DeepLearning.AI Launches Course on Building Memory-Aware Agents with Oracle
Andrew Ng·
· Updated
DeepLearning.AI launched a short course on building memory-aware agents, developed with Oracle. It covers Memory Managers, semantic tool retrieval, and write-back pipelines — giving agents the ability to store, retrieve, and refine knowledge across sessions so they improve over time.
DeepLearning.AI, in partnership with Oracle, launched "Agent Memory: Building Memory-Aware Agents" — an intermediate short course (1h 57min, 7 video lessons, 4 code examples). Using Oracle AI Database and LangChain, it covers three areas: a Memory Manager for different memory types, semantic search that retrieves only relevant tools at inference time, and write-back pipelines that consolidate episodic memory into semantic memory so agents can update their own knowledge base.
Most agents are stateless — when a session ends, all context is gone. This breaks long-horizon tasks: a research agent working across dozens of papers has no way to carry forward what it learned. Memory engineering treats long-term memory as first-class infrastructure: external to the model, persistent, and structured.
Take the course to build a stateful Memory Aware Agent — one that loads prior context at startup, runs a recursive reasoning loop, and writes back refined knowledge after each session.
New course: Agent Memory: Building Memory-Aware Agents, built in partnership with @Oracle and taught by @richmondalake and Nacho Martínez.
Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions.
You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time.
Skills you'll gain:
- Build persistent memory stores for different agent memory types
- Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory
- Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search
Join and learn to build agents that remember and improve over time!
https://t.co/nxNSEHGmr9
