synsense/rockpool

A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

61
/ 100
Established

Rockpool helps machine learning engineers develop specialized signal processing applications using spiking neural networks (SNNs). You can feed in time-series data or event streams, build your SNN models, train them with familiar deep learning frameworks like PyTorch or JAX, and then deploy them directly to neuromorphic hardware or run them in simulation. This is ideal for developers creating energy-efficient, event-driven AI solutions.

Used by 1 other package. Available on PyPI.

Use this if you are an ML engineer building signal processing applications that require the unique capabilities and efficiency of spiking neural networks, especially for deployment on neuromorphic hardware.

Not ideal if you are doing detailed simulations of biological neural networks or if your project doesn't specifically require spiking neural networks.

neuromorphic-computing spiking-neural-networks edge-ai signal-processing machine-learning-engineering
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

77

Forks

13

Language

Python

License

AGPL-3.0

Last pushed

Feb 10, 2026

Commits (30d)

0

Dependencies

2

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/synsense/rockpool"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.