What is Context window?
A context window is the maximum amount of text (measured in tokens) a model can consider at once, including the prompt, conversation history, and its response.
Every request to a language model has a token budget — the context window — that covers everything the model reads and generates in that call. If a conversation or document exceeds it, older content has to be dropped or summarized.
Context window size varies significantly by provider and model, from tens of thousands of tokens to over a million. A larger window lets an agent hold more conversation history or reference bigger documents without losing earlier context.
On VibeOpenClaw
Which context window matters for an OpenClaw or Hermes agent depends on the model provider you choose — providers like Google are often picked specifically for large context windows when an agent needs to reason over long documents.