LLM-powered chat applications are traditionally stateless, often suffering from "amnesia" that forces them to re-derive context, leading to expensive and inefficient prompt-stuffing. This presentation explores a production-ready solution: integrating the Neo4j Agent Memory System (NAMS) with the Vercel AI SDK.
We will walk through the implementation of a persistent memory layer that categorizes knowledge into short-term, long-term, and reasoning graph structures. I will demonstrate two distinct integration patterns:
Provider Mode: A transparent middleware approach for seamless, "invisible" memory integration.
Tools Mode: A model-driven approach that grants the agent agency over memory, providing auditability and debuggability.
We will also cover best practices for using the Model Context Protocol (MCP) to bridge conversational memory with live graph data and discuss strategies for optimising token usage and memory retrieval latency.
Speakers
Karan Chellani
Senior Solution Architect, Persistent
Karan Chellani is a Senior Solution Architect with 19 years of experience in enterprise technology and systems architecture. Throughout his career, he has specialized in designing and deploying complex AI/ML infrastructures. Currently, Karan focuses on modern GenAI frameworks and Agentic AI, helping organizations bridge the gap between experimental LLM implementations and production-grade, scalable applications. He is passionate about solving the "amnesia" problem in conversational AI through persistent, memory-augmented agent architectures.
Kaustubh Darekar
AI Engineer, Persistent Systems
AI Engineer working on neo4j graph database integrating neo4j agent memory with various agent frameworks
Prakriti Solankey
Full Stack Developer, Persistent Systems
Full Stack Developer skilled in building scalable applications, responsive user interfaces, and cloud-native solutions. Passionate about AI, Generative AI, and Agentic AI, with a strong interest in intelligent agent-based systems. Continuously learning emerging technologies to deliver innovative and impactful solutions.
Pravesh Kumar
Data & AI Engineer, Persistent Systems
Data & AI Engineering Leader specializing in GenAI, MCP Servers, and agentic systems. Enabling intelligent automation, enterprise knowledge management, and scalable AI-driven solutions across industries.
