Notes from the graph & GenAI frontier.
Tutorials, patterns and field notes on building GraphRAG systems, knowledge graphs and LLM agents on Neo4j — written by the people who build them.
Featured
Editor's Picks
Getting started with the GraphAcademy MCP server
Connect Claude Code, Cursor, or VS Code to the GraphAcademy MCP server and take courses, verify challenges, and generate Neo4j code from your editor.
Introducing the New GraphAcademy
Our first full redesign since 2024 — with teams, a revamped Neo4j Fundamentals course, editable data models, and a new onboarding assistant.
Your AuraDB is probably bigger than it needs to be
How to reduce your database size and save money
Browse Posts
Find your next read
Using the GraphAcademy AI proxy in workshops
An introduction to the GraphAcademy AI proxy, how to get a key, the budget and time limits, and what each error message means when a request fails.
GraphRAG vs RAG - Two Retrievers, One Question
RAG vs GraphRAG: however you ask, the graph wins. See both retrievers answer the same movie question on Neo4j's recommendations dataset, then build it yourself.