Store a memory with auto-enrichment (importance scoring, tag extraction, auto-summarization, auto-pruning). This is the primary method for recording interactions.

Store a memory directly without enrichment. Use this when you already have importance/tags or want precise control.

Store multiple memories in one call, directly without enrichment. Embeddings (if configured) are computed in a single batched call for efficiency.

Get a single memory by ID. Returns null if not found.

Retrieve memories for an actor with optional filtering, semantic search, and date range constraints.

Compile memories into an LLM-ready system prompt (markdown formatted, token-budgeted, split into important and recent sections).

Summarize old memories into a single summary memory. Compresses N interactions into 1 summary via LLM.

Prune (delete) memories matching the given strategy. Scoped to a single actor — defaults to the current session actor. Returns the pruned memory IDs and count. Handle with care.

Delete ALL memories belonging to a specific actor. Irreversible.

Merge multiple memories into one. Uses the highest-importance memory as the base and appends content from the rest.

Get memory statistics: total count, by type, by actor, average importance, and more.

Delete a single memory by ID.

Delete multiple memories by ID in one call. Returns the number actually deleted.

Bump a memory's recency (last-accessed timestamp) without changing its content, id, or createdAt.

Export a snapshot of memories for backup or migration. Returns { version, memories, exportedAt }.

Import memories from a snapshot previously produced by memory_export. Restores each memory as-is, including its original ID.

Check the health of storage, LLM, and embedding connections.

Preview what would be pruned by a given strategy WITHOUT actually deleting. Scoped to a single actor — defaults to the current session actor. Returns the memory IDs that would be removed.