Menu

Spiking network software in 2026

The open-source software for spiking neural networks in 2026: what each tool is for, its licence, and how a model reaches a chip

Review · NeuromorphicNovember 22, 2026Senova Systems Research

A neuromorphic chip is only as useful as the software that trains and loads it. We read the READMEs, licence files and release records of eleven open-source projects: which ones train networks, which ones simulate brains, which ones target hardware, how models move between them, and the licence terms that matter if you build a product.

Why the software matters

A spiking neural network is trained on an ordinary computer and then run somewhere else: on a CPU, a GPU or a neuromorphic chip. The tools in between decide what you can build. They decide which neuron models you can use, how you train them, whether the result can be loaded onto a chip, and on what licence terms you can ship it.

This piece is a map of those tools as they stand in November 2026. Every fact comes from a project's own README, licence file or release record on PyPI, read on 22 November 2026. The descriptions are the projects' own words, summarised. We have not benchmarked these libraries against each other, so there are no speed or energy figures here.

Three kinds of tool

Training libraries treat spiking neurons as layers in a deep learning framework, so you can train a network with gradient descent on a GPU. snnTorch, Norse, SpikingJelly and Sinabs build on PyTorch. Spyx builds on JAX and Flax NNX. Rockpool offers layers backed by PyTorch, JAX or Brian.

Simulators come from neuroscience. They model how networks of neurons behave over time, rather than training them for a task. Brian 2 describes itself as a clock-driven simulator written in Python. NEST focuses on the dynamics, size and structure of neural systems. NEST's README says it runs from a laptop to the largest supercomputers and was first released in 1994 (as SYNOD).

Hardware toolchains turn a trained network into something a chip can run. Intel's Lava and Lava-DL targeted the Loihi chips. Two SynSense projects target the company's own chips: Rockpool for Xylo, and Sinabs for Speck and DYNAP-CNN.

The projects we read, as of 22 November 2026. Release dates are the upload dates of the latest version on PyPI.
ProjectWhat it is forBuilt onLicenceLatest release
snnTorchTraining spiking networks with gradientsPyTorchMIT1.0.0, June 2026
NorseDeep learning with spiking networksPyTorchLGPL-3.01.1.0, March 2024
SpikingJellyLarge-scale training and inference, conversion from ordinary networksPyTorchApache-2.02.0.0, October 2026
SpyxCompact training libraryJAX, Flax NNXMIT1.0.0, July 2026
SinabsSpiking convolutional networks, deployment to DYNAP-CNN and Speck chipsPyTorchApache-2.03.1.3, February 2026
RockpoolSignal processing with spiking networks, deployment to Xylo chipsPyTorch, JAX or BrianAGPL-3.0 or later3.1.0, July 2026
LavaBuilding applications for neuromorphic hardware (archived)PythonBSD-3-Clause and LGPL-2.1 or later0.10.0, August 2024
Lava-DLTraining and deploying event-based deep networks (archived)PyTorchBSD-3-Clause0.6.0, August 2024
Brian 2Simulating spiking networksPythonCeCILL-2.12.11.0, October 2026
NESTSimulating large networks of spiking neuronsPython interface or stand-alone programGPL-2.0 or later3.10.0, June 2026
NIRA shared format for moving models between toolsPythonBSD-3-Clause1.0.8, July 2026

How the training libraries train

A spike is all or nothing, so it has no useful slope for gradient descent. The training libraries work around this in two ways, and the Lava-DL README states the trade-off plainly.

Direct training uses the precise timing of spikes. Lava-DL calls it very accurate and efficient, but slow and costly to train. In practice this means surrogate gradients: during training, the spike's missing slope is replaced with a smooth stand-in. snnTorch ships these stand-ins as a module of their own, so you can swap one for another.

Conversion trains an ordinary network first, then swaps its activations for spiking neurons whose firing rates stand in for the values. It reuses fast, familiar training. The cost, in Lava-DL's words, is that converted networks typically need more time steps to reach an answer than directly trained ones. SpikingJelly lists conversion among its core features. Our own spiking conversion study found the same pattern in simulation: accuracy improved only as the network ran for more time steps.

Some tools add other routes. Spyx offers gradient-free training by neuroevolution alongside surrogate gradients. Lava-DL lists a plug-in for local learning, where each layer learns from its own signal instead of a gradient passed back through the whole network.

A detail that matters on small machines: snnTorch says its neuron models are written as recursive functions, so it does not need to store every neuron's membrane potential over time to compute a gradient. Its README says this keeps networks small enough to train on a CPU where needed.

