Crystalyse
Dec 1st, 2025 — Crystalyse v1.0.0 stable release and preprint
We're releasing Crystalyse, a provenance-enforced scientific AI agent that grounds large-language model (LLMS) reasoning with materials modelling.
Crystalyse addresses a challenge in scientific AI: current language models excel at reasoning but struggle with factual grounding, leading to materials–property hallucinations where models estimate values rather than compute them.
From a terminal prompt like "Suggest a new Na-ion battery cathode", the system computes capacity (193 mAh/g) and voltage (3.7 V) in ~90 seconds—despite having no pre-coded battery workflows. The agent reasons about which fundamental calculations to chain together, then derives electrochemical properties.
The system orchestrates established tools (SMACT for compositional screening, Chemeleon for structure generation, MACE foundation models for energy calculations, PyMatGen for stability analysis), while enforcing that every numerical value must trace to explicit tool invocations, with audit trails showing which calculation produced each result.
The goal is both to leverage LLM creativity and accelerate computational aspects of materials design, so scientists can focus their effort on the challenging discovery questions. This is early work and a proof-of-concept framework that makes advanced computational methods feel as natural as starting with a written prompt.
Preprint: Crystalyse: a multi-tool agent for materials design
Code: github.com/ryannduma/CrystaLyse.AI
July 20th, 2025 — Update: CrystaLyse.AI, our agentic materials design tool, is now available in limited research preview.
CrystaLyse.AI lets materials scientists delegate substantial computational materials design tasks directly from their terminal. In early testing, CrystaLyse completed materials discovery workflows in minutes that would normally take s few days of manual computational work. With CrystaLyse.AI, our goal is to better understand how researchers approach materials design and to help build a tool that accelerates their workflows and focuses their energies towards the challenging materials discovery frontiers.