Awesome AI Agents › Generative Agents Simulation
SkyAGI is a Python package that showcases the emerging capability of large language models (LLMs) to simulate believable human behaviors through generative agents. It implements the concept of Generative Agents, enabling the creation of non-player characters (NPCs) in role-playing games that exhibit highly realistic and human-like responses. Unlike traditional AI-based NPC systems, SkyAGI's NPCs demonstrate nuanced and context-aware interactions, making the gaming experience more immersive and engaging. The project provides example characters from popular franchises like The Big Bang Theory and The Avengers, allowing users to interact with these well-known personalities in a simulated environment. Additionally, users can create customized characters by defining their traits and memories in JSON configuration files, enabling personalized and diverse role-playing scenarios. The system leverages memory and personality traits to generate responses that reflect ongoing story developments and character interactions without direct human intervention. This capability opens new possibilities for game development, particularly in NPC scriptwriting and dynamic storytelling. The project requires an OpenAI API key for operation and can be installed via pip or make commands. The repository includes detailed instructions for setup and usage, along with example agent configurations. Notably, the demo highlights interesting observations such as NPCs remembering past interactions, evolving storylines through agent-to-agent communication, and producing responses indistinguishable from human dialogue. SkyAGI represents a significant advancement in AI-driven character simulation, offering a novel approach to creating interactive and believable virtual characters in gaming and simulation contexts.
https://github.com/litanlitudan/skyagi
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.