ModelRefs / Working Memory (Agents) — AI Glossary
Working Memory (Agents) — AI Glossary
The active context window contents available to an agent during a reasoning step; the agent's immediate information space. Limited by context window size.
Overview
Working memory for agents is the context window: the conversation history, retrieved documents, tool results, and in-progress scratchpad. Limited by context window size. Agents must manage working memory actively—compressing old turns, evicting irrelevant content—as tasks grow longer. Distinct from persistent memory stores.
Reference details
| Topic | agents |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Commonly confused with
Working memory is what is in the context window during this step; long-term memory is what survives the session. The practical difference is what each costs and how each fails: working memory is re-sent and re-billed on every call and disappears when the run ends, while long-term memory costs a retrieval and fails by returning the wrong entry. `memory` is the umbrella above both.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Working Memory (Agents) — AI Glossary.
Frequently asked questions
What is Working Memory (Agents)?
The active context window contents available to an agent during a reasoning step; the agent's immediate information space.
What concepts are related to Working Memory (Agents)?
Closely related concepts include memory store, context management, long term memory.