Build large-scale neural systems
Nengo is a complete neural simulator, running models with deep learning, online learning, static weights, simple linear neurons, complex spiking neurons, and everything in-between.
You can use Nengo to implement pretty much anything: DNNs, CNNs, attractor networks, adaptive motor controllers, SLAM networks, cognitive systems, you name it. It’s used in industry and academia to develop state-of-the-art neural networks.
Nengo is unique in its ability to put your neural application on a wide variety of hardware – including the latest neuromorphic hardware. Compile your model to run on CPUs, GPUs, FPGAs, supercomputers running MPI, the latest Loihi neuromorphic chip from Intel, or research neuromorphic chips like SpiNNaker.
Nengo is free for individuals and academic research. For commercial licenses, please contact us.
8 different hardware backends
Built-in AI libraries
Explore dozens of examples and tutorials based on the principles of the Neural Engineering Framework.
Start working with Nengo today! Explore the code and follow the project on Github.
Nengo is free to try for individuals and academic research. To discuss a commercial license, contact us today.
Solve problems with custom Nengo solutions
Let us build a backend for your neuromorphic hardware. You will gain access to hundreds of Nengo models that can be immediately deployed in your ecosystem.
New neuromorphic tools
Let us extend Nengo to include a new tool for your team. Automate model building, convert non-spiking to spiking networks, visualize complex time-varying data and more.
Nengo was used to create Spaun, the world’s largest functional brain model, combining many different kinds of models into a single comprehensive whole. It can see, write, reason, and follow simple commands. Spaun has been featured in hundreds of media stories from around the world. Right now we consider it research, but it hints at the power and flexibility of Nengo.