Graph of the World.
Perception fills a world model and physics makes it actionable, but the model has to live somewhere. It lives as a graph. Every entity an embodied system knows, a part, a material, a surface, a constraint, another agent, a sensor reading, is a node; every relationship is an edge. And because the world is continuous, each node carries a vector embedding, so a system can both traverse relationships and search by similarity in one engine, on the device. Graph of the World is that substrate, the hybrid graph and vector store that holds what a system perceives and reasons over. The research effort is hyperdb.
A graph is only as good as the names in it. This bench recognises a pattern by parsing it into named primitives over a small finite lexicon, so every recognition is explicit and checkable rather than learned from billions of examples.
hyperdb on GitHub ↗A property graph and vector search (HNSW) in one engine; queries traverse relationships and find nearest neighbors at once.
↓ Whitepaper · PDFRead online◆ Living paper◆ Explore the live corpus graphTechnical Report TR-2026-12 · Institute for Physical AI @ JBI
A queryable graph of grounded relations is straightforward to build and hard to keep true, and the second half is the interesting one. A relation grounded once and never re-grounded looks identical to one that still holds. Build the maintenance loop and the graph becomes something you can act on rather than something you have to check.
One of eight, and only one of them is physics. How we read a frontier →