Registry › Compare › FAISS vs Graphiti

FAISS vs Graphiti

Graphiti leads on trust: 86.3/100 (Grade A) against 75.8/100 (Grade B), a 10.5-point gap. FAISS leads on maintenance and adoption, and rests on broader evidence; Graphiti leads on supply-chain integrity and provenance. Note: Graphiti's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

B FAISS 75.8

A library for efficient similarity search and clustering of dense vectors.

facebookresearch/faiss · #263 overall · #15 Memory & Knowledge · coverage A (4/5)

Choose FAISS if maintenance and adoption matter most.

  • +1.8Maintenance: last push today, against 2d ago
  • +1.7Adoption: 3.0M weekly downloads against 245.5k
  • +0.6Transparency: OSSF Scorecard 6.1 against 5.4
  • A vs BEvidence coverage: 4 of 5 independent signal types, against 3
A Graphiti 86.3

Build Real-Time Knowledge Graphs for AI Agents

getzep/graphiti · #88 overall · #8 Memory & Knowledge · coverage B (3/5)

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

  • +10.9Safety / Integrity: 84% of recent commits signed, against 0%
  • +7.2Identity / Provenance: package provenance attested, against none

Where they differ

7.6
Safety / IntegrityGraphiti +10.9
18.5
10.8
Identity / ProvenanceGraphiti +7.2
18.0
13.7
TransparencyFAISS +0.6
13.1
20.0
MaintenanceFAISS +1.8
18.2
19.7
AdoptionFAISS +1.7
18.0
+4.0
Runtime calibrationFAISS +3.5
+0.5

Full evidence table

An independent, evidence-based trust comparison of FAISS and Graphiti, 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 FAISSfacebookresearch/faiss Graphitigetzep/graphiti
HVTrust score 75.8 86.3
Evidence grade B A
Coverage grade A B
Overall rank #263 #88
Rank in Memory & Knowledge #15 #8
GitHub stars 41.9k 33.0k
Last updated today 2d ago
Build provenance No Yes
OSSF Scorecard 6.1 / 10 5.4 / 10
License MIT Apache-2.0
Downloads 3.0M/wk 245k/wk
Trust dimensions (points earned)
Safety / integrity / 25 7.6 18.5
Identity & provenance / 18 10.8 18.0
Transparency / 17 13.7 13.1
Maintenance / 20 20.0 18.2
Adoption / 20 19.7 18.0
Runtime capability surface (full matrix)
MCP server — Implemented
External providers — 6 — Amazon Bedrock, Anthropic, Google Gemini, …
Requires API keys No Yes
Plugin surface — —
Provenance drift Match Match
Open in the live compare tool → FAISS profile Graphiti 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 →