Awesome AI Agents › Generative Agents Simulation
Wolfcha is a browser-based version of the social deduction game Werewolf (Mafia) in which a single human player joins a table of eight to twelve seats and large language models control every other participant. The player picks a role from Villager, Werewolf, White Wolf King, Seer, Witch, Hunter, Guard or Idiot, and the game then runs the usual loop of night actions, daytime discussion and a group vote. Each AI seat is given a stable personality that sits on top of a hidden game role, and the models track speeches, votes, deaths and shifting suspicion across rounds, so they accuse, defend, bluff, follow the crowd or stay quiet according to the goals of their faction. Because the dialogue is generated at run time rather than scripted, the same starting setup produces different conversations and different outcomes on each play. The interface is built for atmosphere as much as for mechanics: retro artwork, day and night transitions, lip-sync animation while a character speaks, dedicated illustrations for night actions, optional voice playback and a spectator mode that lets a viewer watch a table of models argue without joining it. The project came out of the Watcha and ModelScope hackathon and is built with Next.js 16, TypeScript, Tailwind CSS, Jotai, Radix UI, Framer Motion and Tiptap, with model access configured through environment variables so a self-hosted instance can point at whichever providers the operator has keys for. A hosted instance is available and the repository can also be cloned and run locally with pnpm. It is aimed at people who want to study how language models handle deception, persuasion and group reasoning, and at players who want a full table of opponents without scheduling one.
https://github.com/oil-oil/wolfcha
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.