RushDB in Action: Building AI-Native Apps with Self-Aware Graphs
summary
Claims a graph-native DB called RushDB built on Neo4j that auto-ingests JSON, auto-discovers schema and creates labeled meta property graphs with reusable hyperproperties, running all transformations in transactions. Demo ingests ~4K records instantly, exposes a unified API across records/properties/labels/relationships/values, supports faceted filtering and agent-driven analytics, and reconstructs payloads; code is open source with Docker and Kubernetes deployment, though some UI visuals aren’t production-ready yet.
AI-written summary · about
chapters (20)
- 0:00Introduction to RushDB
- 1:10Data rituals and bottlenecks
- 2:35Why humans think in graphs
- 3:43Hyperproperties explained
- 5:11Labeled meta property graphs
- 6:38RushDB architecture overview
- 9:11Setting up a project
- 10:35Importing simple data
- 12:02Ingesting large datasets
- 13:27Unified query API demo
- 15:16Dynamic faceted search
- 16:47Graph analytics with agents
- 18:54Dynamic ontologies for AI
- 20:45JSON-based queries
- 21:50Democratizing graph databases
- 23:14Behind the scenes of properties
- 25:24Data normalization and types
- 26:54Building dynamic filters
- 27:39Seamless app development
- 28:23Q&A session
related talks
49mModern Graph Databases
30mPerformant GraphRAG Improving Neo4j to Drive Autonomous AI ...
31mBuilding a Customer-Intelligence Brain: How GraphRAG Turns Data into Decisions
32mNever use a graph database!
26mGraph Databases will change your (freakin') life
30mSurrealDB: The Database Revolution ✨ NewSQL ✨
58mJSON in → App out: from tables and documents to graphs and agent memory
39mEnhancing RAG with Neo4j Knowledge Graph