What types of memory do agents use, and what is context engineering and compaction?

For AI / LLM Engineer ML Engineer research-engineer

The short answer

Agents use short-term memory (the working context window) and long-term memory stored in vector databases or files, often split into episodic, semantic, and procedural memory. Context engineering is the discipline of curating what goes into the limited context window, and compaction summarizes or prunes older history so the agent retains key information without overflowing the window or degrading from too much noise.

How to think about it

Agents use short-term memory (the working context window) and long-term memory stored in vector databases or files, often split into episodic, semantic, and procedural memory. Context engineering is the discipline of curating what goes into the limited context window, and compaction summarizes or prunes older history so the agent retains key information without overflowing the window or degrading from too much noise.

Learn it properly Context engineering

Keep practising

When should you use RAG vs fine-tuning vs a long-context model? What is a context window in an LLM and why does its size matter? What is an AI agent, and how does it differ from a single LLM call? How do function/tool calling and LLM agents work at a high level? What is tool use or function calling in LLMs, and how do you design good tools for an agent?

All NLP & LLMs questions

Explore further

Agent Memory Mem0 — a memory layer for agents AGENTS.md, Skills & Tools

Context Engineering Compaction Context Window Agent