There are 16 repositories under multi-agent-simulation topic.
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
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。
[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.
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.
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.
A Multi-Agent Simulation Framework and Analysis of the IOTA Tangle - Python implementation and PDF of M.Sc. thesis, Imperial College London
web based multi-agent simulator for individual-based modeling in population dynamics and ecotoxicology
A Simulation System for Implementing and Testing Multi-Agent Reinforcement Learning Algorithms
An interactive command-line interface that uses the Agent2Agent (A2A) & Model Context Protocols (MCP) to manage multi-agent systems.
Multi-Agent-AI-Researcher-Powered-by-DeepSeek-R1-main
Reinforcement Learning for Unmanned Airial Vehicles
JAX Multi-Agent RL, Neuro-Evolution, and A-Life Library
JASA is a high-performance auction simulator written in JAVA. It is designed for performing experiments in agent-based computational economics.
Simulating the TCR protocol
Reproduction of papers about evolution of cooperation
Multi-agent Simulation Software for Crowd Crush Prevention and Store Layout Optimizer
Master mind Board Game implemented in Python
Simulations of domestic abuse & coercive control traits from articles, narratives, documents, timelines, media on domestic abuse with multi-agent modeling. Abuse AI Simulation/Predict Training, action-trees
Sky-Drive: A Distributed Multi-Agent Simulation Platform for Human-AI Collaborative and Socially-Aware Future Transportation
A swarm simulator that uses client-server architecture with socket communication to implement swarm algorithms
This is an instance of the SmartGovSimulator applied to the Low Emission Zones (LEZ) model and its impact to the Urban Freight Transport (UFD)
Multi-agent collaboration using Reinforcement Learning
Multi-Agent Creative Collaboration with AutoGen