Axon SDK

Python Toolkit for Spiking Neural Networks and general purpose Neuromorphic Computing

Overview

Axon SDK is a Python simulation toolkit for spiking neural networks (SNNs). Instead of mimicking biology through conventional neuron models, it leverages the STICK (Spike Time Interval Computation Kernel) framework to represent and execute any algorithm through precise spike timing. This makes it possible to map symbolic or control-oriented computation into spiking time-coded dynamics.

The project aims to overcome the von Neumann bottleneck by shifting computation to neuromorphic principles where information and processing are tightly interwoven in time. By providing a framework that structures non-neural algorithms into spike-based representations, Axon SDK brings computation closer to truly general-purpose neuromorphic platforms. It also addresses issues where current neuromorphic hardware pipelines still depend on external digital preprocessing (e.g., noise filtering in DVS vision), which creates latency and energy inefficiencies.

Axon SDK is developed and maintained by Neucom, a Denmark-based startup focused on building general-purpose neuromorphic computing platforms.

Axon SDK logo

Axon SDK

GitHub Release GitHub Stars
Maintainer(s):
Neucom
Language:
Python
License:
GPL-3.0
Application:
Neuromorphic Computing
Dependencies:
Numpy

Help Improve this Software Guide

Our software guide is maintained by the community. If you have updates, see an error, or want to suggest a new tool, please let us know by opening an issue on our GitHub repository.