Awesome AI Agents › Generative Agents Simulation
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.
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.
Python multi-agent world engine where LLM agents receive roles, rules, private information and consequences, then interact until useful artifacts emerge across research, simulation and narrative scenes.
SkyAGI is a Python package that leverages large language models to simulate highly believable human behaviors in NPCs for immersive role-playing games, enabling dynamic and realistic character interactions.
Interactive LLM Powered NPCs is an open-source project that enables natural voice-based conversations with NPCs in popular open-world games by integrating advanced AI technologies like large language models, facial recognition, and lip synchronization without modifying the game source code.
A deep reinforcement learning project that trains a model to autonomously play the first level of Super Mario World using raw pixel inputs and deep Q-learning with a spatial transformer.
Wolfcha is an open-source Next.js implementation of the Werewolf social deduction game where one human takes a single seat and LLM-driven characters play every other role at an 8 to 12 seat table.
Poke-env is a Python interface for creating and training reinforcement learning and rule-based bots to battle on Pokemon Showdown, providing a comprehensive environment for AI-driven Pokemon battles.
Simulator Controller is a modular and extendable sim racing application featuring AI-powered assistants that provide real-time race management, strategy, and driving coaching to create a realistic and immersive racing experience.
ChatSim is an editable scene simulation platform for autonomous driving that leverages LLM-agent collaboration and advanced rendering techniques to create realistic and manipulable driving scenarios.
JARVIS-1 is an open-world multimodal language model-based agent designed to perform complex multi-task planning and embodied control in the Minecraft environment, leveraging memory-augmented models for enhanced performance.
MineStudio is a comprehensive package that provides tools and APIs for developing, training, and deploying AI agents in Minecraft, featuring simulation, data handling, model training, inference, and benchmarking capabilities.
Odyssey is a framework that empowers Minecraft agents with advanced open-world skills using a fine-tuned LLaMA-3 model and a comprehensive skill library to enable autonomous exploration and complex task planning.
OpenSteer is an open-source C++ library and interactive demo for creating and prototyping steering behaviors for autonomous characters in games and animation.
Gigax is a runtime environment for AI-powered NPCs that perform complex actions in real-time using fine-tuned large language models running locally on your hardware.
Suspicion-Agent is an AI project implementing a theory of mind aware GPT-4 agent to play imperfect information games, enhancing strategic reasoning and decision-making.