Create or update entities in the knowledge graph. If an entity already exists, merge observations (don't overwrite). Returns the created/updated entities.

Create relations between entities. Both entities must exist. Returns created relations or errors for missing entities.

Add observations to an existing entity.

Delete entities and all their relations/observations.

Delete specific observations from an entity.

Delete relations between entities.

Search for nodes in the knowledge graph by name, type, or observation content.

Open specific nodes by name. Returns full entity data with observations.

Read the entire knowledge graph. Returns all entities with observations and all relations.

Semantic search using vector embeddings. Finds entities most similar to the query. Requires the embedding model to be downloaded (run download_model.py first).

Migrate data from Anthropic MCP Memory JSONL format to SQLite. This is idempotent — running it multiple times won't duplicate data.