INTELLIGENCE_MODE=enhanced (the default). They add entity extraction and graph traversal on top of the memory store. Basic mode does not register them.
If these tools are missing from your client, confirm you have not set
INTELLIGENCE_MODE=basic and check stderr for embedding model download errors. See Troubleshooting.extract_entities
Extract named entities and relationships from text using NLP. Identifies people, organizations, technologies, and projects.string
required
Input text to analyze. Longer text yields more entities.
{people[], organizations[], technologies[], projects[], relationships[], keywords[]}.
get_knowledge_graph
Build a knowledge graph from stored memories. Returns entities as nodes and relationships as edges.string
Filter nodes by type:
people, organizations, technologies, or projects. Omit for all types.string
Filter nodes containing this name (case-insensitive substring match). Omit for all entities.
string
Filter edges by relationship:
WORKS_FOR, USES, BUILT_WITH, KNOWS, etc. Omit for all relationships.number
Maximum nodes to return. Range: 1-100. Default: 20.
{nodes[], edges[]} where nodes have {id, type, name, memories[]} and edges have {from, to, type, confidence}.
find_connections
Discover relationship paths between entities in the knowledge graph. Uses BFS traversal to find how entities connect.string
required
Starting entity name for path search. Must match an entity in the knowledge graph exactly.
string
Target entity name. If omitted, returns all reachable entities up to
max_depth.number
Maximum relationship hops to traverse. Range: 1-5. Default: 2.
{from, to, max_depth, paths_found, paths[]} where each path is an array of {from, to, type} edges.
Related
Memory Tools
Store the memories the graph is built from.
Configuration
Switch between enhanced and basic intelligence modes.