Search Results for "software without code" - Page 12

This project provides some hyperheuristics, implemented as C libraries. A hyperheuristic can be used to handle any optimization problem, as long as you implement some simple specific code to interact with it. Some examples/applications are also provided.

MultiBoost is a C++ implementation of the multi-class AdaBoost algorithm. AdaBoost is a powerful meta-learning algorithm commonly used in machine learning. The code is well documented and easy to extend, especially for adding new weak learners.

Hippal is an integrating GUI-framework for a multimodular symbolic A.I.-system IPAL, which combines A.I. Planning, Inductive Program Synthesis, Analogical Reasoning and Learning. Hippal is client-/server-based and uses the Lili Lisp Interpreter as Centr

Metaprogramming: proof of the concept.

neuralnetgen is intended to be a universal neural net generator that receives a neural net description (on Neural Net Description Language, also developed on this project) and generates ANSI C code of a library that implements it.

8. Mai 2005: We have discontinued SourceForge as a download place for our open source projects. You can now download these projects directly from the XLOG Technologies GmbH web site at http://www.xlog.ch/omonia.

The Language Processing Agency provides agents and an agent-oriented infrastructure for developing language processors in .NET. Typical language processors are transformation tools, extraction tools, language interpreters, etc.

Spiritbot is a suite of tools designed for use in software-engineering, CodeGenUML includes an XMI/MOF/UML reader and exporter. An IRC ticker bot is also provided to aid in the development process.

Set of Java packages to apply Genetic Algorithms to any kind of problem. Various genetic operators are implemented and an example shows of how the system could be applied to digital circuit evolution.

This project is an off-shoot of the EGADSS project. The nature of the changes made to the PD CLIPS code means a separate project would be best. This is an FOSS version of the PD CLIPS Engine to include such features as backwards chaining and more....

Network gaming environment for AI warriors. Offers an application server, a soccer game application, an observer module visualizing a match and a template code for the warriors development.

JEOPS is a Java based forward chaining RULE ENGINE. This Rule Engine is used to power up the business process by rules in Java Application Servers, client applications, and Servlets.

Experiments, etc. tools, frameworks for version control, business rules, persistence, code generation, etc. not an active project these days.

Jaybird is java-language based, source & xml & codebyte class inter-converting tool. You can write your Envolvable Code with it; You can make your computer write program itself; You can run program without compiling time; You can manage source as data

Unit tests-based Genetic Programming in Java. The developer specifies unit tests, and the tool will use GP to evolve software that passes those tests.

myBeasties is a highly flexible evolutionary programming module. It is designed to be extendable and customisable for maximum use by the discerning Perl hacker. Phenotypes can be anything: simple binary strings, or whole classes of objects and methods.

Gnubert will be a system to use the power of many computers across the internet to solve problems using evolutionary techniques. Any user may define a problem and the system will attempt to solve it.

Tourk is a framework for developing programming games, where two (or more) people write game playing code (like Deep Blue) and a controller puts the two against each other.

EvoLab is a genetic programming system written in Java. This project is not active at the moment.

The Python Genetic Programming Project implements a Genetic Programming System a la J Koza in Python.

This is an open source state machine template for C++. Initially FSM support will be given. The purpose is to facilitate developers to create state machine based C++ applications easily.

This Meshula Kernel contains a reactive AI core, a high quality physics simulator, a math library, and assorted utility routines

Leanstral is an open-weight large language model developed by Mistral AI and specifically designed as a code agent for the Lean 4 proof assistant, enabling advanced interaction with formal mathematics and program verification systems. The model is built to understand and generate Lean 4 code, which is used to express complex mathematical constructs as well as formal software specifications. By focusing on theorem proving and formal reasoning, Leanstral represents a specialized direction within large language models, targeting domains that require strict correctness and logical rigor rather than general conversational tasks. ...

...The base Nano architecture uses a hybrid Mamba-Transformer Mixture-of-Experts (MoE) design, allowing the model to activate only a small fraction of its 31.6 billion parameters per token, which improves speed and efficiency without sacrificing quality on complex queries. This configuration supports a massive context length of up to 1 million tokens, making it suitable for long-context reasoning, agentic tasks, extended dialogues, and applications like code generation or document summarization.

Kimi K2.7 Code is a coding-focused agentic model built on Kimi K2.6, designed for long-horizon software engineering, autonomous coding workflows, and complex tool-based execution. It improves end-to-end task completion across real-world programming scenarios while reducing thinking-token usage by about 30% compared with K2.6. Architecturally, it uses a 1T-parameter Mixture-of-Experts design with 32B activated parameters, 61 layers, 384 experts, a 256K-token context window, and a MoonViT vision encoder. ...