Developer Tools
Sipp
Last updated 2026-06-24 · benchmark measured 2026-08-09 — deterministic & reproducible
Sipp is a WebGPU-based AI inference runtime that runs models directly in the browser.
Is Sipp production-ready?
Legit.Show scores Sipp 81 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Sipp (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 90/100
- Accessibility — 97/100
- Security — 45/100
- Privacy — 100/100
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 47/100
What we measured
- Security headers present: HSTS.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 949 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 built it
product account @sippdev
Who it's for
Web developers · AI/ML engineers · Game developers · Agent builders · Vision & chat application developers
Pricing
Open source, free to install via npm
Visit Sipp → · Alternatives to Sipp → · How this was measured →