• Github repository: https://github.com/isayevlab/aimnetcentral/
• Documentation https://isayevlab.github.io/aimnetcentral/

• Accurate and Versatile: AIMNet2 excels at modeling neutral, charged, organic, and elemental-organic systems.
• Flexible Interfaces: Use AIMNet2 through convenient calculators for popular simulation packages like ASE and PySisyphus.
• Flexible Long-Range Interactions: Optionally employ the Damped-Shifted Force (DSF) or Ewald summation Coulomb models for accurate calculations in large or periodic systems.

AIMNet2 requires Python 3.11 or 3.12.

AIMNet2 works on CPU out of the box. For GPU acceleration:

• CUDA GPU: Install PyTorch with CUDA support from pytorch.org
• compile_mode: Requires CUDA for ~5x MD speedup (see Performance Optimization)

Example PyTorch installation with CUDA 12.4:

pip install torch --index-url https://download.pytorch.org/whl/cu124

X = 0-3 for ensemble members. Ensemble averaging recommended for production use.

Install from GitHub:

pip install git+https://github.com/isayevlab/aimnetcentral.git

AIMNet2 provides optional extras for different use cases:

ASE Calculator (for atomistic simulations with ASE):

pip install "aimnet[ase] @ git+https://github.com/isayevlab/aimnetcentral.git"

PySisyphus Calculator (for reaction path calculations):

pip install "aimnet[pysis] @ git+https://github.com/isayevlab/aimnetcentral.git"

Training (for model training and development):

pip install "aimnet[train] @ git+https://github.com/isayevlab/aimnetcentral.git"

All Features:

pip install "aimnet[ase,pysis,train] @ git+https://github.com/isayevlab/aimnetcentral.git"

For contributors, use uv for fast dependency management:

git clone https://github.com/isayevlab/aimnetcentral.git
cd aimnetcentral
make install
source .venv/bin/activate

from aimnet.calculators import AIMNet2Calculator

# Load a pre-trained model
calc = AIMNet2Calculator("aimnet2")

# Prepare input
data = {
    "coord": coordinates,  # Nx3 array
    "numbers": atomic_numbers,  # N array
    "charge": 0.0,
}

# Run inference
results = calc(data, forces=True)
print(results["energy"], results["forces"])

The calculator returns a dictionary with the following keys:

B = batch size, N = number of atoms

With aimnet[ase] installed:

from ase.io import read
from aimnet.calculators import AIMNet2ASE

atoms = read("molecule.xyz")
atoms.calc = AIMNet2ASE("aimnet2")

energy = atoms.get_potential_energy()
forces = atoms.get_forces()

For periodic systems, provide a unit cell:

data = {
    "coord": coordinates,
    "numbers": atomic_numbers,
    "charge": 0.0,
    "cell": cell_vectors,  # 3x3 array in Angstrom
}
results = calc(data, forces=True, stress=True)

Configure electrostatic interactions for large or periodic systems:

# Damped-Shifted Force (DSF) - recommended for periodic systems
calc.set_lrcoulomb_method("dsf", cutoff=15.0, dsf_alpha=0.2)

# Ewald summation - for accurate periodic electrostatics
calc.set_lrcoulomb_method("ewald", cutoff=15.0)

For molecular dynamics simulations, use compile_mode for ~5x speedup:

calc = AIMNet2Calculator("aimnet2", compile_mode=True)

Requirements:

• CUDA GPU required
• Not compatible with periodic boundary conditions
• Best for repeated inference on similar-sized systems

With aimnet[train] installed:

aimnet train --config my_config.yaml --model aimnet2.yaml

Common development tasks using make:

make check       # Run linters and code quality checks
make test        # Run tests with coverage
make docs        # Build and serve documentation
make build       # Build distribution packages

If you use AIMNet2 in your research, please cite the appropriate paper:

AIMNet2 (main model):

@article{aimnet2,
  title={AIMNet2: A Neural Network Potential to Meet Your Neutral, Charged, Organic, and Elemental-Organic Needs},
  author={Anstine, Dylan M and Zubatyuk, Roman and Isayev, Olexandr},
  journal={Chemical Science},
  volume={16},
  pages={10228--10244},
  year={2025},
  doi={10.1039/D4SC08572H}
}

AIMNet2-NSE: ChemRxiv preprint

AIMNet2-Pd: ChemRxiv preprint

See LICENSE file for details.