Entity types, functional relations, imported ontologies, and store stats for a dataset. Call once per session before remember.

Add an entity type when nothing in describe_ontology fits. PascalCase name; optional parent (collapses onto a basic type) and aliases.

Import an OWL/RDF/Turtle ontology (text). Classes become entity types with parents collapsing onto basic types; labels become aliases.

Declare relation names that hold a single current value per subject (e.g. current_owner, deployed_in). New assertions then supersede older ones automatically; nothing is deleted.

Store memory as a typed graph: entities (name, type, description) and relations (source --name--> target, one-sentence description, evidence, optional valid_from/valid_to). Pass source_text and a summary so recall can find it lexically. Validates against the ontology, merges entities by name, supersedes functional relations, records provenance, and warns about hotspots that may be contradictions.

Record that two stored facts cannot both be true. Adds a contradicts edge between their subjects. Use supersede instead when the newer fact simply replaces the older in time.

Mark an older fact as superseded by a newer one. The old fact stays in history and leaves default recall.

Merge two entities that denote the same thing. Relations and chunks move to keep; drop is removed and recorded as an alias.

Add relations between existing entities proposed by memify_candidates(cross_connect).

Write the summary for a global-context bucket returned by memify_candidates(stale_summaries).

Forget an entity (and its relations) by exact name, a relation by id, a session, or a whole dataset. Prefer supersede for facts that were true once. Confirm with the user first.

Recall memory. Routes the query to a mode unless given: hybrid (default), facts, neighbourhood, lexical (quoted phrase), summaries, temporal, rules, session. Searches the project dataset then the user dataset. Returns ranked raw entities, facts (with evidence, validity, superseded/contested flags), chunks; you synthesise.

Facts around given entities or relations, grouped by subject, with hotspots where one subject holds several values for one relation. Judge them with the mnemoth-contradictions skill.

Provenance ledger for an entity (and its relations) or a relation: every create, merge, assert, supersede, forget with actor and time.

Maintenance proposals: cross_connect (co-occurring entities without a relation), consolidate (near-duplicate names), stale_summaries (global-context buckets needing a summary).

Global context index: one bucket per entity type with its summary, and how many are stale.

List datasets (memory scopes) on this machine; the default for this project and the user-global dataset.

Start (or resume) a session. Returns standing context (goals, rules, preferences, lessons) to load before work.

Append a turn (user/assistant/tool/system) to the session's fast cache.

Record a session context entry: goals, rules, preferences, lessons_learned, tool_rules, workflow_state, success_patterns, failure_lessons, environment_facts, or feedback ('+Name'/'-Name' adjusts recall weight). Pass retire_entry_id to replace an outdated entry.

Read a session: turns and context entries, optionally filtered by section.

Pack a session into batches for distillation, with prior lessons and the curator/writer rules. Then judge and call publish_lessons.

Persist accepted lessons as Lesson entities linked to what they apply to; marks the session distilled.

Close a session. Tells you whether it still needs distillation.