Choose your training style

Pick the format that matches the level of support you want.

Self-pacedAvailable

Self-paced

Start immediately and work through the training on your own schedule.

Free

Human trainerComing soon

Human trainer

Join a guided cohort or workshop format when live delivery is available.

$99

Guided by an instructor

AI trainerComing soon

AI trainer

Practice with an AI-guided trainer experience tailored to the course topic.

Personalized guidance

What you'll learn

Implement vector-store-backed memory for AI agents
Build knowledge graphs for structured agent memory
Design hybrid memory systems with short-term and long-term recall
Choose the right memory infrastructure for your use case

Overview

Persistent agent memory (244K+ stars) is what separates toy demos from production agents. This course covers the infrastructure and patterns for giving agents durable, queryable memory.

What you'll build

A vector-store-backed memory layer for conversation history
A knowledge graph for structured relationship tracking
A hybrid memory system combining short-term and long-term recall

Tools covered

Mem0 — Open-source memory layer for AI agents
ChromaDB / Qdrant — Vector databases for semantic search
Neo4j — Graph database for relationship memory
LangMem — LangChain's memory management toolkit

Why this matters

Memory is the missing piece in most agent architectures. Without it, agents forget everything between sessions — which means they can never truly learn or improve.