Awesome AI Agents › Generative Agents Simulation
OpenSteer is a C++ library designed to facilitate the creation of steering behaviors for autonomous characters in games and animation. It provides a comprehensive toolkit for simulating realistic movement and navigation behaviors through an abstract mobile agent called a "vehicle." The library includes sample code and examples that demonstrate how to combine simple steering behaviors to create more complex and lifelike character movements. OpenSteer is designed to be flexible and easily integrated with existing game engines, either through layering or inheritance, making it a valuable resource for game developers and animators. In addition to the core library, OpenSteer offers an OpenGL-based application called OpenSteerDemo. This application serves as a platform for prototyping, visualizing, annotating, and debugging steering behaviors interactively. Users can write plug-ins for OpenSteerDemo to quickly test new behaviors, adjust simulation parameters, and control the simulation flow by starting, stopping, or single-stepping through time. The demo also allows users to select specific vehicles or agents, adjust camera views, and track characters dynamically, enhancing the development and testing process. OpenSteer is open-source software distributed under the MIT License, ensuring it is freely available for use and modification. Originally developed by Craig Reynolds at Sony Computer Entertainment America, the project has since been maintained and extended by a community of volunteers. It supports multiple platforms, including Linux, Mac OS X, and Windows. The project encourages community involvement through forums and GitHub, where users can report issues, contribute code, and participate in discussions. Overall, OpenSteer is a powerful and flexible tool for developers and researchers interested in autonomous character movement, offering both a robust library and an interactive environment for experimentation and development.
https://github.com/meshula/OpenSteer
This project provides a simulation framework for generative agents that mimic believable human behaviors within an interactive game environment, enabling running, saving, replaying, and demonstrating agent-based simulations.
Voyager is an open-ended embodied agent powered by large language models that autonomously explores and learns diverse skills in Minecraft through lifelong learning and an evolving skill library.
SFighterAI is a deep reinforcement learning-based AI agent designed to master and beat the final boss in Street Fighter II: Special Champion Edition using only game screen pixel data.
A comprehensive Godot framework for creating smooth and complex AI motion using steering behaviors in both 2D and 3D games.
WorldX turns a single sentence into a running simulated world, generating maps and characters with LLMs and letting autonomous agents act, remember and form stories inside it.
Control room for LLM agent societies: pause and scrub a running simulation, question individual residents, inject instructions into the next step, and export replayable experiment packs.
PyGame Learning Environment (PLE) is a Python-based reinforcement learning platform that provides a variety of games and tools to facilitate the development and testing of reinforcement learning algorithms.
A locally runnable, low-cost implementation of generative agents simulating human-like behavior in an interactive Dungeons & Dragons setting using large language models.