Interview: Half the Tokens: Giving AI Agents Memory | William Lyon, Neo4j

Some of you know @lyonwj and many of your don't... Will has been thinking about data, systems, and graphs since long before the current AI wave.

Recently, Will spoke with Sri Kalimani, Technology Product Manager & Podcast Host, on The Foundry Alley

:backhand_index_pointing_right: Watch the conversation and join the discussion in the Neo4j Developer Community: https://dev.neo4j.com/will_lyon_foundry_alley

Learn how Will got involved with Neo4j and Graph Technology and all of the critical topics listed below.

Chapters

00:00 Introduction to Neo4j and Graph Technology
01:07 The Role of Knowledge Graphs in AI
02:16 Applying Knowledge Graphs to Generative AI
03:23 Cost Control and Efficiency in AI Agents
05:20 Data Storage and Retrieval Changes Post-AI
08:47 Handling Unstructured Data with Vectors and Graphs
11:38 Scaling GraphRAG for Large Data Sets
25:11 Demo: Neo4j Agent Memory Service in Action
36:42 Best Practices for Building Agent Memory Systems
45:31 The Impact of Graph Memory on Enterprise AI

What should AI agents remember between runs?

Explore Neo4j Agent Memory: Neo4j Agent Memory - Neo4j Agent Memory

1 Like