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

Independent study: GraphRAG makes AI agents 80% more truthful

Illustration representing a context graph for AI agent memory

Agentic AI

What is a context graph?

Welcome, GraphAware

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

Building graph-based agentic systems: Failures, fixes, and how the answer gets there — Part 2

SumoDB in Neo4j: Graph Analytics in Snowflake — Part 2

Get start With Neo4j Aura Cloud Graph Database Network

Getting started with Neo4j Aura: A guide to the leading cloud graph database

Learn what agentic RAG is, how it works, which design patterns to use, and when it beats traditional RAG.

Agentic AI

Agentic RAG: What it is, how it works, and when to use it

Introducing Neo4j Agent Skills

Introducing Asynchronous I/O in Neo4j using io_uring

SumoDB in Neo4j: Graph Analytics of Grand Sumo

Building stateful AI: Integrating Aura Agent lifecycle with MCP and persistent memory

Precise economic policy in a world of chaos

GraphAcademy content is moved into Neo4j Aura, and an Aura Agent used to provide MCP server access to VS Code, Cursor, and Claude agents.

Can I use Aura Agents to create an MCP enabled teacher?

Graph database

From agents to analytics: What’s new from Neo4j on Google Cloud

Integrating Neo4j with Google Genkit: A Practical Guide