The AI Agent Memory Landscape

Session Track: Graph Memory & Agents

Session Time: 01:30 pm - 02:00 pm April 15

Session description

As AI agents evolve from stateless chatbots to persistent, context-aware systems, memory has become the critical differentiator between demos and production-ready applications. This talk maps the rapidly emerging ecosystem of agent memory solutions and provides practical guidance on choosing and implementing the right memory architecture for your agents.

We’ll explore the cognitive architecture frameworks (episodic, semantic, procedural memory) that underpin modern agent systems, survey the competitive landscape of memory providers, and examine real-world implementation patterns from leading agent frameworks like LangGraph, CrewAI, and Pydantic AI.

Attendees will leave with a clear mental model of the memory stack and actionable strategies for building agents that truly learn and adapt.