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 ⇄| Dimension | Memory | Context Window |
|---|---|---|
| Purpose | Retain information for reuse. | Bound the information available during a model interaction. [Anthropic][LangChain] |
| Role in the system | Application state and recall mechanisms. | A model or service capacity constraint. [Anthropic][LangChain] |
| Inputs and outputs | Selected information is stored and may later be recalled. | Supplied tokens and generated content consume available capacity. [Anthropic][LangChain] |
| Persistence | Retention can span one session or many, depending on the design. | The window itself is not cross-session storage. [Anthropic][LangChain] |
| Example | Save a learner preference for a future lesson. | Keep a relevant manual excerpt within the current request. [Anthropic][LangChain] |
| Boundary caveats | Stored information is not automatically included in the next input. | Larger capacity does not make all stored information visible. [Anthropic][LangChain] |
Evidence for this distinction
- Context windows ↗ (opens in new tab)Anthropic · Publication date unknown
Relevant section: Understanding the context window - Memory overview ↗ (opens in new tab)LangChain · Publication date unknown
Relevant section: Short-term memory; Long-term memory
Last editorial review: 2026-09-13.