AI & Agents

LightRAG

Source: HKUDS/LightRAG · ★ 36442 · Python

Last updated 2026-06-11 · benchmark measured 2026-08-21 — deterministic & reproducible

LightRAG is a graph-based retrieval-augmented generation system for LLMs.

Is LightRAG production-ready?

Legit.Show scores LightRAG 58 out of 100 — the simple average of its 5 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on LightRAG (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Standards; its weakest is Discoverability. 5 of the seven frames returned a score; Performance and Accessibility were not measurable on this service and are recorded as null — not as zero. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — not measurable on this service (null — not scored as 0)
• Accessibility — not measurable on this service (null — not scored as 0)
• Security — 60/100
• Privacy — 25/100
• Reliability — 90/100
• Standards — 100/100
• Discoverability — 15/100

What we measured

• Security headers present: CSP, X-Frame-Options.
• No HSTS.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 39 ms to first byte.
• Returns a proper 404 for unknown routes.
• 2 of 3 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

LLM developers · RAG system builders · AI researchers · Data engineers

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