Infrastructure
Context Window
The amount of text and conversation history a model can remember and work with at one time.
Also written as context length
- Messages
- 259
- Members using it
- 72
- First seen
- Nov 19, 2025
What it means
The total amount of tokens (text, code, and conversation) that an AI model can hold in its working memory during a single interaction. Think of it as the model's short-term memory - everything it can "see" at once to understand your request and generate a response. When you exceed this limit, the model starts forgetting earlier parts of the conversation.
How it's used here
Members actively monitor context window usage to avoid hitting limits during long coding sessions or complex projects. Frequently discussed when orchestrating multiple agents or pulling large project contexts from databases. A practical concern when building with AI rather than a theoretical concept.
Seen in the wild
“can someone explain what a context window is in stupid terms - does it mean the amount of discussion you can have before starting a new chat?”
“Nice!! Got 5.5 on OC to build a tool for my CC orchestrator to have visibility of context window usage across the others for managed compacts.”
“When you pull the project context from the DB, how are you deciding what actually gets sent to the model so the context window doesn't explode?”
More in this category
- APIApplication Programming Interface; how software talks to other software programmatically.
- TokensThe units of text that language models read and generate, used to measure cost and limits.
- Open SourceSoftware whose code is publicly available for anyone to view, modify, and run.
- Mac MiniApple's compact desktop computer, popular here for running local AI models.