Registry › Compare › Graphiti vs LightRAG

Graphiti vs LightRAG

Graphiti leads on trust: 86.6/100 (Grade A) against 81.4/100 (Grade A), a 5.2-point gap. Graphiti leads on supply-chain integrity and maintenance; LightRAG rests on broader evidence. Note: Graphiti's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

A Graphiti 86.6

Build Real-Time Knowledge Graphs for AI Agents

getzep/graphiti · #77 overall · #6 Memory & Knowledge · coverage B (3/5)

Choose Graphiti if supply-chain integrity and maintenance matter most.

+2.7Maintenance: last push 2d ago, against 5d ago
+1.6Safety / Integrity: 91% of recent commits signed, against 53%
+0.8Adoption: 211k weekly downloads against 35.6k

A LightRAG 81.4

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

HKUDS/LightRAG · #144 overall · #11 Memory & Knowledge · coverage A (4/5)

Choose LightRAG if breadth of evidence matters most.

A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

18.6

Safety / IntegrityGraphiti +1.6

17.0

12.9

TransparencyLightRAG +0.3

13.2

18.9

MaintenanceGraphiti +2.7

16.2

17.9

AdoptionGraphiti +0.8

17.1

+0.3

Runtime calibrationGraphiti +0.4

-0.1

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of Graphiti 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.

Full evidence

Signal	Graphitigetzep/graphiti	LightRAGHKUDS/LightRAG
HVTrust score	86.6	81.4
Evidence grade	A	A
Coverage grade	B	A
Overall rank	#77	#144
Rank in Memory & Knowledge	#6	#11
GitHub stars	32.5k	40.5k
Last updated	2d ago	5d ago
Build provenance	Yes	Yes
OSSF Scorecard	5.2 / 10	5.5 / 10
License	Apache-2.0	MIT
Downloads	211k/wk	36k/wk
Trust dimensions (points earned)
Safety / integrity / 25	18.6	17.0
Identity & provenance / 18	18.0	18.0
Transparency / 17	12.9	13.2
Maintenance / 20	18.9	16.2
Adoption / 20	17.9	17.1
Runtime capability surface (full matrix)
MCP server	Implemented	—
External providers	6 — Amazon Bedrock, Anthropic, Google Gemini, …	6 — Anthropic, Google Gemini, OpenAI, …
Requires API keys	Yes	Yes
Plugin surface	—	—
Provenance drift	Match	Match

Open in the live compare tool → Graphiti profile LightRAG profile More Memory & Knowledge →

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 v4.4 →