myBeasties is a highly flexible evolutionary programming module. It is designed to be extendable and customisable for maximum use by the Perl developer. Many species of genotypes can be evolved, and these can be used to build phenotypes of any size or complexity. These can be as simple as a list or as large as a whole class of objects.
Evolvica is an evolutionary computation framework written in Java. The aim of the project is to provide a toolkit that enables developers to create genetic/evolutionary algorithms with minimal programming effort. The toolkit has a modular architecture and is highly extensible. It includes a visual algorithm editor, a source code editor, and a debugger.
Torch is a machine learning library written in C++ that works on most Unix/Linux platforms. It can be used to train MLPs, RBFs, HMMs, Gaussian Mixtures, Kmeans, Mixtures of experts, Parzen Windows, KNN, and can be easily extended so that you can add your own machine learning algorithms.
Algorithm::Evolutionary is a flexible set of classes for doing evolutionary computation in Perl, integrated with XML for evolutionary algorithm description. So far, it contains classes for doing string, tree, and vector array-based evolutionary computation, several variation operators, and simple population-level algorithms. It has been distributed algorithms using SOAP, and integrated with the DBI and HTML::Mason libraries. It contains an XML dialect for definition of evolutionary algorithms, called EvoSpec; experiments defined using Algorithm::Evolutionary can be completely serialized/deserialized using this language.
PyWordNet is a Python interface to the WordNet database of word meanings and lexical relationships. It presents a concise interface to WordNet, that allows the user to type expressions such as N['dog'], hyponyms(N['dog'] ), and closure(ADJ['red'], SYNONYM) to query the database.
YAKS - Yet Another Khepera Simulator, is a Khepera simulator that uses prerecorded sensor values from a real robot in order to provide simulation speeds of 3600 times reality. It has support for the infrared sensors, light sensors, K213 vision turret, gripper arm, and more. The simulator comes with a GTK interface, a genetic algorithm (GA), and an artificial neural net (ANN).
Jess is a fast, light rule engine and scripting environment written entirely in Java. You can build Java software that has the capacity to "reason" using knowledge you supply in the form of declarative rules. It is supplied as a programmer's library, making it ideal for embedding in larger applications. Jess includes development tools built on the Eclipse platform. It is free for academic use and can be licensed for commercial use.