ModelRefs / Memory Store — AI Glossary
Memory Store — AI Glossary
A persistent storage layer that agents read from and write to, enabling information to persist across agent steps and sessions.
Overview
Agent memory stores vary by scope: working memory (current context window), episodic memory (past interaction summaries), semantic memory (extracted facts in vector DB), procedural memory (learned tool-use patterns). Implementations: LangMem, Mem0, Zep, MotherDuck, and custom vector/relational hybrid stores.
Reference details
| Topic | agents |
|---|---|
| Also known as | agent memory, persistent memory |
| Last reviewed | 2026-06-24 |
Related terms
Commonly confused with
The store is where memories live; memory is the behaviour of using them. Swapping a vector database for a different one changes the store and nothing about the hard part, which is the policy — what gets written, what gets overwritten when a fact changes, and what is allowed to be forgotten. A store with no forgetting policy grows until retrieval quality collapses.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Memory Store — AI Glossary.
Frequently asked questions
What is Memory Store?
A persistent storage layer that agents read from and write to, enabling information to persist across agent steps and sessions.
Is Memory Store the same as agent memory?
Yes — agent memory, persistent memory are common aliases for Memory Store.
What concepts are related to Memory Store?
Closely related concepts include working memory, long term memory, agent.