Registry › Compare › Graphiti vs LanceDB

Graphiti vs LanceDB

Both are Grade A and 0.4 points apart, so choose on what you weigh most. LanceDB leads on maintenance and rests on broader evidence.

A Graphiti 87.3

Build Real-Time Knowledge Graphs for AI Agents

getzep/graphiti · #54 overall · #4 Memory & Knowledge · coverage B (3/5)

Graphiti doesn't lead on any scored dimension in this pair.

A LanceDB 87.7

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

lancedb/lancedb · #46 overall · #3 Memory & Knowledge · coverage A (4/5)

Choose LanceDB if maintenance matters most.

  • +1.4Maintenance
  • A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

19.6
Safety / IntegrityLanceDB +0.1
19.7
13.5
TransparencyLanceDB +0.3
13.8
18.5
MaintenanceLanceDB +1.4
19.9
17.7
AdoptionLanceDB +0.4
18.1
+0.0
Runtime calibrationGraphiti +1.8
-1.8

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of Graphiti and LanceDB, 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 LanceDBlancedb/lancedb
HVTrust score 87.3 87.7
Evidence grade A A
Coverage grade B A
Overall rank #54 #46
Rank in Memory & Knowledge #4 #3
GitHub stars 31.5k 11.6k
Last updated 1d ago 1d ago
Build provenance Yes Yes
OSSF Scorecard 5.9 / 10 6.2 / 10
License Apache-2.0 Apache-2.0
Downloads 156k/wk 1.8M/wk
Trust dimensions (points earned)
Safety / integrity / 25 19.6 19.7
Identity & provenance / 18 18.0 18.0
Transparency / 17 13.5 13.8
Maintenance / 20 18.5 19.9
Adoption / 20 17.7 18.1
Runtime capability surface (full matrix)
MCP server Implemented —
External providers 6 — Amazon Bedrock, Anthropic, Google Gemini, … 4 — Amazon Bedrock, Cohere, Google Gemini, …
Requires API keys Yes No
Plugin surface — plugins
Provenance drift Match Unknown
Open in the live compare tool → Graphiti profile LanceDB 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 →