Write something into long-term memory so it survives this conversation. Routing is automatic by default: steps or instructions become a procedure; content with an emotional weight above 0.5 (detected, or set via emotionalWeight) becomes an episode; a confidence above 0.9 makes it a pinned core memory; anything else becomes a semantic fact. Set type only when you want to override that. Every call adds a new memory, except that storing the same core memory again updates it; the content is also kept in working memory while the server runs. Returns the id of the stored memory. If it may already be stored, check with zenbrain_recall first: storing it again adds a duplicate.

Search long-term memory for anything relevant to a query. By default it searches the episodic, semantic, procedural and core layers; working memory (a handful of recently stored items, held only while the server runs) is searched only when named in layers. Returns results ranked by relevance, each tagged with the layer it came from. Use this before answering when the user refers to something from an earlier session. To see how much is stored rather than what, use zenbrain_health; to save something, use zenbrain_store.

Run one consolidation pass: among the 100 most recent episodes, each one with an emotional weight above 0.5 becomes a semantic fact — once, however often the pass runs. Working-memory slots lose relevance with age, and slots whose relevance has dropped to 0.01 or below are removed; that is the only deletion, and nothing in long-term memory is deleted. Run it between sessions or after a batch of zenbrain_store calls, not on every turn; compare zenbrain_health before and after to see the effect.

Report how full the memory layers are: working-memory slots in use, interactions held, episodes, facts and how many are due for review, procedures, core blocks. Read-only and cheap, safe to call at any time. It returns counts only; to read the memories themselves, use zenbrain_recall.