MineDojo/Voyager
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.
Awesome AI Agents › Generative Agents Simulation
joonspk-research/generative_agents
The project "Generative Agents: Interactive Simulacra of Human Behavior" is a research-based simulation framework that models believable human behaviors through computational generative agents. These agents operate within a game-like environment called Smallville, where they interact and exhibit human-like actions. The repository provides a core simulation module and a game environment to run and visualize these agents' behaviors. The project is designed to be run locally, requiring users to set up an environment with dependencies and an OpenAI API key for the generative capabilities. The environment server is implemented using Django, serving the frontend and game assets, while the backend simulation server runs the agent logic and interactions. Users can start the environment server and simulation server concurrently to run simulations, control the number of simulation steps, and observe agent movements on a map interface in a web browser. The system supports saving and replaying simulations, allowing users to resume or review past agent interactions. Additionally, the project includes functionality to compress simulation data for demonstration purposes, optimizing the visual presentation of agents. The simulation steps correspond to time intervals in the game world, and the project emphasizes the importance of managing API rate limits and saving progress frequently due to potential costs and limitations. Overall, this project offers a sophisticated platform for exploring and demonstrating interactive, human-like agent behaviors in a controlled virtual environment, useful for research and development in AI, human-computer interaction, and behavioral simulation.
https://github.com/joonspk-research/generative_agents
Also in Generative Agents Simulation
linyiLYi/street-fighter-ai
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.
GDQuest/godot-steering-ai-framework
A comprehensive Godot framework for creating smooth and complex AI motion using steering behaviors in both 2D and 3D games.
YGYOOO/WorldX
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.
XiaoLuoLYG/GOD
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.
ntasfi/PyGame-Learning-Environment
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.
mkturkcan/generative-agents
A locally runnable, low-cost implementation of generative agents simulating human-like behavior in an interactive Dungeons & Dragons setting using large language models.
dzoba/gptrpg
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.