Implementing Persistent Memory in AI Agents
Technical approaches to building memory systems that enable agents to learn, remember, and improve over time.
This session examines the technical implementation of memory systems for AI agents, covering short-term working memory, long-term episodic memory, and semantic knowledge storage. We explore memory architectures including key-value stores, graph databases for relationship modeling, and vector stores for semantic retrieval. Topics include memory consolidation strategies, forgetting mechanisms to prevent context overflow, memory retrieval strategies, and integration patterns with LLMs. The discussion covers practical implementation using tools like Redis, PostgreSQL with pgvector, and specialized memory frameworks, along with patterns for memory-augmented reasoning and learning from interactions.
Overview
This session examines the technical implementation of memory systems for AI agents, covering short-term working memory, long-term episodic memory, and semantic knowledge storage. We explore memory architectures including key-value stores, graph databases for relationship modeling, and vector stores for semantic retrieval. Topics include memory consolidation strategies, forgetting mechanisms to prevent context overflow, memory retrieval strategies, and integration patterns with LLMs. The discussion covers practical implementation using tools like Redis, PostgreSQL with pgvector, and specialized memory frameworks, along with patterns for memory-augmented reasoning and learning from interactions.
Thank you for your interest in this talk. We look forward to seeing you!
Recommended Talks
Explore related talks that complement this research
TECHNICAL
Agents
Introduction to Agentic AI
A practical introduction to the core components required to build reliable, production-ready agentic AI systems.
TECHNICAL
Agents
Agent Architectures and Design Patterns
Design Patterns for Robust, Controllable Multi-Agent Systems
TECHNICAL
Agents
Vector Databases for LLM Systems: Foundations, Architectures, and Emerging Directions
A practical look at how vector databases power RAG systems, improve retrieval quality, and support real-world LLM applications.
TECHNICAL
Agents
Building AI Systems That Learn from Real Humans
A practical overview of how human feedback, cognitive biases, and behavioral models can improve AI alignment.