Neo4j
Property graph DB with Cypher; native vector search; Aura Agent + MCP server for graph-as-memory. $100M GenAI investment in 2025.
At a glance
- Type
- Property graph + vectors + Aura Agent
- Tier
- T1
- Section
- Knowledge-graph platforms
- Created
- 2024-12
- Latest release
- mcp-neo4j-cyphe… 2026-04-10
- License
- MIT
- GitHub
- 944★ +15/mo Python
- Pricing
- Free + paid
- Funding
- $325M total $2.0B val Series F · 2021-06
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
Largest graph database community by orders of magnitude; Cypher is the de-facto graph query language; strong native AI/RAG integrations.
Cons
Property-graph model can be awkward for RDF/semantic-web workloads; clustering and scale-out can get expensive.
Claims & capabilities
$200M ARR milestone (2024); $325M total funding at $2B valuation (Series F, June 2021); 2,000+ Neo4j jobs worldwide on LinkedIn; 843 in US; Fortune 500 customer base (Daimler, Dun & Bradstreet, EY, IBM, Merck); $100M GenAI investment in 2025; native Aura Agent + MCP server for graph-as-memory
Technical surface
- API surface
- Bolt, REST, GraphQL, Cypher, SDK: many
- Backend storage
- custom (native graph store)
- Deployment
- Both
- Embedding model
- BYO
- Multi-tenancy
- AuraDB Virtual Dedicated Cloud / AuraDS Enterprise: dedicated AWS/Azure/GCP account/subscription/project per customer; PrivateLink supported
- MCP
- via official adapter — neo4j-mcp
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- first-class — Neo4j metrics + OTel
Compare Neo4j with…
Similar systems
Other knowledge-graph platforms in the catalog, ranked by inbound references.
- 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.
- Diffbot T1
Auto-built knowledge graph from web crawl. 1T+ facts, 10B+ entities. GraphRAG-fine-tuned model based on open-source Llama 3.3.
Related systems
Referenced by (7)
- Cognee depends on at runtime — adjacent-infrastructure cell: BYO LLM; bundles Kuzu/Neo4j for graph + LanceDB for vectors
- Graphiti MCP Server (Zep) depends on at runtime — backend-storage cell: Neo4j
- Mem0 depends on at runtime — adjacent-infrastructure cell: BYO LLM provider; bundles vector store (Qdrant default) and graph store (Neo4j optional)
- Memary depends on at runtime — adjacent-infrastructure cell: BYO LLM; Neo4j required
- Spring AI ChatMemory integrates with — pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j)
- Zep — governance posture depends on at runtime — backend-storage cell: Postgres + Neo4j
- Zep & Graphiti depends on at runtime — backend-storage cell: Postgres + Neo4j (Graphiti)