Skip to content

Cuequivariance vs Nvmolkit usage

Cuequivariance is an open-source agent skill for health and science. Nvmolkit usage is an open-source agent skill for health and science.

  • Cuequivariance is best for build a fully connected tensor product between two sets of so3 irreps.
  • Nvmolkit usage is best for compute tanimoto similarity across a library of thousands of molecules.
What it is
Cuequivariance is an open-source agent skill for health and science.
Nvmolkit usage is an open-source agent skill for health and science.
Best for
Build a fully connected tensor product between two sets of SO3 irreps
Compute Tanimoto similarity across a library of thousands of molecules
Kind
Skill
Skill
Pricing
Open source
Open source
Platforms
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
GitHub stars
4K
4K
Last commit
Nov 2026
Nov 2026
License
Apache-2.0
Apache-2.0
Open source
Good for
Build a fully connected tensor product between two sets of SO3 irreps; Define a custom Z2 group and check its Clebsch-Gordan covariance; Convert equivariant features between mul_ir and ir_mul layouts
Compute Tanimoto similarity across a library of thousands of molecules; Generate and minimize many conformers for a set of drug-like molecules; Cluster a conformer ensemble by heavy-atom RMSD using Butina

What Cuequivariance does

  • Irreps and layouts

    Defines irreducible representations and multiplicities for built-in or custom groups, with memory layout control.

  • Segmented tensor products

    Builds contractions over segments of varying shape linked by Clebsch-Gordan path coefficients.

  • Descriptor constructors

    Provides ready-made equivariant layers such as fully connected and channelwise tensor products, linear maps and spherical harmonics.

  • Custom group definitions

    Shows how to subclass the Irrep base class with selection rules, generators and Clebsch-Gordan coefficients.

  • NumPy validation workflow

    Gives steps to check shapes, equivariance and layout conversions on a small CPU example.

  • Troubleshooting guide

    Lists common failures such as wrong operand sizes, layout mismatches and custom-group equivariance errors.

What Nvmolkit usage does

  • Batched fingerprints and similarity

    Covers Morgan fingerprint generation and bulk Tanimoto or cosine similarity matrices on the GPU.

  • Conformer embedding and minimization

    Describes ETKDG embedding and MMFF or UFF optimization across batches of conformers.

  • Clustering and RMSD workflows

    Shows conformer RMSD matrices, Butina clustering and atom-atom path DISE clustering.

  • Substructure and MCS search

    Explains batched substructure matching and maximum common substructure search with pair modes.

  • GPU result handling

    Explains asynchronous results, synchronization, CUDA streams and device-resident outputs.

  • Install verification and limits

    Includes a smoke test, backend selection guidance and a list of unsupported options.

Cuequivariance vs Nvmolkit usage: questions

Is Cuequivariance or Nvmolkit usage cheaper?

Both are open source. Compare current plans on each official site.

What is the difference between Cuequivariance and Nvmolkit usage?

Cuequivariance is an open-source agent skill for health and science. Nvmolkit usage is an open-source agent skill for health and science.

Keep comparing