Kuzu
Embedded graph DB with built-in vector index + full-text search. MCP server packages for Claude (sub-3ms recall). Offline-first, single-file deployment. Community fork adds concurrent multi-writer support for multi-agent.
At a glance
- Type
- Embedded graph DB + sub-3ms recall
- Tier
- T2
- Section
- Knowledge-graph platforms
- Created
- 2025-09
- Latest release
- v1.12.9 2026-04-09
- License
- Unlicensed
- GitHub
- 24★ Python
- Pricing
- Free (MIT-licensed open source); acquired by Apple so no commercial cloud
- Funding
- No external funding confirmed; acquired by Apple ~Oct 2025
Taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- long-term
- update
- overwrite
- unit
- fact
- governance
- inspectable
- conflict
- overwrite
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.
- AllegroGraph (Franz) T1
RDF triple/quad store with RDFS++ / OWL reasoning. v8.4 (May 2025) added an NLQ interface.
- Apache AGE T2
openCypher over Postgres. Pairs with pgvector for graph + vector hybrid retrieval. Azure Database for PostgreSQL ships AGE with ai_extension LLM functions for entity extraction directly in SQL.
- ArangoDB T1
HybridGraphRAG combines vector search, graph traversal, full-text in one AQL query. ArangoGraphML for ML pipelines; LangChain integration.
- Dgraph T2
Vector indexing on any node. Google Gen AI Toolbox integration; LangChain agent orchestration.
Related systems
References (1)
- Model Context Protocol (MCP spec) depends on at runtime — Sub-3ms recall via MCP.