AI Concept Atlas
FIELD NOTES / 01
Side by side

Memory & Context Window

The context window limits the current interaction; application memory retains information that may be selected for later interactions.

Some frameworks call conversation state short-term memory. Always distinguish retained state from the actual information supplied to the model.

Swap columns ⇄
DimensionMemoryContext Window
PurposeRetain information for reuse.Bound the information available during a model interaction. [Anthropic][LangChain]
Role in the systemApplication state and recall mechanisms.A model or service capacity constraint. [Anthropic][LangChain]
Inputs and outputsSelected information is stored and may later be recalled.Supplied tokens and generated content consume available capacity. [Anthropic][LangChain]
PersistenceRetention can span one session or many, depending on the design.The window itself is not cross-session storage. [Anthropic][LangChain]
ExampleSave a learner preference for a future lesson.Keep a relevant manual excerpt within the current request. [Anthropic][LangChain]
Boundary caveatsStored information is not automatically included in the next input.Larger capacity does not make all stored information visible. [Anthropic][LangChain]

Evidence for this distinction

Last editorial review: 2026-09-13.