Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
| Date | Stars |
|---|---|
| 2026-07-24 | 2076 |
| 2026-07-25 | 2076 |
| 2026-07-28 | 2076 |
| 2026-07-30 | 2076 |
| 2026-07-31 | 2083 |
| 2026-08-01 | 2085 |
| 2026-08-02 | 2086 |
| 2026-08-03 | 2086 |
| 2026-08-04 | 2089 |
| 2026-08-05 | 2090 |
| 2026-08-06 | 2091 |
Today
+1 stars today
This week
+15 stars this week
This month
— stars this month
Momentum
19.0
growth rate 0.72%/day
# SpikingJelly
[中文](./README_cn.md) | English
[](https://pypi.org/project/spikingjelly)
[](https://pypi.org/project/spikingjelly)
[](https://spikingjelly.readthedocs.io/zh_CN/latest)
[](https://github.com/fangwei123456/spikingjelly/graphs/contributors)
## Contents
- [Why SpikingJelly](#why-spikingjelly)
- [Installation](#installation)
- [Quick Start](#quick-start)
- [Core Capabilities](#core-capabilities)
- [Backend Performance](#backend-performance)
- [Large-Scale SNN Systems](#large-scale-snn-systems)
- [Datasets](#datasets)
- [Interchange and Deployment](#interchange-and-deployment)
- [Project Status and Version Notes](#project-status-and-version-notes)
- [Acknowledgement](#acknowledgement)
- [Contributing](#contributing)
- [Citation](#citation)
## Why SpikingJelly
SpikingJelly is a PyTorch-native framework for spiking neural networks (SNNs), with support for large-scale SNN training and inference.
- Beginner-friendly API
- ANN2SNN conversion
- Event-based datasets
- Acceleration backends: `torch`, `cupy`, `triton`
- Memory-efficient training, distributed execution, precision control
- Hardware deployment and framework exchange
## Installation
SpikingJelly is built on PyTorch. Install [PyTorch, torchvision, and torchaudio](https://pytorch.org/) first.
- Python `>=3.11`
- PyTorch `>=2.6.0` (tested with `2.7.1`)
Install the latest stable PyPI release:
```bash
pip install spikingjelly
```
Install V2 pre-releases from PyPI when they are published:
```bash
pip install --pre spikingjelly
```
Install the latest development version from source:
```bash
git clone https://github.com/fangwei123456/spikingjelly.git
cd spikingjelly
pip install .
```
Optional dependencies:
| Feature | Install |
| --- | --- |
| CuPy backend | `pip install cupy-cuda12x` or `pip install cupy-cuda11x` |
| Triton backend | `pip install triton==3.3.1` |
| NIR exchange | `pip install nir nirtorch` |
| Lightning integration | `pip install lightning jsonargparse[signatures]` |
## Quick Start
Define an SNN in the same way that you would define any PyTorch model:
```python
from torch import nn
from spikingjelly.activation_based import layer, neuron, surrogate
net = nn.Sequential(
layer.Flatten(),
layer.Linear(28 * 28, 10, bias=False),
neuron.LIFNode(tau=2.0, surrogate_function=surrogate.ATan())
)
```
Next steps:
- [Learn about spiking neurons](https://spikingjelly.readthedocs.io/zh_CN/latest/tutorials/en/neuron.html)
- [Train on event-based datasets](https://spikingjelly.readthedocs.io/zh_CN/latest/tutorials/en/classify_dvsg.html)
- [Convert ANN to SNN](https://spikingjelly.readthedocs.io/zh_CN/latest/tutorials/en/ann2snn.html)
## Core Capabilities
| Area | What SpikingJelly provides |
| --- | --- |
| SNN modeling | Activation-based SNN components: spiking neurons, surrogate gradients, stateful and stateless modules. Predefined SNN models. |
| Training workflows | PyTorch-native training flows, online-learning utilities, and ANN2SNN conversion |
| Performance | `torch`, `cupy`, and `triton` backends, FlexSN for customized neuron kernels, and mixed-precision training utilities (e.g., `fp8`) |
| Scaling | Memory-efficient training, and distributed training |
| Datasets | Neuromorphic datasets, and data preprocessing pipelines |
| Analysis | FLOPs / SynOps / memory-access profiling, and inference energy estimation |
| Interchange and deployment | NIR, Lava, and Lynxi-oriented exchange intExcerpt of 11,497 characters
Read on GitHub
1.8k
624
187
52
35
24
18
11
10
Ridger Zhu · University of California, Santa Cruz
8
8
7
6
6
6
6
5
4
4
4
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:895c4eddd2177c7b, topic:deep-learning, topic:pytorch, desc:deep learning framework