danielegrattarola/spektral
Graph Neural Networks with Keras and Tensorflow 2. observed · 2026-08-28
Health v2 · maintenance only
23/100
- Activity 0
- Release rhythm 8
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2785
- days_rel: n/a
- days_push: 955
- n_releases_24m: 0
Adoption not part of the score
2396 stars · 343 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
Spektral is a Python library for graph deep learning built on the Keras API and TensorFlow 2. It provides popular graph neural network layers (GCN, GAT, GraphSAGE, GIN, etc.), pooling layers, and utilities for representing and transforming graph data.
Use cases
- build graph neural networks with keras
- classify nodes in a social network graph
- predict molecular properties with GNNs
- cluster nodes in a graph
- predict links between entities
- generate new graphs with GANs
- implement GCN or GAT models in tensorflow
When to choose
- you want GNN layers that integrate natively with Keras and TensorFlow 2
- you need ready implementations of popular graph convolutions and pooling layers
- your data is naturally represented as graphs and you work in Python
When to avoid
- you prefer PyTorch-based GNN frameworks like PyTorch Geometric
- you need very recent GNN research implementations or active development
- your project does not use TensorFlow
Facets
library · maturity maintenance
deep-learning machine-learning sdk deep-learning machine-learning graph-processing python windows graph-neural-networks gnn keras tensorflow2 graph-convolutions graph-pooling linux macos
5 sources
- readme: https://github.com/danielegrattarola/spektral · fetched 2026-08-28 · 4017071ef144
- homepage: https://graphneural.network · fetched 2026-08-29 · 0816ee45590e
- site_page: https://graphneural.network/getting-started · fetched 2026-08-29 · bba074e55521
- site_page: https://graphneural.network/about · fetched 2026-08-29 · 7fd984ea765d
- registry_pypi: https://pypi.org/pypi/spektral/json · fetched 2026-08-29 · f34733776029
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| danielegrattarola/spektral | main | 23 |
For agents
markdown · JSON · MCP: product_card(name="danielegrattarola/spektral")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem