Search Results for "computer adaptive testing"

BruteForceAI is an open-source security testing tool that applies large language models to the analysis of login forms and authentication flows in web applications. At a high level, the project uses AI to inspect HTML content, identify the relevant form elements, and automate selector discovery so that a tester does not need to hand-map every field before evaluation. It combines that analysis layer with automated credential testing workflows, framing itself as a more adaptive alternative to older brute-force tooling that depends heavily on manual configuration. ...

Beehave is a powerful AI behavior tree framework designed as an addon for the Godot game engine, enabling developers to create sophisticated and dynamic non-player character behaviors in games. It uses a node-based system that integrates directly into the Godot scene tree, allowing developers to visually design and organize complex AI logic in a structured and intuitive way. Behavior trees provide a modular approach to decision-making, making it easier to manage large and adaptive AI systems...

Sapiens is a research framework from Meta AI focused on embodied intelligence and human-like multimodal learning, aiming to train agents that can perceive, reason, and act in complex environments. It integrates sensory inputs such as vision, audio, and proprioception into a unified learning architecture that allows agents to understand and adapt to their surroundings dynamically. The project emphasizes long-horizon reasoning and cross-modal grounding—connecting language, perception, and...

Phantom is an experimental AI agent framework designed to simulate autonomous workflows with an emphasis on stealth, abstraction, and flexible execution across environments. The system likely focuses on orchestrating tasks in a way that minimizes friction between user intent and execution, allowing agents to operate with minimal direct supervision. Its architecture suggests modular components that handle planning, execution, and context management independently, enabling scalable and...

OpenNN is a software library written in C++ for advanced analytics. It implements neural networks, the most successful machine learning method. Some typical applications of OpenNN are business intelligence (customer segmentation, churn prevention…), health care (early diagnosis, microarray analysis…) and engineering (performance optimization, predictive maitenance…). OpenNN does not deal with computer vision or natural language processing. The main advantage of OpenNN is its...

NOMAD is a C++ code that implements the MADS algorithm (Mesh Adaptive Direct Search) for difficult blackbox optimization problems. Such problems occur when the functions to optimize are costly computer simulations with no derivatives.

Computer System for Adaptive Intelligent Life :: seeks to create a software system that is capable of learning. The project's ultimate goal is to further the ability of software to both adapt to individual users, and to respond their needs.

Computer chess engine written using Qt4, which works under Knights, Jose, Arena and other chess board GUI games. Uses bitboard game representation and alpha beta brute-force search to analyse chess positions.

A scientific framework for testing and learning the learning of a computer.

The Guiey project is an attempt to develop a system for graphical user interface scripting and testing in Java. Guiey will use a computer by seeing, typing, and clicking - just like a human user.