Moving a model from one tool to another

For years, a network trained in one library could not easily run in another or on a chip from another maker. The Neuromorphic Intermediate Representation (NIR) is a shared set of building blocks that tools can write to and read from. It was conceived at the 2023 Telluride Neuromorphic Workshop and described in a 2024 paper in Nature Communications. Its README says it is supported by 9 simulators and 5 hardware platforms.

Support is not symmetrical. The table below is the README's own list. Lava-DL and SpiNNaker2 read NIR but do not write it, so they are destinations, not sources.

Which tools read and write NIR, from the NIR README (November 2026).
ToolWrites NIRReads NIRHardware it reaches
snnTorchYesYesNone of its own
NorseYesYesNone of its own
SpyxYesYesNone of its own
NengoYesYesNone listed
RockpoolYesYesSynSense Xylo
SinabsYesYesSynSense Speck
hxtorch, jaxsnnYesYesBrainScaleS-2
Lava-DLNoYesIntel Loihi
SpiNNaker2NoYesSpiNNaker2

SpikingJelly is not in that list, but its own README links tutorials for NIR exchange, Lava exchange and deployment to Lynxi chips. A shared format is a real step, but it describes the network, not how a given chip will run it. Chips can differ in the neuron types and number formats they support, so a moved model still has to be checked on the target.

The licence terms that matter for a product

If you only do research, most of these licences will not get in your way. If you ship a product, they differ a lot. This is a summary for engineers, not legal advice.

Permissive licences: snnTorch and Spyx (MIT), SpikingJelly and Sinabs (Apache-2.0), Lava-DL and NIR (BSD-3-Clause). SpikingJelly's licence guide sums up what Apache-2.0 allows: research, commercial use, change and redistribution, on the licence's terms.

Copyleft licences, which attach conditions to sharing changed or combined code: Norse is LGPL-3.0, NEST is GPL-2.0 or later, Brian 2 uses CeCILL-2.1, and Rockpool is AGPL-3.0 or later. Rockpool's README says commercial licences are available on request.

Mixed: the Lava licence file puts the core, processes, utilities and tutorials under BSD-3-Clause, and the compiler and runtime under LGPL-2.1 or later. Its README calls the framework permissively licensed, so read the licence file, not only the summary.

Read the full terms, or ask a lawyer, before a copyleft library ends up inside something you sell.

SpikingJelly moved to Apache-2.0 for its version 2. Its licence guide says that older tags and published releases keep their original licensing records, so check which version you install.

Maintenance is a risk to plan for

Intel's Lava and Lava-DL repositories are archived. The READMEs say Intel will not provide maintenance, bug fixes or new releases, and that Intel is developing a new SDK for its next-generation Loihi chip, built on open-standard AI frameworks. Code written for Lava today has no maintained path forward from Intel.

Release records tell a mixed story elsewhere. SpikingJelly, Brian 2, Rockpool, snnTorch, Spyx, NIR and NEST all published releases in 2026. Norse's latest release on PyPI is from March 2024; its repository may hold newer code, but there is no newer packaged release.

What we use, and what we have not done

Our simulation studies use none of these libraries. They are written in plain JavaScript with no dependencies and fixed random seeds, so anyone can re-run them and get the same numbers. That is right for small studies and wrong for anything larger.

We have not benchmarked these tools against each other, trained the same network in each, or run any of them on neuromorphic hardware.

Sources

  1. snnTorch README (project README)
  2. snnTorch MIT licence file
  3. snnTorch release record on PyPI
  4. Norse README (project README)
  5. Norse LGPL-3.0 licence file
  6. Norse release record on PyPI
  7. SpikingJelly README and licence guide (project README)
  8. SpikingJelly Apache-2.0 licence file
  9. SpikingJelly release record on PyPI
  10. Spyx README (project README)
  11. Spyx MIT licence file
  12. Spyx release record on PyPI
  13. Sinabs README (vendor README, SynSense)
  14. Sinabs Apache-2.0 licence file
  15. Sinabs release record on PyPI
  16. Rockpool README (vendor README, SynSense)
  17. Rockpool AGPL-3.0 licence file
  18. Rockpool release record and licence classifier on PyPI
  19. Lava README and archive notice (vendor README, Intel)
  20. Lava licence file (BSD-3-Clause and LGPL-2.1 or later)
  21. Lava-DL README and archive notice (vendor README, Intel)
  22. Lava-DL BSD-3-Clause licence file
  23. Lava release record on PyPI
  24. Lava-DL release record on PyPI
  25. Brian 2 README (project README)
  26. Brian 2 CeCILL-2.1 licence file
  27. Brian 2 release record on PyPI
  28. NEST README (project README)
  29. NEST GPL-2.0 or later licence file
  30. NEST release record on PyPI
  31. NIR README and support table (project README)
  32. NIR BSD-3-Clause licence file
  33. NIR release record on PyPI