Neo4j blog

Introducing Neo4j GraphAware Financial Crime Intelligence

Move from fragmented data to connected intelligence, for better detection, deeper investigations, and defensible decisions.

Vector RAG vs. GraphRAG: Which retrieval do you need?

Scaling Karpathy’s LLM wiki: Why your knowledge base needs a graph

Independent study: GraphRAG makes AI agents 80% more truthful

Featured voices

Emil Eifrem

CEO & Founder, Neo4j

See all articles

Sudhir Hasbe

Chief Product Officer, Neo4j

See all articles

Philip Rathle

Chief Technology Officer, Neo4j

See all articles

Most recent

Going Meta: A Season of Building (and Grading) Ontologies

The startup’s guide to getting started building on Neo4j Aura

Train once, embed forever: GraphSAGE and the model repository in Aura Graph Analytics

Understanding GraphSAGE

Building a Neo4j Memory and Graph Agent for IBM watsonx Orchestrate

Secure GraphRAG: Wiring Microsoft Copilot Studio to Neo4j with per-user Okta SSO

Secure GraphRAG: Wiring Microsoft Copilot Studio to Neo4j with per-user Okta SSO

Graph database

What is graph technology? And why it’s the future of enterprise AI

From first graph algorithm experiment to production with Aura Graph Analytics

SumoDB in Neo4j: Microsoft Fabric bridging Decades of Rikishi — Part 4

The payload: the semantic layer, memory, and the loop that fills it

From Agent Memory to Portable Skills

From Agent Memory to Portable Skills

Illustration representing a context graph for AI agent memory

Agentic AI

What is a context graph?