Save a new memory to the knowledge graph.

Args: content: The memory content to save (Korean or English text). keywords: Optional list of keywords. Auto-extracted if not provided. category: Memory category. One of: fact, preference, experience, emotion, technical, core_principle. Defaults to "auto" which auto-classifies from content. related_ids: Optional list of memory IDs to link as related. immutable: If True, memory cannot be updated or deleted. pinned: If True, memory is protected from the forgetting pipeline.

Search memories by semantic similarity.

Args: query: Search query text (Korean or English). top_k: Number of results to return (default: 5, max: 200). category: Optional category filter (fact/preference/experience/emotion/technical/core_principle).

Automatically retrieve and compose relevant memories for a user message.

Searches the memory store, selects the most relevant memories, and composes them into a context string within the token budget using multi-resolution levels (full text, summary, entity triple).

This tool should be called at the beginning of every conversation turn to inject relevant memory context.

Args: user_message: The user's current message to find relevant memories for. token_budget: Maximum tokens for the composed context (default: 1024). top_k: Number of memories to retrieve (default: 10, use higher values like 100 for memory review).

Update an existing memory's content and/or keywords.

Args: memory_id: The ID of the memory to update. content: New content text (optional, keeps existing if not provided). keywords: New keywords list (optional, keeps existing if not provided).

Delete a memory from the knowledge graph.

Cannot delete immutable memories. Automatically cleans up graph edges.

Args: memory_id: The ID of the memory to delete.

Get memories related to a given memory via graph edges (BFS traversal).

Args: memory_id: The starting memory ID. depth: How many hops to traverse (default: 1, max: 3).

Pin a memory to protect it from the forgetting pipeline.

Args: memory_id: The ID of the memory to pin.

Remove pin protection from a memory, allowing it to be forgotten over time.

Args: memory_id: The ID of the memory to unpin.

Get statistics about the memory store: total count and category breakdown.

Run the memory sleep cycle.

Performs consolidation, resolution regeneration, forgetting, and checkpoint saving.

This performs periodic memory maintenance. Recommended to run periodically (e.g., daily or after many conversations).

Get the current status of the memory policy (RL bandit model).

Returns epsilon (exploration rate), recent action distribution, and total update count.

Ask the RL policy to decide what memory action to take for a user message.

Returns the policy's decision (SAVE/SKIP/RETRIEVE) with reasoning. If SAVE: also returns the saved memory entry. If RETRIEVE: also returns retrieved memories.

Args: user_message: The user's message to evaluate. turn_id: Optional turn identifier.

Generate an interactive HTML visualization of the memory graph.

Creates a browser-viewable graph showing memory nodes, relationships, and knowledge graph entity triples. Requires the 'viz' extra to be installed.

Args: output_path: Optional output file path for the HTML. Defaults to data/visualizations/. include_inactive: If True, include inactive (forgotten) memories in the graph.