Neo4j blog

Agentic AI

The knowledge layer for enterprise AI

A manifesto for context-rich enterprise AI

Chart of the knowledge layer comprising ontologies, data, and memory

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

Independent study: GraphRAG makes AI agents 80% more truthful

Context graph diagram illustrating decision traces for AI agents

Agentic AI

What are decision traces in a context graph? How they reveal agentic reasoning

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

Adding RAG to your GraphQL API

GQL is here: Your Cypher queries in a GQL world.

Cypher & GQL

GQL is here: Your Cypher queries in a GQL world

GQL: The ISO Standard for Graphs Has Arrived!

GQL: The ISO standard for graphs has arrived

Building RAG Applications With the Neo4j GenAI Stack: A Comprehensive Guide

Building RAG applications with the Neo4j GenAI stack: a comprehensive guide

Node embeddings in a knowledge graph.

The future of knowledge graph: Will structured and semantic search become one?

What is retrieval-augmented generation RAG)?

GenAI

What is retrieval-augmented generation (RAG)?

Entity resolved knowledge graphs: A tutorial

Entity resolved knowledge graphs: A tutorial

GQL, the future of graph databases is here.

ISO GQL: A defining moment in the history of database innovation

LangChain Library now supports Neo4j vector index.

LangChain library adds full support for Neo4j vector index

Developer

Maximizing your Neo4j project’s potential: An in-depth guide to solution assessment

Graph data models for RAG applications

Neo4j brings GraphRAG capabilities for GenAI to Google Cloud