ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

[ICML 2025] ResearchTown: Simulator of Human Research Community

本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

PyTorch implementation for Social-LSTM, which is built to predict multi-vessel trajectories.

Multi agent simulation code for 2×2 Game on complex network

Multi-Agent Simulation of Collective Behavior (Pedestrian Crowd)

A lightweight Python-based 3D network multi-agent simulator. Uses a cell-based congestion model. Calculates risk, loudness and battery capacities of the agents. Suitable for 3D network optimization tasks.

Beer Game implemented as an OpenAI gym environment.

A Multi-Agent Simulation Framework and Analysis of the IOTA Tangle - Python implementation and PDF of M.Sc. thesis, Imperial College London

JAX Multi-Agent RL, Neuro-Evolution, and A-Life Library

Reinforcement Learning for Unmanned Airial Vehicles

Multi-Agent-AI-Researcher-Powered-by-DeepSeek-R1-main

Master mind Board Game implemented in Python

Multi-Agent Grid Environment (MAGE)

Multi-agent collaboration using Reinforcement Learning

Multi-Agent Creative Collaboration with AutoGen

Stock Exchange Simulator

Détection d'un blob dans une image ainsi que détection des comprimés de nourriture. Simulation d'un blob dans PyGame à travers un système multi-agents à connaissance partagée.