Memory & Context
Keeping long stories coherent past the context window.
With memory enabled, the oldest chunk of a long chat folds into a running summary and leaves the prompt. Token use stays flat as the story grows.
Summarization runs on fast free models in the background, so you keep chatting. The current summary rides along in a system block.
Recent chat is embedded and compared against older messages and lore candidates. The closest matches are injected as background, so old details resurface when relevant.
Per-conversation opt-in. A small classifier decides whether your message needs fresh facts. Only then does a real search run and join the context.
Search engine and context size are configurable in the settings drawer. Web search is available on paid accounts.
Memory and web search are per-conversation switches in the settings drawer. Presets carry defaults for new chats. The utility model setting picks which model does background work.