Awesome AI Agents › Generative Agents Simulation
The Godot Steering AI Framework is a comprehensive tool designed to facilitate the creation of smooth and complex AI motion within the Godot game engine. It supports both 2D and 3D game environments, making it versatile for various game development needs. The framework is built using GDScript and is inspired by the GDX-AI framework from the LibGDX Java-based framework. It implements steering behaviors originally developed by Craig Reynolds in the 1990s, which are algorithms that dictate how AI agents move frame-by-frame based on their current state and environment. These behaviors include essential actions such as fleeing, following, looking at targets, and more advanced behaviors like blended behaviors, group behaviors, avoiding neighbors, path following, and leader following. The framework is designed to be lightweight and efficient, avoiding the complexity of traditional pathfinding algorithms like A*. It uses a steering agent model where each agent represents a character or vehicle with properties like position, orientation, maximum speeds, and current velocity. The steering behavior calculates changes in velocity, which can then be applied to the agent using Godot's physics methods such as apply_impulse or move_and_slide. The framework is easy to integrate into Godot projects by copying the addons directory and does not require complex scene trees, as all AI movement logic is contained within GDScript classes extending Godot's Reference type. The project includes documentation and demos to help users learn and implement the framework effectively. It is actively maintained and supported by GDQuest, which also offers tutorials and courses to help developers improve their game creation skills. The community can engage through Discord, Twitter, and YouTube for support and updates.
https://github.com/GDQuest/godot-steering-ai-framework
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.
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.
GPTRPG is a proof-of-concept project featuring a GPT-based AI agent that autonomously interacts within a simple RPG-like environment using the OpenAI API.