Kuzu

https://kuzudb.github.io

Embedded property-graph database (Cypher) with a built-in vector index and full-text search, widely used as an embedded store for agent memory and GraphRAG. The kuzudb/kuzu repository was archived on 2025-10-10 after Apple acquired the company; 0.11.3 is the final release and earlier releases remain usable.

Archived. repository archived (read-only) Source · Alternatives and migration notes →

Archived · Verified 2026-10-29 · fresh as of 2026-10-29 · 49 cited facts, 26 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Tier
T2
Created
2025-09 repo fix
License
MIT repo fix
Freshness
2026-10-29 fix
Layer
model-infra repo fix
Licensing
open-source repo fix
Deployment locus
local repo fix
Platform vs product
platform repo fix

When to use

Optimised for: relationship modeling + reasoning + governance over pure vector

Anti-fit: not for purely-vector or simple-RAG use cases (graph adds setup cost)

Pros & cons

Pros

Embedded graph DB (think SQLite for graphs) — fastest path to local graph querying with no ops.

Cons

Embedded scope; not appropriate for production multi-user services.

Claims & capabilities

Sub-3ms recall via MCP.

Technical surface

API surface
SDK: Python, C++, Java, Node.js, Rust
Backend storage
custom (embedded native graph)
Deployment
Self-hosted only (embedded library; no managed cloud at time of acquisition)
Embedding model
BYO
Multi-tenancy
not applicable — embedded library
MCP
via community port
A2A
not supported
OpenTelemetry
no first-party OpenTelemetry exporter documented; standard logs/metrics typically available.

Similar systems

Other knowledge-graph platforms in the catalog, ranked by inbound references.

  • Neo4j T1

    Property graph DB with Cypher; native vector search; Aura Agent + MCP server for graph-as-memory. $100M GenAI investment in 2025.

  • Amazon Neptune Analytics T1

    Vector index on graph nodes queryable via openCypher. Mem0 integration GA 2025; Cognee integration for agentic RAG. Combines semantic recall with multi-hop traversal in one managed service.

  • FalkorDB T2

    Native GraphRAG SDK. Graph-memory backend for Mem0; MCP server via Graphiti integration; context graphs for long-term agent memory.

  • ArangoDB T1

    HybridGraphRAG combines vector search, graph traversal, full-text in one AQL query. ArangoGraphML for ML pipelines; LangChain integration. The company now brands itself Arango (Arango Contextual Data Platform unifying graph, vector, document and search), with ArangoDB as its database.

  • Memgraph T2

    In-memory GraphRAG engine. Memgraph 3.0 adds native vector search alongside graph traversal. LangChain toolkit.

  • Diffbot T1

    Auto-built knowledge graph from web crawl. 1T+ facts, 10B+ entities. GraphRAG-fine-tuned model based on open-source Llama 3.3.

Sources (48 cited facts, 26 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-26
    • License “Unlicensed” → “MIT” source
    #258
  2. 2026-10-26
    • Lifecycle first recorded as “archived”
    • Latest release “v1.12.9 2026-04-09” → “0.11.3 (final release; repository archived 2025-10-10)” source
    #254

Related systems

References (1)

Referenced by (2)

  • LangChain (framework) integrates with — LangChain docs have a Kuzu integration provider page (Embedded graph database management system). (verified 2026-10-29)
  • Zep & Graphiti integrates with — Graphiti README lists Kuzu as a graph backend, now marked deprecated but still shipped. (verified 2026-10-29)