Skip to main content
Active Memory is the deep-recall lane for eligible conversational sessions. The default escalate mode runs its blocking recall sub-agent only when the message asks about the past and the deterministic memory lane found no strong trusted trigger match. This keeps ordinary replies fast while preserving a deeper search path for prior decisions, conversations, and temporal or multi-hop questions. Flat retrieval is strongest for direct fact matches and weaker on temporal and multi-session questions. LongMemEval (arXiv:2410.10813) measures that gap, while the PrefEval benchmark highlights the value of preference-adjacent reminders. Escalation by default spends the blocking model call where those harder recall shapes are actually present. This page is an index. Active memory is documented on nine pages, one per reader job. Open the page that matches your task.

Where each section moved

Every section heading from the previous single-page version keeps its anchor here, so an existing link such as /concepts/active-memory#lossless-claw still resolves. Each entry points at the page that now holds the content.