e3nn
Equivariant convolutional neural networks for the group E(3) of 3 dimensional rotations, translations, and mirrors.
Decision gist · record as of 2026-08-14
Yes, if you are building neural networks for 3D geometric or molecular data and need built-in equivariance guarantees. The library is mature enough for research use, has no known vulnerabilities, and low install friction. The aging maintenance status (182 days since last release) is a minor concern for a research tool but not a blocker if your use case aligns with the current API.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- PyTorch must be installed before e3nn; the package requires Python ≥3.8.
- Low friction installation as a pure Python wheel.
- Maintenance status is aging—last release was 182 days ago—but the repository remains active with recent commits and the package supports current Python versions (3.8–3.10).
License · maintenance · safety
MIT (permissive) — MIT license is permissive; you may use, modify, and distribute e3nn freely in commercial and private projects with minimal restrictions.
last release 2026-02-13 (182 days) · last repo commit 2026-02-13 · 1,273 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 532,675 downloads/mo, #6,146 on PyPI
Alternatives
Verify before relying
pip install e3nn
import torch
from e3nn import o3
irreps_in = o3.Irreps("0e + 1o")
x = irreps_in.randn(-1)
linear = o3.Linear(irreps_in=irreps_in, irreps_out=o3.Irreps("2x0e + 2x1o"))
y = linear(x)- Whether opt_einsum_fx is a required runtime dependency or an optional performance enhancement.
- Stability guarantees or API compatibility policy beyond the stated breaking-change versioning scheme.
What it is and what it does
e3nn is a PyTorch library for building neural networks that respect Euclidean symmetries—rotations, translations, and reflections in 3D space. It provides building blocks like equivariant linear layers, tensor products, and spherical harmonics that automatically enforce these symmetries during computation, eliminating the need to manually encode geometric constraints.
The library is designed for researchers and practitioners working with 3D geometric data: point clouds, molecular structures, volumetric data, and other problems where rotational or translational invariance is a natural property of the problem. It depends on PyTorch for computation, sympy and scipy for mathematical operations, and opt_einsum_fx for tensor contraction optimization.
Use it for
- Build neural networks for molecular property prediction that respect 3D rotational symmetry of atomic structures.
- Process point cloud data with layers that automatically handle arbitrary rotations and translations.
- Implement steerable convolutional networks for volumetric data like medical imaging or climate simulations.
- Compose custom equivariant architectures using tensor products and irreducible representations.
- Accelerate geometric deep learning research by reusing tested equivariance operations instead of deriving them from scratch.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building neural networks for 3D geometric or molecular data and need built-in equivariance guarantees.
The library is mature enough for research use, has no known vulnerabilities, and low install friction. The aging maintenance status (182 days since last release) is a minor concern for a research tool but not a blocker if your use case aligns with the current API.
Install
e3nn on PyPI
Before you install
Low friction installation as a pure Python wheel. Maintenance status is aging—last release was 182 days ago—but the repository remains active with recent commits and the package supports current Python versions (3.8–3.10).
PyTorch must be installed before e3nn; the package requires Python ≥3.8.
License in practice
MIT license is permissive; you may use, modify, and distribute e3nn freely in commercial and private projects with minimal restrictions.
Quickstart
pip install e3nn
import torch
from e3nn import o3
irreps_in = o3.Irreps("0e + 1o")
x = irreps_in.randn(-1)
linear = o3.Linear(irreps_in=irreps_in, irreps_out=o3.Irreps("2x0e + 2x1o"))
y = linear(x)Verify before relying
- Whether opt_einsum_fx is a required runtime dependency or an optional performance enhancement.
- Stability guarantees or API compatibility policy beyond the stated breaking-change versioning scheme.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagessympyscipytorchopt_einsum_fx |
| Maintenance | Aging 182 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 532,675 / month, #6,146 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseOperating System :: MacOSOperating System :: POSIXProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9 |
Evidence: e3nn-0.6.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “equivariant neural networks”
- e3nne3nn provides PyTorch-based operations for building E(3)-equivariant…
- mace-torchMACE trains and evaluates machine learning interatomic potentials…
- cuequivariance-torchPyTorch bindings for NVIDIA's CUDA-accelerated library for building…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also e3nn-jax · cuequivariance-torch · cuequivariance · mace-torch · torch-geometric · cuequivariance-ops-cu13 · cuequivariance-ops-torch-cu12 · cuequivariance-ops-cu12 · tesseract · tensorflow-graphics