Memgraph
In-memory GraphRAG engine. Memgraph 3.0 adds native vector search alongside graph traversal. LangChain toolkit.
Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 53 cited facts, 4 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- In-memory GraphRAG + native vector search vendor fix
- Tier
- T2
- Section
- Knowledge-graph platforms
- Latest release
- not applicable — not OSS fix
- Pricing
- Free + paid vendor fix
- Funding
- $14M Seed · 2023-12 third-party fix
- Freshness
- 2026-10-26 fix
- Layer
- model-infra repo fix
- Licensing
- commercial repo fix
- Accelerator
- techstars-2016 third-party fix
- Protocols
- mcp-server repo fix
- Developer activity
- OpenRank 20.09 (12-mo avg 23.99) · 26 participants — 2026-09 third-party 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
In-memory graph DB optimized for real-time analytics; Cypher-compatible.
Cons
Smaller community than Neo4j; in-memory cost limits scale.
Claims & capabilities
Used by NASA and Cedars-Sinai for GenAI knowledge graphs.
Technical surface
- API surface
- Bolt, Cypher, SDK: many
- Backend storage
- custom (in-memory native graph)
- Deployment
- Both
- Embedding model
- BYO
- Multi-tenancy
- hard-isolation
- MCP
- yes — official MCP server in memgraph/ai-toolkit
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- first-class — Prometheus + OTel
Alternatives to Memgraph → live options ranked by shared design, licence, hosting and MCP support
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.
- Kuzu T2
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.
- 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 (52 cited facts, 4 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is In-memory GraphRAG + native vector search vendor
- What it does & what's distinct In-memory GraphRAG engine. Memgraph 3.0 adds native vector search alongside graph traver… vendor
- Claims / benefits Used by NASA and Cedars-Sinai for GenAI knowledge graphs. vendor
- Modalities text vendor
- Created 2016 vendor
- License BSL-1.1 (source-available, Community); Enterprise under proprietary MEL repo
- GitHub memgraph/memgraph — ~4.4k stars, active (commit date not captured) repo
- Mindshare 1 press ~50 (Memgraph L jobs vendor
- Funding $14M Seed · 2023-12 third-party
- Customers / scale 51-200 ppl Real-time graph use cases, enterprise third-party
- Pricing Free + paid vendor
- Compliance SOC 2 Type II vendor
- Deployment Both vendor
- HQ UK vendor
- Founders / pedigree Dominik Tomicevic (CEO/co-founder), Marko Budiselic (CTO/co-founder) vendor
- Memory volume / scale no scale claim vendor
- Performance Vendor benchmark vs Neo4j: 120× faster on shortest-path, 7× faster on PageRank, ~6× fast… vendor
- API surface Bolt, Cypher, SDK: many vendor
- Backend storage custom (in-memory native graph) vendor
- Multi-tenancy hard-isolation vendor
- Encryption at-rest + in-transit vendor
- SSO / RBAC SSO + RBAC vendor
- Embedding model BYO vendor
- Versioning immutable append-log vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- Forgetting policy none (permanent) vendor
- MCP support yes — official MCP server in memgraph/ai-toolkit repo
- OTel first-class — Prometheus + OTel vendor
- Webhooks / events event stream — triggers + Kafka/Pulsar streams vendor
- Import / export Cypher dump, CSV, JSON vendor
- Validated verticals financial-services, healthcare, legal, government, internal IT, KM vendor
- Time to running <1hr (Docker / managed cloud) to <1week (enterprise procurement) vendor
- Anti-fit not for purely-vector or simple-RAG use cases (graph adds setup cost) vendor
- Optimised for relationship modeling + reasoning + governance over pure vector vendor
- Adjacent infrastructure BYO LLM; bundled graph store; some require additional vector index vendor
- Pros In-memory graph DB optimized for real-time analytics; Cypher-compatible. vendor
- Cons Smaller community than Neo4j; in-memory cost limits scale. vendor
- Project & sources memgraph.com vendor
- cost-input-usd-per-mtok 0 vendor
- cost-output-usd-per-mtok 0 vendor
- cost-tier free vendor
- cost-pricing-model free-tier vendor
- cost-last-verified 2026-06-29 vendor
- adoption-accelerator techstars-2016 third-party
- architecture-deployment-locus hybrid vendor
- licensing-bucket commercial repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup model-infra repo
- developer-activity-opendigger {"activity":156.31,"as_of":"2026-09","openrank_12mo":23.99,"openrank_current":20.09,"par… third-party
- protocol-support mcp-server repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
Related systems
References (1)
- LangChain (framework) integrates with — Memgraph 3.0 adds native vector search alongside graph traversal. LangChain toolkit.
Referenced by (2)
- LangChain (framework) integrates with — LangChain docs have a Memgraph integration provider page (Real-time graph database platform). (verified 2026-10-29)
- LlamaIndex (framework) integrates with — LlamaIndex has an official graph store integration package llama-index-graph-stores-memgraph in its repo. (verified 2026-10-29)