# google/TensorNetwork

A library for easy and efficient manipulation of tensor networks.

Repository: https://github.com/google/TensorNetwork
Canonical: https://ross.abutalabs.com/products/tensornetwork
Language: Python
License: Apache-2.0
License Family: permissive
Topics: tensor-networks, matrix-product-states
Archived: true
Last push: 2023-09-04T14:48:58+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2687, "days_push": 1094, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1870, forks 361 (observed 2026-08-28T04:05:46.774692+00:00)

## What it is
TensorNetwork is a Python library for building and contracting tensor networks, with backends for TensorFlow, JAX, PyTorch, and NumPy. It provides a high-level API for tensor manipulation aimed at physics simulations and machine learning research.

## Use cases
- contract tensor networks efficiently
- simulate quantum many-body systems with matrix product states
- build tensor network layers inside neural networks with Keras
- perform SVD-based tensor splitting and truncation
- run tensor calculations on GPU via TensorFlow, JAX, or PyTorch backends

## When to choose
- you need a backend-agnostic tensor network API across TensorFlow, JAX, PyTorch, and NumPy
- you're doing computational physics research involving tensor network contractions
- you want to integrate tensor network layers into machine learning models

## When to avoid
- you need a general-purpose deep learning framework rather than tensor network operations
- you require frequent updates and active development, as the project's release cadence has slowed
- you need production ML tooling rather than research-grade numerical code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, math, sdk
- domain: machine-learning, gpu-computing
- platform: python, cross-platform
- tags: tensor-networks, matrix-product-states, tensorflow, jax, pytorch, numpy, quantum-physics, tensor-contraction, physics, algorithms, gpu

## Member repositories
- google/TensorNetwork (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:46.774692+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:15:05.082237+00:00, confidence not recorded.
  - readme: https://github.com/google/TensorNetwork (fetched 2026-08-28T04:05:46.774692+00:00, sha ea518bbcf69d)
  - registry_pypi: https://pypi.org/pypi/tensornetwork/json (fetched 2026-08-29T10:54:09.380233+00:00, sha 012287085379)
- Data as of 2026-08-30T08:39:29.467469+00:00.