GraphAcademy
Course · Part of Generative AI & GraphRAG

Context Graphs: Agent Memory with Neo4j

Build an AI agent that records its reasoning, then query the trace to understand what it did and why

2 hours20 lessons across 4 modules
Context EngineerGenerative AI & GraphRAGIntermediateBuild a Neo4j-backed Application
About this course

In this 2-hour course, you will learn

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.

  • Context Graphs

  • Agent Memory

  • neo4j-agent-memory

  • Reasoning Traces

  • POLE+O

Course content

4 modules, 2 hours.

  1. 5 lessons
    1. The Three Gaps6 min
    2. The Three Memory Types6 min
    3. Why Graphs for Agent Memory5 min
    4. Installation and Configuration4 min
    5. The Complete Memory API8 min
  2. 4 lessons
    1. The Stateless Agent Problem4 min
    2. Short-Term Memory4 min
    3. The Short-Term Memory API5 min
    4. How Messages Connect to Long-Term Memory3 min
  3. 5 lessons
    1. The Persistent Knowledge Problem4 min
    2. The long-term memory schema5 min
    3. Why graphs over vector embeddings5 min
    4. Entity Extraction Pipeline5 min
    5. The Long-Term Memory API5 min
  4. 6 lessons
    1. The Auditability Problem4 min
    2. What is a context graph?6 min
    3. The reasoning memory schema6 min
    4. Recording Reasoning Traces4 min
    5. Querying the Trace Graph5 min
    6. Build and run the agent6 min
Where to next

Keep going on Generative AI & GraphRAG.

View the full path
Up next in path

Developing with Neo4j MCP Tools

2 hoursStart
Later in path

Building Agents in Neo4j Aura

2 hoursStart