Matlantis Integrates Claude Code Into Its Atomistic Simulation Platform, Launches Public Skills Library on GitHub

(SeaPRwire) –   This new integration enables researchers to create, edit, and run simulations via natural language, extending access to advanced computational chemistry for non-specialists

CAMBRIDGE, Mass. and TOKYO, May 27, 2026 — Matlantis, a leading provider of AI-powered atomistic simulation solutions for industrial materials R&D, today announced a new AI agent integration for its universal atomistic simulator that allows researchers to build and run simulations using natural language instructions. This launch includes a public Skills library hosted on GitHub, available immediately, plus an upcoming installer that will run Anthropic’s Claude Code directly within the Matlantis terminal environment.

Atomistic simulation has long required a combination of computational chemistry knowledge, programming fluency, and environmental expertise, a barrier that has limited the technology to specialists even as other parts of materials R&D have become more cross-functional. Matlantis has already removed much of the infrastructure hurdles by offering its high-precision AI model, PFP (Preferred Potential), as a cloud service. This new release addresses the final remaining barrier: the scripting layer that lies between a researcher’s query and a functional simulation.

This integration arrives as AI agents are transitioning from experimental use to production deployment across technical workflows. By embedding Claude Code inside Matlantis and granting it access to a domain-specific Skills library, Matlantis is connecting general-purpose AI agent capabilities to the specialized procedures and APIs that simulation work actually requires.

“Simulation has always had three core barriers: infrastructure, scientific expertise, and scripting. We’ve spent five years removing the first one,” said Daisuke Okanohara, President & CEO, Matlantis. “This release focuses on removing the third, and it will change which teams can reliably perform atomistic simulation within an R&D organization.”

A public Skills library, available now

The Skills library, published on GitHub, bundles Matlantis-specific knowledge—including functions, APIs, and standard workflows—into a format that general-purpose AI agents can load and reference. This gives agents access to specialized expertise not present in their base training data, allowing them to generate more accurate, context-aware simulation scripts on their first attempt. Initial workflows include structure relaxation, molecular dynamics, reaction pathway exploration, crystal structure prediction, visualization, and retrieving structures from external databases. The library will expand as customer use cases evolve over time.

Claude Code, embedded in the simulation environment

An installer scheduled for release in a forthcoming platform update will let users launch Anthropic’s Claude Code directly from the Matlantis terminal. Running the agent within the same workflow context means researchers can describe their desired simulation in plain language, generate or edit the underlying scripts, run the calculation, and interpret outputs—all without leaving their current work process. For experimental researchers who lack programming fluency, this opens up simulation as a practical tool. For computational specialists, it eliminates the repetitive scripting work that typically sits between forming a hypothesis and achieving results.

What it changes for R&D teams

Experimental researchers can now generate and interpret simulations through conversation instead of writing code. Computational chemistry specialists can reduce the time spent reproducing published analyses, screening candidates, and adapting workflows for new systems, adopting a “try first, analyze second” workflow. R&D leaders gain the ability to apply computational methods to a broader range of research topics, including questions that were previously deprioritized because they did not justify the specialist time required to set them up.

“Matlantis already enables non-specialists to predict material behavior with high accuracy and speed,” said Okanohara. “With AI agents now serving as a practical interface for complex tools, we can close the remaining gap between a researcher’s question and a running simulation. Our goal is to make undiscovered physical world knowledge as accessible through natural language as knowledge in the textual world has become.”

Availability

The Matlantis Skills library is available now on GitHub. The installer that enables Claude Code to run inside the Matlantis terminal environment will be released in a forthcoming update. For more information, visit matlantis.com.

About Matlantis

Jointly developed by PFN and ENEOS, Matlantis is a universal atomistic simulator that supports large-scale material discovery by replicating new materials’ behavior at the atomic level on a computer. PFN and ENEOS integrated a deep learning model into a conventional physical simulator to boost simulation speed by tens of thousands of times while supporting a wide variety of materials. Matlantis launched in July 2021 as a cloud-based software-as-a-service offering from Matlantis Corp. (formerly named Preferred Computational Chemistry), a company jointly invested by PFN, ENEOS and Mitsubishi Corporation.

Matlantis is used by over 150 companies and organizations to discover various materials including catalysts, batteries, semiconductors, alloys, lubricants, ceramics and chemicals. For more information, please visit: https://matlantis.com/en/.

Media Contact:
Emily Townsend
Scratch Marketing + Media for Matlantis
matlantis@scratchmm.com