// Query Neo4j knowledge graph for entities, relationships, and graph analysis.
Build and deploy the realtime-api Docker container with full verification that deployed code matches local source.
Speak text aloud using the Magpie TTS container in the realtime-api Docker stack. Zero external dependencies — just curl + aplay.
Run TTS round-trip tests — pure-logic unit tests and optional integration tests against live TTS/STT services.
Unified memory management for notes, knowledge graph, RAG search, and file analysis. Use when working with: (1) Core memory — protected identity, projects, relationships, and system facts that should never be forgotten, (2) Working notes — per-session ephemeral notes organized by section, (3) MongoDB RAG — vector-search-enabled notes with importance scoring, decay, deduplication, and archival, (4) Neo4j knowledge graph — entities, relationships, merge duplicates, reinforce mentions, Cypher queries, (5) File analysis — deep file reading that extracts knowledge into all memory layers, (6) Service initialization — health-check, start/stop MongoDB, Neo4j, TEI embeddings via docker-compose with partial setup support.
Query MongoDB notes store for memory analysis and statistics.
Calls qq agent from cli.
| name | neo4j-query |
| description | Query Neo4j knowledge graph for entities, relationships, and graph analysis. |
| triggers | ["neo4j","knowledge graph","entities","relationships","graph query","cypher"] |
Query the Neo4j knowledge graph to investigate entities, relationships, and graph structure.
bolt://localhost:7687 (or NEO4J_URI env var)neo4j (or NEO4J_USER env var)refinerypass (or NEO4J_PASSWORD env var)from qq.knowledge.neo4j_client import Neo4jClient
# Initialize client
client = Neo4jClient()
# Execute raw Cypher query
results = client.execute("MATCH (n) RETURN n LIMIT 10")
# Get graph summary (entity and relationship counts by type)
summary = client.get_graph_summary()
# Get entity by name
entity = client.get_entity("entity_name")
# Get related entities (up to N hops)
related = client.get_related_entities("entity_name", depth=2, limit=20)
# Close when done
client.close()
-- Total entities
MATCH (n) RETURN count(n) as total_entities
-- Entities by type
MATCH (n) RETURN labels(n)[0] as type, count(n) as count ORDER BY count DESC
-- Total relationships
MATCH ()-[r]->() RETURN count(r) as total_relationships
-- Relationships by type
MATCH ()-[r]->() RETURN type(r) as type, count(r) as count ORDER BY count DESC
-- Entities with no incoming or outgoing relationships
MATCH (n) WHERE NOT (n)--() RETURN n.name, labels(n)[0] as type
-- Entities with most connections
MATCH (n)-[r]-() RETURN n.name, labels(n)[0] as type, count(r) as connections ORDER BY connections DESC LIMIT 10
-- Distribution of relationship counts per entity
MATCH (n)
OPTIONAL MATCH (n)-[r]-()
WITH n, count(r) as rel_count
RETURN rel_count, count(n) as entities_with_this_count ORDER BY rel_count
-- Sample entities with their properties
MATCH (n) RETURN n.name, labels(n)[0] as type, n.description LIMIT 20
-- Sample relationships with endpoints
MATCH (a)-[r]->(b) RETURN a.name, type(r), b.name LIMIT 20
# Use cypher-shell directly
docker exec -it qq-neo4j-1 cypher-shell -u neo4j -p refinerypass "MATCH (n) RETURN count(n)"