WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
Harish Santhanalakshmi Ganesan

TL;DR
WorldDB is a novel memory engine that models each node as a recursive, content-addressed world with programmable edges, enabling superior long-term reasoning and knowledge management in agentic systems.
Contribution
It introduces a recursive, content-addressed graph-of-worlds structure with programmable edges for write-time reasoning, improving over flat knowledge graphs.
Findings
Achieves 96.40% accuracy on LongMemEval-s, surpassing state-of-the-art.
Provides perfect single-session recall and robust temporal reasoning.
Graph layer contributes +7.0pp to task accuracy independently.
Abstract
Persistent memory is the bottleneck separating stateless chatbots from long-running agentic systems. Retrieval-augmented generation (RAG) over flat vector stores fragments facts into chunks, loses cross-session identity, and has no first-class notion of supersession or contradiction. Recent bitemporal knowledge-graph systems (Graphiti, Memento, Hydra DB) add typed edges and valid-time metadata, but the graph itself remains flat: no recursive composition, no content-addressed invariants on nodes, and edge types carry no behavior beyond a label. We present WorldDB, a memory engine built on three commitments: (i) every node is a world -- a container with its own interior subgraph, ontology scope, and composed embedding, recursive to arbitrary depth; (ii) nodes are content-addressed and immutable, so any edit produces a new hash at the node and every ancestor, giving a Merkle-style audit…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
