NebulaGraph
v5.2 adds graph-vector-text hybrid retrieval natively. MCP server for Claude/GPT agents. GraphRAG in three lines of code.
At a glance
- Type
- Graph + vector + text hybrid retrieval
- Tier
- T2
- Section
- Knowledge-graph platforms
- Created
- 2018
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- OSS (Apache-2.0) + NebulaGraph Enterprise (commercial)
- Funding
- $18M total (Seed + pre-A); investors: Redpoint China Ventures, Matrix Partners China, Source Code Capital, Jeneration
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
Strong at trillion-edge scale; popular in China for fraud / social-network workloads.
Cons
Heavy operational overhead; documentation in English lags Chinese resources.
Claims & capabilities
100× faster path queries. Open-source + commercial.
Technical surface
- API surface
- nGQL, SDK: Python, Java, Go, JS, C++
- Backend storage
- custom (RocksDB-backed distributed graph)
- Deployment
- Both (self-hosted + NebulaGraph Cloud)
- Embedding model
- BYO
- Multi-tenancy
- namespace
- MCP
- no first-party MCP adapter published as of 2026-05; community connectors may exist.
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- via Prometheus
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.