NVIDIA ALCHEMI: AI Lab for Chemical and Materials Innovation
NVIDIA ALCHEMI is a collection of domain-specific NVIDIA NIM™ microservices and a toolkit for accelerating chemical and materials discovery for diverse use cases, such as battery materials, catalysts, organic light-emitting diodes (OLEDs), and beauty products.
Discovery in these areas is historically slow and costly due to the trial-and-error nature of experimentation. Traditional computational chemistry methods are either not accurate enough or too computationally expensive.
By accelerating AI-enabled atomistic simulation at the machine learning framework level, ALCHEMI enables researchers and developers to achieve performant simulations at near-quantum chemistry accuracy, speeding up chemical and materials discovery.
How ALCHEMI Works
NVIDIA ALCHEMI delivers capabilities across three integrated layers:
- ALCHEMI NIM microservices: A scalable layer of cloud‑ready, domain‑specific microservices for chemistry and materials science, enabling deployment and orchestration on NVIDIA‑accelerated platforms
- ALCHEMI Toolkit: A collection of GPU-accelerated simulation building blocks, including geometry optimizers, integrators, and data structures, to enable large-scale, batched simulations with AI
- ALCHEMI Toolkit-Ops: A repository of GPU-accelerated, batched common operations for AI-enabled atomistic simulation tasks, such as neighbor list construction, DFT-D3 dispersion corrections, and long-range electrostatics
ALCHEMI NIM is intended for researchers who need atomistic simulation at near-quantum chemistry accuracy to inform chemical and materials discovery. ALCHEMI Toolkit and Toolkit-Ops are intended for community code, independent software vendor (ISV), and startup developers training machine learning interatomic potentials (MLIPs) and building accelerated batched MLIP atomistic simulation engines.
Get Started With ALCHEMI
ALCHEMI NIM
Scalable, cloud‑ready microservices for chemistry and materials science
Coming Soon
ALCHEMI Toolkit
Modular training, simulation, and active learning workflows
Download on GitHubRead DocumentationInstallation With PyPI
pip install nvalchemi-toolkit
Installation With uv
uv venv --seed --python 3.12 && source .venv/bin/activate uv pip install nvalchemi-toolkit
ALCHEMI Toolkit-Ops
GPU-accelerated, batched kernels for AI-enabled atomistic simulation
Installation With PyPI
pip install nvalchemi-toolkit-ops
Installation With Conda
conda create -n nvalchemi python=3.12 pip conda activate nvalchemi pip install nvalchemi-toolkit-ops
uv venv --seed --python 3.12 uv pip install nvalchemi-toolkit-ops
Starter Kits
ALCHEMI NIM
Access cloud‑ready, domain‑specific microservices for chemistry and materials science to deploy and orchestrate on NVIDIA‑accelerated platforms.
ALCHEMI Toolkit
Create your own custom simulation workflows with GPU-accelerated building blocks, including geometry optimizers, integrators, and data structures.
ALCHEMI Toolkit-Ops
Leverage GPU-accelerated, batched common operations for AI-enabled atomistic simulation tasks, such as neighbor list construction, DFT-D3 dispersion corrections, and long-range electrostatics.
