AI & Agents
Kilo
Last updated 2026-06-11 · benchmark measured 2026-08-09 — deterministic & reproducible
Open source AI coding agent for VS Code, JetBrains, CLI, and cloud.
Is Kilo production-ready?
Legit.Show scores Kilo 86 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Kilo (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Performance. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 43/100
- Accessibility — 92/100
- Security — 70/100
- Privacy — 100/100
- Reliability — 100/100
- Standards — 100/100
- Discoverability — 100/100
What we measured
- Security headers present: HSTS, X-Frame-Options, X-Content-Type-Options.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 761 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
Scott Breitenother · product account @kilocode
Who it's for
Software developers · Development teams · Open source contributors · Enterprise developers · DevOps engineers
Pricing
Free tier available; Premium tiers with Auto Model pricing
Visit Kilo → · Alternatives to Kilo → · How this was measured →