A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Fractal Graph-of-Thought. Rhizomatic Mind-Mapping for Ai-Agents, Web-Links, Notes, and Code.

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.

One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.

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。

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

[ICML 2025] ResearchTown: Simulator of Human Research Community

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

An ecologically inspired multi-agent system. Agents are designed with neural network based decision making, and complex resource requirements.

Reciprocal Collision Avoidance for Real-Time Multi-Agent Simulation (port to Javascript). This is an alpha release of a RVO2 port from the C# version to Javascript, only for research purposes.

GATSim: Generative-Agent Transport Simulation

CORMAS (COmmon pool Ressources and Multi-Agent Simulations)

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

Java Agent Based Modelling toolkit

Multi-Agent Simulation of Collective Behavior (Pedestrian Crowd)

AI-powered autonomous coding agent for Unity/Strada.Core — PAOR agent loop, 40+ tools, RAG over C# codebases, persistent HNSW memory, multi-channel (Web/Telegram/Discord/Slack/WhatsApp), 24/7 daemon mode, multi-agent orchestration, and SOUL.md personality system.

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.

The purpose of this simulator is simulates and allows visualization of the evacuation process of people located in buildings during emergencies.

Beer Game implemented as an OpenAI gym environment.