awesome-neuromorphic

sends event-based data from A to B. AEStream is both a command-line tool an a C++/Python library with built-in GPU-acceleration for use with PyTorch, and Jax. It supports reading and writing from files, event cameras, network protocols, and visualization tools.

Tonic is a tool created by SynSense, to facilitate the download, manipulation and loading of event-based/spike-based data. It's like PyTorch Vision but for neuromorphic data. Tonic provides publicly available event-based vision and audio datasets and event transformations. The package is fully compatible with PyTorch Vision/Audio, giving you the flexibility you need.

Brain-inspired neural architecture implementing excitation-inhibition tension dynamics between expert groups. Models neural agonist-governor balance in transformers. Part of the TECS-L consciousness framework.

multi-compartment neuron simulation library; compatible with next-generation accelerators; best-practices applied to research software; focussed on community-driven development.

Simulator for recurrent spiking neural networks with synaptic plasticity.

Python package used for simulating spiking neural networks (SNNs) on CPUs or GPUs using PyTorch Tensor functionality. BindsNET is a spiking neural network simulation library geared towards the development of biologically inspired algorithms for machine learning.

BrainCog is an open source spiking neural network based brain-inspired cognitive intelligence engine for Brain-inspired Artificial Intelligence and brain simulation. The current version of BrainCog contains at least 50 functional spiking neural network algorithms including perception and learning, decision making, knowledge representation and reasoning, motor control, social cognition, etc. BrainCog also provide brain simulations to drosophila, rodent, monkey, and human brains at multiple scales based on spiking neural networks at multiple scales.

Brian is a simulator for spiking neural networks. It is written in the Python programming language and is available on almost all platforms. We believe that a simulator should not only save the time of processors, but also the time of scientists. Brian is therefore designed to be easy to learn and use, highly flexible and easily extensible.

Analog machine learning chips for the lowest always-on system power.

Akida NPU.

Brian2-based Loihi simulator. The neuron and synapse model results in an exact match to Loihi, the pre- and post-synaptic traces have very small variations from the Loihi chip due to stochastic rounding.

Paper.

neuromorphic microcontroller built for real-time intelligence at the sensor edge. Delivering brain-like efficiency in a milliwatt power envelope, it enables always-on, responsive devices across wearables, IoT, and industrial systems.

models, modules, algorithms and applications developed by the INRC Community using nxsdk to run on the Intel Loihi Platform. Archived. Not supported by Intel now.

Computational Neuro Science repository.

Big articles list.

Official site.

Projects code.

Official site.

Official site.

Official site.

Official site.

Framework for computational neuroscience and brain-inspired computation based on the Just-In-Time (JIT) compilation (built on top of JAX, Numba, and other JIT compilers). It provides an integrative ecosystem for brain dynamics programming, including brain dynamics building, simulation, training, analysis, etc.

Dynamic Animation and Robotics Toolkit.

list with robotics simulation tools in Unity.

set of computational primitives, shared across different neuromorphic frameworks and technology stacks. Currently supported by 9 simulators and 5 hardware platforms, allowing users to seamlessly move between any of these platforms. Reference implementation was written in Python, can save network structure (also supports layers) and events activity.

turn NIR definitions into a nice graph, the original publication serving as a template.

Scalable Open Data Format for multiscale neuronal network models and simulation output, jointly developed by the Allen Institute for Brain Science (AIBS) and the Blue Brain Project (BBP) of the École polytechnique fédérale de Lausanne (EPFL). The design and architecture of SONATA builds on both organizations’ expertise with large-scale high-performance network simulation, visualization and analysis. JSON, CSV used for metadata, HDF5 used for data.