding assistant and personal agent for Mac, Windows, and Android.
Are you the maker of KelvinAI? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/kelvinai-ai/2026-09-14. That address never changes; this page moves with every re-measure.
Legit.Show scored KelvinAI 81/100 on 2026-09-14, measured across all 7 frames from its public surface. legit.show/s/kelvinai-ai/2026-09-14
Is KelvinAI production-ready?
Legit.Show scores KelvinAI 81 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on KelvinAI (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 — 100/100
- Accessibility — 93/100
- Security — 45/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 100/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 35/100
What we measured
- Security headers present: HSTS.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 934 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 · Software engineers · Individual contributors · Remote workers · Technical professionals
Pricing
Free download; Pro and Lite plans available; subscription model for advanced features like semantic memory and video generation (usage-based credits)
Visit KelvinAI → · Alternatives to KelvinAI → · How this was measured →