← Protein structure & design

OriDynamics

OriDynamics is a protein structure & design tool whose code is published by LG-FrontierAI on GitHub, first public in 2026. Generative model that samples all-atom conformational ensembles for protein monomers, protein–ligand complexes and protein–protein assemblies, from sequences plus MSAs (an input structure is optional; a Protenix cofolding backbone predicts one).

Visit website ↗

CategoryProtein structure & design
Developer (GitHub)LG-FrontierAI
TaskAll-atom conformational ensemble generation for protein monomers, protein–ligand and protein–protein complexes, including alternative functional states and ligand-dissociation configurations
GitHubLG-FrontierAI/oridynamics
Released2026-11-09 (source)
Code licenseApache-2.0
Weights licensecheckpoints ae.ckpt and oridynamics.ckpt on Hugging Face also tagged Apache-2.0
What this allowsPermissive (commercial OK)
Use, modify and ship it inside closed-source commercial products; keep the license text and copyright notices. What do these mean?
License sourcehuggingface.co/LG-FrontierAI/oridynamics · checked 2026-11-13
PricingOpen source
Tags#dynamics#ensembles#generative#protein-ligand#protein-protein
Last checked · links verified

Can I use OriDynamics commercially?

Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices.

What the license types mean · not legal advice.

Specs

TaskAll-atom conformational ensemble generation for protein monomers, protein–ligand and protein–protein complexes, including alternative functional states and ligand-dissociation configurations
Modalities—
MSA required—
Open weightsReleased on Hugging Face (LG-FrontierAI/oridynamics: ae.ckpt, oridynamics.ckpt), Apache-2.0
GPU need—
GitHub stars16
Interface—

Compare with…

Pick 1–3 other Protein structure & design tools to compare side by side with OriDynamics.

Select 1–3 tools

Related

AlphaFold 2

DeepMind's open-source protein structure prediction model (monomer and multimer).

Protein structure & designOpen sourcePermissive (commercial OK)#structure

Structure prediction of proteins, nucleic acids, ligands and their complexes; hosted web server plus open code, weights on request for non-commercial use.

Protein structure & designNo cost (research use)Mixed (code vs weights differ)#structure

Boltz

Open biomolecular interaction models (Boltz-1, Boltz-2) for complex structure and binding-affinity prediction.

Protein structure & designOpen sourcePermissive (commercial OK)#structure