WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
Coffee With Developers • Mar 25, 2026

What is Agent Memory? - William Lyon

William Lyon

William Lyon proves why naive text-based AI memory fails at scale. Learn how building graph-based reasoning memory with Neo4j slashes token costs and boosts multi-agent accuracy.

Pause
Mute Enter Fullscreen
#1 about 5 min

Introduction to Neo4j and real-time graph database recommendations

Transitioning from stale batch computing to real-time graph databases enables highly personalized product recommendations.

#2 about 5 min

Defining AI agents as reasoning loops equipped with tools

An AI agent operates as a continuous reasoning loop that uses tools to interact with its environment and resolve tasks.

#3 about 4 min

Keeping humans in the loop for safe agent deployment

Integrating human oversight with AI agents ensures explainable decision-making and compliance in regulated industries like finance.

#4 about 5 min

Solving the agent memory problem to reduce token usage

Implementing a shared graph-based memory layer prevents repetitive onboarding and significantly reduces token consumption across agent ecosystems.

#5 about 4 min

Structuring agent memory with short-term and reasoning layers

Combining conversation history, entity extraction, and execution paths creates a context graph that improves agent efficiency.

#6 about 2 min

Evaluating reasoning traces to optimize future agent tasks

Capturing and comparing previous execution paths through vector search allows agents to reuse successful tool calling strategies.

#7 about 4 min

Exploring different industry approaches to AI agent memory

While many frameworks rely on static markdown files, experimental systems are moving toward graph-based propositions and observational memory.

#8 about 5 min

Integrating graph memory into Python AI agent frameworks

Developers can easily add shared memory capabilities by dropping a Neo4j package into existing Python frameworks.

#9 about 3 min

Building cost-effective entity extraction pipelines for unstructured data

A three-stage extraction process using statistical NLP and local CPU models minimizes expensive LLM fallback calls.

#10 about 3 min

Improving system accuracy and efficiency with graph rag

Transitioning to graph-based memory systems dramatically increases retrieval accuracy before addressing token efficiency optimizations.

#11 about 4 min

Establishing language-agnostic conventions for shared memory substrates

Standardizing graph data models allows agents built in different languages and frameworks to seamlessly collaborate through one database.

#12 about 2 min

Managing organizational expectations for AI agent deployments

The biggest challenge in implementing agents involves aligning internal stakeholders on practical capabilities and ensuring adequate human oversight.

#13 about 4 min

Testing local memory plugins for conversational AI agents

Developers can instantly upgrade their local conversational agents by dropping in a plugin that parses markdown into a knowledge graph.

#14 about 6 min

Expanding engineering teams and the future of agents

As organizations scale their engineering capacity, continuous iteration on reasoning loops will drive the next generation of efficient agent systems.

Matching moments

1:24 min

Designing short-term and long-term memory for intelligent agents

Zaid Zaim Zaid Zaim +1 · World Congress 2026 Europe

1:30 min

Empowering autonomous agents with persistent relationship memory architectures

Gal Shubeli Gal Shubeli · World Congress 2026 Europe

1:15 min

Equipping AI agents with memory and context

Oren Penso Oren Penso · World Congress 2026 Europe

2:36 min

Exploring the core architecture and components of AI agents

Jörg Neumann Jörg Neumann · World Congress 2025

1:27 min

Moving beyond chat interfaces using intelligent agents

Viktoria Semaan Viktoria Semaan · World Congress 2025

4:45 min

Agent components, memory types, and execution loops

Saoussen Chaabnia Saoussen Chaabnia · Europe 2026 Virtual

More from Coffee With Developers

Using Agents to Curate the Content You See Online - Dan Gish thumbnail
12:47
about 1 month ago

Using Agents to Curate the Content You See Online - Dan Gish

Dan Gish

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka thumbnail
11:14
about 1 month ago

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka

Ewa Szyszka

What is Cross-Origin Storage - Thomas Steiner thumbnail
34:51
about 1 month ago

What is Cross-Origin Storage - Thomas Steiner

Thomas Steiner

Women in AI - Nalini Garg thumbnail
42:19
about 1 month ago

Women in AI - Nalini Garg

Nalini Garg

Agents and People Dynamics in Shared Chats - Sam Liu thumbnail
37:41
about 1 month ago

Agents and People Dynamics in Shared Chats - Sam Liu

Sam Liu

Why Token Reduction Isn’t Cost Reduction - Dave Anderson & Sarel Weinberger, PhD. thumbnail
41:09
about 2 months ago

Why Token Reduction Isn’t Cost Reduction - Dave Anderson & Sarel Weinberger, PhD.

Dave Anderson, Sarel Weinberger, Phd

Related videos

Solving AI Amnesia: Building "Infinite Memory" for Agents without the RAM thumbnail
11:00
Europe 2026 Virtual • 3 months ago

Solving AI Amnesia: Building "Infinite Memory" for Agents without the RAM

Tara Khani

Context Graphs for Explainable, Decision-Aware AI Agents thumbnail
23:20
World Congress 2026 Europe • 3 months ago

Context Graphs for Explainable, Decision-Aware AI Agents

Zaid Zaim, Jordi Spranger

AI Agents Graph: Your following tool in your Java AI journey thumbnail
30:38
World Congress 2025 • about 1 year ago

AI Agents Graph: Your following tool in your Java AI journey

Alex Soto

Context is all you need thumbnail
24:18
World Congress 2026 Europe • 3 months ago

Context is all you need

Raphael De Lio, Samuel Agbede

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j thumbnail
46:51
over 1 year ago

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j

On a Secret Mission: Developing AI Agents thumbnail
29:03
World Congress 2025 • about 1 year ago

On a Secret Mission: Developing AI Agents

Jörg Neumann

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.