Free Course on Memory in Agent Systems
Free Course on Memory in Agent Systems
Explore a free course covering memory in agent systems, including various methods of storing and retrieving information.
Free Course on Memory in Agent Systems
This course, presented by a former Google engineer, covers key aspects of memory in agent systems. Here are the main topics discussed:
- 0:00 — Why every LLM call starts with amnesia.
- 2:31 — Storing memory in text, tables, or graphs.
- 5:04 — Four methods of searching: doing nothing, keywords, RAG, Graph RAG.
- 7:29 — Memory support: adding, deleting, retiring, attribution, reflection.
- 9:47 — Collecting everything on plain text and SQLite.
- 13:13 — Adding vector storage only when truly needed.
- 14:38 — Memory in strings, graph memory, and temporal graphs.
- 21:03 — Running code for all five options.
This course is a great opportunity for those looking to deepen their understanding of memory in agent systems.
Why it matters
AnalysisThis course provides essential insights into how memory impacts the effectiveness of agent systems, which is crucial for AI development. Understanding these concepts can significantly enhance the performance of LLMs.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Part II. AI Agent Architecture: From Model to Memory and Tools
A deep engineering dive: tokenization, KV-cache, sampling determinism, the training stack, quantization, context engineering, the safety stack, production RAG, ReAct, and multi-agent swarm systems.
Agent Memory
A comprehensive subsystem for data storage, filtering, and retrieval that transforms stateless LLM calls into a stateful system: from short-term scratchpad buffers to multi-session knowledge repositories.
Short-Term and Long-Term Memory of Agents
The architecture of multi-tier memory for autonomous agents. It distinguishes between Short-Term Memory (active context window of the current session) and Long-Term Memory (vector databases, user profile files, and episodic diaries).
Loop Engineering: Architecture of Autonomous Agentic Loops and the Post-Prompting Era
A deep dive into Loop Engineering: self-sustaining execution loops for Claude Code and autonomous agents, the DOER/CHECKER topology, deterministic verification, the /goal primitive, and reward hacking mitigation.