Memory for LLM Agents: From Context to Durable State

Hosted by Amir Feizpour and Suhas Pai

Fri, Feb 27, 2026

5:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

148 students

Invite your network

Go deeper with a course

AI Agents for Pragmatic Builders - Claude Code, LangGraph, n8n
Amir Feizpour, PhD
View syllabus

What you'll learn

Memory Architecture for Agents

Understand the layers of agent memory: working context, episodic traces, long-term state, and external knowledge.

Context Engineering in Practice

Techniques for converting raw interaction history into structured, retrievable state.

Retrieval and Swapping Strategies

How search, ranking, and context window management enable scalable memory systems.

Operational Mechanics

Practical considerations including caching, deduplication, eviction, and invalidation of stale facts.

Why this topic matters

Without reliable memory, agents remain short-lived and brittle. Robust memory systems enable continuity, personalization, and long-horizon reasoning—unlocking more capable, trustworthy, and production-ready agentic applications. As LLM systems evolve beyond single interactions, memory becomes foundational infrastructure rather than an optional feature.

You'll learn from

Amir Feizpour

Founder @ Aggregate Intellect

Amir Feizpour is the founder, CEO, and Chief Scientist at Aggregate Intellect building a generative business brain for service and science based companies. Amir has built and grown a global community of 5000+ AI practitioners and researchers gathered around topics in AI research, engineering, product development, and responsibility. Prior to this, Amir was an NLP Product Lead at Royal Bank of Canada. Amir held a research position at University of Oxford conducting experiments on quantum computing resulting in high profile publications and patents. Amir holds a PhD in Physics from University of Toronto. Amir also serves the AI ecosystem as an advisor at MaRS Discovery District, works with several startups as fractional chief AI officer, and engages with a wide range of community audiences (business executives to hands-on developers) through training and educational programs. Amir leads Aggregate Intellect’s R&D via several academic collaborations.

Suhas Pai

CTO @ Hudson Labs

Suhas is the CTO & Co-founder of Hudson Labs, an NLP startup operating in the financial domain, where he conducts research on LLMs, domain adaptation, text ranking, and more. He was the co-chair of the Privacy WG at BigScience, the chair at TMLS 2022 and TMLS NLP 2022 conferences, and is currently writing a book on Large Language Models.

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.