# google-deepmind/jraph

A Graph Neural Network Library in Jax

Repository: https://github.com/google-deepmind/jraph
Canonical: https://ross.abutalabs.com/products/jraph
Homepage: https://jraph.readthedocs.io/en/latest/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: graph-neural-networks, jax, machine-learning, deep-learning
Archived: true
Last push: 2024-03-18T13:56:39+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2109, "days_push": 898, "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 1474, forks 106 (observed 2026-08-28T04:04:49.717961+00:00)

## What it is
Jraph is a lightweight Graph Neural Network library built on JAX, providing a GraphsTuple data structure, graph utilities, and a zoo of forkable GNN models. It integrates with Haiku or Flax for parameter management and supports distributed training of large graphs.

## Use cases
- train graph neural networks in jax
- batch and pad variable-sized graphs for jit compilation
- run message passing neural networks on molecules
- distribute large graph networks across multiple devices
- learn graph neural networks with tutorials

## When to choose
- you use JAX and need GNN primitives you can fork and adapt
- you want lightweight graph data structures and utilities without a heavy framework
- you need to scale large MPNNs across devices with pmap

## When to avoid
- you want a framework that manages model parameters for you
- you need PyTorch or TensorFlow GNN support
- you need actively developed features with frequent releases

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, graph-processing
- platform: python, cross-platform
- tags: graph-neural-networks, jax, message-passing, graphs, gpu

## Member repositories
- google-deepmind/jraph (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:49.717961+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 2026-08-30T04:34:33.644239+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/jraph (fetched 2026-08-28T04:04:49.717961+00:00, sha c74ad85491a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.