Research
In addition to developing HASH, we publish much of the original research we conduct into graphs, agents, and formally-verified systems as part of our mission
Recent Work
- 2026 –
Specification elicitation tools for faithful intent representation
One of several projects we’re working on as part of ARIA’s Safeguarded AI programme, where we lead the “Interaction Paradigms” / HCI technical area. Learn more at brunch.ai - 2025 –
Petri Nets for trustworthy agentic coordination
Exploring how Petri Nets, a mathematical formalism for modeling distributed, concurrent systems, can be used to coordinate and audit agentic workflows. Try using Petrinaut at petrinaut.org - 2025 –
Formally-verifiable modeling of safety-critical supply chains
In collaboration with the University of Oxford’s Department of Computer Science: Professor Nobuko Yoshida, Professor David Parker, and Adrian Puerto Aubel. Check out the announcement blog post and stay tuned for more information soon. - 2022 –
Backend-agnostic, strongly-typed graph data engine
A data engine for typed property graphs that decouples query and schema semantics from the underlying database, allowing the same graph workloads to run unchanged across multiple optimized storage backends. Learn more at hgres.org - 2022 –
Multi-temporal hypergraph query language
HashQL is a query language with first-class support for hypergraph relations and multiple, independent time dimensions — enabling precise reasoning over how data evolves and when it was known. Learn more at hgres.org/hashql - 2021 –
Composable, interoperable, decentralized semantic types
A shared, open registry of semantic types — definitions of the concepts, measures, and entities that structured data refers to. SemType provides a common vocabulary that both people and AI agents can reference to exchange data unambiguously. - 2021 – 2024
Embedder-agnostic blocks
An initiative to make interactive UI blocks portable across applications, regardless of the host environment. The output of this work was the Block Protocol — an open standard for structured, composable blocks that can be embedded in any supporting application.
Productized Research
2019
hCore: High-performance agent-based simulation engine developed in Rust, compiled to WASM, capable of running user-created JavaScript, Python and Rust simulations.2019
GPT-2 ABMs: Early LLM-integrated agent-based simulations, and grounding of agents in world models begins.2020
Real-world applications: Optimization of real-world systems like vaccine distribution and supply chains begins.2021
Graph-backed models: Multi-temporal, strongly-typed graph underpinning for error-sensitive, safety-critical environments.
Active Research Areas
In-Transformer Simulation
Graph Machine Learning / JEPA
Temporal Hypergraph Querying
Autoformalization
Logic Programming
Process (De)composition
Hierarchical Reinforcement Learning
Join Us
Create a free account
Sign up to try HASH out for yourself, and see what all the fuss is about
By signing up you agree to our terms and conditions and privacy policy