Context Graphs: Agent Memory with Neo4j
Course Description
In this course, you will learn how to give AI agents persistent, explainable memory backed by Neo4j using the neo4j-agent-memory library.
You will learn why most AI agent deployments fail to deliver enterprise value — and how context graphs solve the three critical gaps: no memory, no audit trail, and no shared learning. You will explore the three-layer memory model (short-term, long-term, and reasoning), the POLE+O entity classification system, and the full graph schema that connects them.
By the end of the course, you will have built a Pydantic AI agent that records its complete reasoning trace into Neo4j, and written Cypher queries to traverse that trace and explain exactly what the agent did and why.
Prerequisites
-
Neo4j Fundamentals — graph database concepts
-
Cypher Fundamentals — query language basics
-
Neo4j & GenAI Fundamentals — generative AI and GraphRAG concepts
-
Basic Python — reading and writing simple Python programs
Duration
1 hour
What you will learn
-
The three gaps in modern AI agent systems and how context graphs address them
-
The three structural layers of a context graph: entities, events, and context (the "why")
-
Short-term, long-term, and reasoning memory — their schemas, lifetimes, and access patterns
-
The POLE+O entity classification model (Person, Object, Location, Event, Organization)
-
How to install and configure
neo4j-agent-memoryagainst a live Neo4j instance -
How to use the Memory API to record reasoning traces from a Pydantic AI agent
-
How to write Cypher to traverse the reasoning trace graph and audit agent decisions
This course includes
-
4 modules
-
19 lessons
-
1 hands-on challenge
Get Support
If you find yourself stuck at any stage then our friendly community will be happy to help. You can reach out for help on the Neo4j Community Site, or head over to the Neo4j Discord server for real-time discussions.
Feedback
If you have any comments or feedback on this course you can email us on graphacademy@neo4j.com.