Aitomistic Logo
Atomistic simulations — Powered by AI

Elevate your aitomistic simulations

Launch Aitomistic Hub

About Us

Aitomistic delivers cutting-edge AI solutions for atomistic simulations, based on many-year research of the company's experts in quantum chemistry, machine learning, and computational science. Founded on the pioneering vision of field leaders, we empower researchers with state-of-the-art tools that make simulations accurate, fast, and trustworthy—while ensuring accessibility and ease of use.

Our mission extends beyond software: we provide customizable solutions, from private installations on high-performance clusters to a user-friendly browser-based platform ideal for education and collaboration. Additionally, we offer tailored training programs—workshops and courses designed to accelerate adoption and mastery of our technology.

Every tool we develop adheres to the highest standards of scientific rigor, bridging the gap between advanced research and practical, scalable applications.

Products

Aitomistic Hub

Aitomistic Hub

Aitomistic Lab

Aitomistic Lab

Models

Aitomic

Agents

Aitomic

News

2026-09-06

Full lecture: from ML potentials to agents that write the paper — AI for computational chemistry

Prof. Pavlo O. Dral gave the AI lecture at the 2026 International Workshop on Chemical Bonding and AI in Chemistry on 29 August — organised by the College of Chemistry and Chemical Engineering at Xiamen University and the Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, and held online over three evenings. Our thanks to the organisers for sharing the video and permitting its reuse.

News image

2026-08-28

MLatom 3.25: fine-tune the universal machine learning potentials on your own data

In MLatom 3.25 the whole family — ANI, AIQM1, AIQM2, AIQM3, UAIQM, OMNI-P1 and OMNI-P2x — fine-tunes through the same train() call, with dispersion declared once and handled on both sides. On ethanol, thirty-five training geometries close AIQM2's gap to its target from 1.37 to 0.67 kcal/mol, in ten to thirty seconds a run.

News image

2026-08-21

Science Done on a Machine by a Machine: AI Agents in Computational Chemistry

A Perspective surveying 49 agentic systems for computational chemistry to a cutoff of 8 August 2026: what they do, how much of a study each is handed, what runs them, how much of it a reader can actually obtain — and where this is heading.

News image

2026-08-03

MLatom: one-line install, and a more permissive licence

MLatom 3.24.0 installs with a single pip command and is now released under the Apache License 2.0.

News image

2026-07-15

Find a transition state — just by chatting (Protomia 2.6.0)

One prompt → NEB path → the TS → imaginary mode → IRC → the reaction energy diagram.

News image