Neo4j Live: AgentMemory for .NET: Persistent AI Agent Memory Engine

Neo4j Live
  • Length: 1 hr 4 min
Play video on YouTube: Neo4j Live: AgentMemory for .NET: Persistent AI Agent Memory Engine
Presented by Jose Latorre: more videos Presenter
Watch on YouTube (opens in a new tab)

Chapters 12

  1. Play from Introduction
  2. Play from Jose's Inspiration: From Sci-Fi Robots to Agent Memory
  3. Play from Agent Memory Basics: Context, RAG & Graph RAG Explained
  4. Play from Surveying the Memory Landscape: Mem0, Graphiti & Others
  5. Play from Choosing Storage: Files vs. Vector DBs vs. Graphs
  6. Play from Building Agent Memory for .NET & the POLE Schema
  7. Play from Live Demo: Inside the Memory Brain
  8. Play from Voice Interaction, Alice in Wonderland & Forgetting
  9. Play from Performance Optimization & Benchmarking Results
  10. Play from Roadmap: Extensibility, Skill Distillation & Auto-Learning
  11. Play from Behavioral Memory & Alignment Research
  12. Play from Audience Q&A & Closing

.NET developers building AI agents have felt this gap: Neo4j Agent Memory shipped for Python and TypeScript, but .NET was left bolting things together. José L. Latorre closes it with AgentMemory for .NET - a from-scratch implementation verified 178/178 against Neo4j's own Agent Memory Test Compatibility Kit. In this livestream, he shows how the same three memory layers - short-term, long-term (POLE+O), and reasoning - now live natively in .NET, wired straight into Microsoft Agent Framework and Semantic Kernel, so your agent remembers by design, not by hoping it calls the right tool at the right time.

Guest: Jose Latorre ( linkedin.com/in/joslat (opens in a new tab) )

Resources mentioned

GenAI & GraphRAGDeveloper tools

Related videos

Browse all videos