Knowledge Agent

This turns your claude-mem observations into queryable AI sessions. Build a filtered corpus from your observation history (say, all hook-related decisions or last month's bugfixes), prime it to load the knowledge into a chat session, then ask questions conversationally. It's useful when you want focused answers from past work rather than scanning through everything manually. The workflow is straightforward: build with filters like project, types, concepts, or date ranges, prime once, then query repeatedly. The session remembers context across follow-ups. Keep corpora focused for better results, and rebuild plus reprime when you've added new observations worth including.