Awesome AI Agents › Generative Agents Simulation
GPTRPG is a proof-of-concept project that demonstrates a GPT-based AI agent existing within a simple RPG-like environment. The project consists of two main components: a React-based RPG environment and an AI agent that interacts with this environment using the OpenAI API. The environment is designed with the Tiled map editor and rendered using Phaser along with the Grid Engine Plugin, featuring elements such as impassable tiles, plantable tiles, and a character controlled by the AI agent. The agent receives information about its surroundings, possible actions, and its internal state (currently limited to sleepiness) and makes decisions accordingly via the OpenAI API. The project is intended to be run locally, requiring Node.js and an OpenAI API key. The front-end interface is accessible through a local web server. Future enhancements planned for the project include multi-agent support, expanded agent actions like eating, drinking, planting, and harvesting, additional internal states such as hunger and thirst, agent memory and goals, inventory management, deployment to the web, human-controlled characters, and UI improvements to better display agent states and interactions. Currently, the project uses the GPT-3.5-turbo model for the AI agent's decision-making. Overall, GPTRPG serves as an experimental platform exploring the integration of large language models with interactive game environments, showcasing how AI agents can autonomously navigate and interact within a game world.
https://github.com/dzoba/gptrpg
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.