Create multiple new entities in the knowledge graph. Entities are the fundamental nodes with a name, type, and list of observations. Stored in ZeroDB cloud — persists across sessions and devices.

Create multiple new relations between entities in the knowledge graph. Relations should be in active voice.

Add new observations to existing entities in the knowledge graph.

Delete multiple entities and their associated relations from the knowledge graph.

Delete specific observations from entities in the knowledge graph.

Delete multiple relations from the knowledge graph.

Read the entire knowledge graph from ZeroDB cloud storage.

Search for nodes in the knowledge graph based on a text query. Matches against entity names, types, and observation content (case-insensitive substring match).

Open specific nodes in the knowledge graph by their names.

Search for nodes in the knowledge graph using semantic vector similarity. Unlike search_nodes which does exact text matching, this finds entities by meaning — e.g., searching "machine learning frameworks" would find entities about "PyTorch" or "TensorFlow" even without those exact words.