Features
Cypher-compatible graph query language
In-memory ACID transactions with persistence
Vector search for semantic AI
Built-in GraphRAG pipelines
AI memory (semantic, episodic, procedural)
Agentic AI execution graph support
Sub-millisecond multi-hop graph traversal
Real-time fraud detection and network analysis
MAGE algorithm library (centrality, community, GNN)
Stream connectors (Kafka, Pulsar, Redpanda)
Memgraph Lab visual interface
Multi-tenancy and RBAC (Enterprise)
Federated query (MemGQL) across data sources
Memgraph MCP Server for AI agent integration
Graph neural network (GNN) support
Fully managed vector database
Automatic index tuning and upgrades
Writes acknowledged in under 100ms
Consistent p99 latency at any scale
Metadata filtering during queries
Namespace-per-agent isolation
Dense, sparse, and full-text indexes
Hybrid search (vector + BM25) via Pinecone Nexus public preview
Integrated embedding and reranking (Cohere Rerank 4.0 Fast GA)
Customer Managed Encryption Keys (CMEK)
Open-source monitoring stack (June 2026)
Multi-region and multi-cloud support (AWS, GCP, Azure) on Builder+
