For getting your toolbox here, contact Herbert Jaeger or Benjamin Schrauwen

ESNJava1.0.4: Java Echo State Networks from the Cognitive Modeling group (Univ. Tübingen)

A Java implementation of  Echo State Networks with a comfortable GUI,  advanced features for experimentation and visualization, and a detailed documentation, contributed by the Cognitive Modeling group (Martin V. Butz) from the University of Tuebingen. 

PCSIM: Parallel Simulator for Neural Circuits

PCSIM is a tool for simulating heterogeneous networks composed of different model neurons and synapses. This simulator is written in C++ with a primary interface to python. It is intended to simulate networks containing up to millions of neurons and on the order of billions of synapses. Developed at Wolfgang Maass' group in Graz.

The AURESERVOIR C++ library for Reservoir Computing

Efficient C++ library fro analog reservoir computing neural networks (Echo State Networks). Written by Georg Holzmann at Graz University. 

Simple and very simple Matlab toolbox for Echo State Networks

Herbert Jaeger and group members have written (in Matlab) a simple and a very simple toolbox for Echo State Networks, mainly for didactic purposes and quick experiments.

NEST Spiking Network Simulator

NEST ( is a computer program for simulating large heterogeneous networks of point neurons, and has been used (among other biological modeling tasks) for simulating Liquid State Machines. It is developed by the NEST Initiative and is available free of charge as source code.

OrGanic Environment for Reservoir computing (OGER) toolbox

The OrGanic Environment for Reservoir computing (Oger) toolbox is a Python toolbox for rapidly building, training and evaluating modular learning architectures on large datasets. It is the most comprehensive reservoir computing toolset available today, is built on the basis of the MDP toolbox, and provides the computational infrastructure to the FP7 project ORGANIC.

Minimalistic self-contained ESN examples

Educational minimalistic ESN demo programs with a classical task of learning to generate/predict a Mackey-Glass chaotic attractor in Python, Matlab, and R are available at They are commented one-page self-contained source codes not using any reservoir computing or machine learning specific toolboxes.