Awesome AI Agents › Generative Agents Simulation
Simulator Controller is a sophisticated and modular application designed to enhance the experience of sim racing enthusiasts by providing an AI-based virtual pit crew and comprehensive control over racing simulators. The core of the project is a plugin-capable automation framework that supports a wide range of external controller hardware, such as button boxes, to manage typical simulator components like SimHub and SimFeedback. This flexibility allows users to customize their racing setup extensively. The standout feature of Simulator Controller is its suite of AI-powered assistants that simulate real-life racing team roles. These include an AI Race Engineer who manages race logistics such as pit stops, weather monitoring, and damage impact analysis, allowing the driver to focus on racing. The AI Race Strategist oversees the overall race situation, adapting strategies based on race position, traffic, and weather changes. The AI Race Spotter monitors the race environment to alert the driver about critical situations involving nearby cars. Additionally, the AI Driving Coach provides real-time driving advice and coaching to help users improve their skills on the track. Beyond AI assistants, the application offers numerous other functionalities aimed at simplifying and enriching the sim racing experience. It supports automated installation and updates, with detailed documentation and community support available. The project also addresses potential antivirus warnings due to its use of advanced Windows control techniques, reassuring users about safety. Simulator Controller is actively maintained, with regular releases and updates that introduce new features and improvements. It encourages community support through donations and Patreon, which also offers benefits like access to a public team server for multiplayer endurance races. Overall, Simulator Controller is a comprehensive tool that brings AI-driven realism and convenience to sim racing, making it more immersive and enjoyable for users.
https://github.com/SeriousOldMan/Simulator-Controller
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.