GraphRAG vs LightRAG
An independent, evidence-based trust comparison of GraphRAG and LightRAG, two Memory & Knowledge projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
LightRAG leads on trust — 84.5/100 (Grade A) vs 76.1/100 (Grade B), a 8.4-point gap. Full breakdown below.
| Signal | GraphRAGmicrosoft/graphrag | LightRAGHKUDS/LightRAG |
|---|---|---|
| HVTrust score | 76.1 | 84.5 |
| Evidence grade | B | A |
| Coverage grade | B | A |
| Overall rank | #128 | #52 |
| Rank in Memory & Knowledge | #7 | #5 |
| GitHub stars | 35.8k | 39.3k |
| Last updated | 1d ago | 1d ago |
| Build provenance | No | Yes |
| OSSF Scorecard | 7.0 / 10 | 5.4 / 10 |
| License | MIT | MIT |
| Downloads | 19k/wk | 27k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 13.8 | 17.5 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 14.4 | 13.1 |
| Maintenance / 20 | 16.5 | 19.9 |
| Adoption / 20 | 16.6 | 16.9 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | — |
| External providers | 1 — Multi-provider (LiteLLM) | 6 — Anthropic, Google Gemini, OpenAI, … |
| Requires API keys | No | Yes |
| Plugin surface | — | — |
| Provenance drift | Match | Match |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.3 →