Going Meta S03E09 – Shape agent memory with ontologies
Season 03 Episode 9 of Going Meta – a Series on Semantics, Knowledge Graphs and All Things AI
Topic: Shape agent memory with ontologies
Jesús Barrasa: https://twitter.com/BarrasaDV
Repository: https://github.com/jbarrasa/goingmeta
Knowledge Graph Book: https://bit.ly/3LaqE6b
Previous Episodes: https://neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/
Agent Memory: https://github.com/neo4j-labs/agent-memory
Neo4j Agent Memory Service: https://memory.neo4jlabs.com/
Create Context Graph: https://create-context-graph.dev/
Create new ontology: https://create-context-graph.dev/docs/tutorials/customizing-domain-ontology
Art Ontology: https://github.com/jbarrasa/goingmeta/blob/ee0f723eb667f548b1dab30b3e1156252ad495a9/session31/ontos/art.ttl#l300
Chapters
- 00:00Introduction
- 02:35Setting the Stage: Agent Memory & Knowledge Layers
- 05:25How Ontologies Shape What Agents Remember
- 09:17The Three Memory Types: Short-Term, Long-Term & Reasoning
- 13:40Entity Extraction Pipeline: spaCy, GLINER2 & LLM Stages
- 20:15Agent Frameworks & Multi-Agent Memory Architectures
- 27:00Q&A: Separate Database or Combined with Domain Data?
- 30:27NAMS: Neo4j Agent Memory Service Demo
- 44:54Importing Custom Ontologies & Domain-Specific Extraction
- 56:00Wrap-up
Related Videos
070 ESG Supply Chain Knowledge Graph – NODES2022 – Dr. Julian Gruemmer
Introducing Workspace — The Fastest Way To Build Your Neo4j Database
