Store a new memory. Use when something is worth remembering: a preference, fix, decision, or procedure.

Full-text search across all active memories. Returns results ranked by relevance, trust status, and recency. Deprecated and superseded memories are excluded automatically.

Get the most relevant memories for a topic, fitted to a token budget. Use at the start of a task to load context.

Update the title, content, tags, or confidence of an existing memory. Use when a rule changes, a fix gets refined, or new context applies to an existing memory.

Permanently delete a memory by ID. Prefer deprecate_memory for memories that were once true but are no longer. Only delete memories that were created in error or contain incorrect information.

List all memories, optionally filtered by type. Returns memories sorted by most recently created. Use to browse what the memory system knows about a topic or to audit stored rules.

Save current session state before conversation ends or context compresses. Capture: what's in progress, what's blocked, what's done, decisions made. The next agent instance loads this automatically.

Load the most recent session state. Call this at the start of a conversation to pick up where the last instance left off.

Promote a memory's trust level: hypothesis -> active -> validated. Use when evidence confirms a memory is true.

Mark a memory as deprecated. It will be excluded from search/recall but kept for history. Use when a rule or fact is no longer true.

Replace an old memory with a new one. Old memory is marked superseded and linked to the replacement.

Run a health check on the memory system. Returns: score (0-100), conflict count, stale count, status distribution. Use to audit memory quality.

Detect contradictions between active memories. Returns pairs of memories that assert and negate the same topic.