Going Meta S03E05 – Neo4j Agent Memory

Season 03 Episode 5 of Going Meta – a Series on Semantics, Knowledge Graphs and All Things AI
Topic: Neo4j Agent Memory

Jesús Barrasa: https://twitter.com/BarrasaDV
Repository: https://github.com/jbarrasa/goingmeta
GraphAcademy free online courses – https://graphacademy.neo4j.com/
Knowledge Graph Book: https://bit.ly/3LaqE6b
Previous Episodes: https://neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/

0:00 – Intro & welcome: Agent memory and decision tracing
1:49 – Introducing Jesus & today’s focus on agent memory
4:17 – Why graph-based memory matters for AI agents
6:53 – Overview of Neo4j Agent Memory (short-term, long-term, reasoning)
9:49 – Setting up the demo: Aura instance & memory client
11:00 – Short-term memory: capturing conversation messages
20:16 – Long-term memory: entities, preferences & facts
30:58 – Reasoning memory: capturing agent traces & decisions
41:00 – Integrating memory into an assistant (live example)
49:02 – Context graph vs knowledge graph discussion
58:00 – Wrap-up, GraphAcademy & NODES AI

#graphdatabase #neo4j #graphrag #knowledgegraphs #ontology #data