ModelRefs / Long-Term Memory (Agents) — AI Glossary

Long-Term Memory (Agents) — AI Glossary

Persistent storage of information an agent accumulates across sessions, retrievable in future interactions.

Overview

Long-term agent memory persists beyond context window limits using vector or key-value stores. Agents write important facts, user preferences, and past task outcomes to long-term memory and retrieve relevant entries at the start of new sessions. Enables personalization, user preference learning, and continuity across multi-session workflows.

Reference details

Topicagents
Last reviewed2026-06-24

Commonly confused with

The counterpart to working memory: this is what persists once the context window is gone. It is not RAG — a RAG corpus is documents you supplied, while this accumulates from the agent's own interactions, which means nobody curated it and stale entries stay retrievable until something removes them. Episodic and semantic memory are the two forms it usually takes.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Long-Term Memory (Agents) — AI Glossary.

Frequently asked questions

What is Long-Term Memory (Agents)?

Persistent storage of information an agent accumulates across sessions, retrievable in future interactions.

What concepts are related to Long-Term Memory (Agents)?

Closely related concepts include memory store, working memory, retrieval pipeline.