Multi Agent Simulation Python Packages

esquilax

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

vmas

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

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

chatarena

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

leanswarm

Lean Swarm is a cost-focused multi-agent prediction and simulation engine designed to approximate MiroFish-class narrative forecasting with aggressive batching, sparse activation, hybrid state, and strict LLM routing guardrails.

llm-agent

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

opentaxi

Open-source airport surface movement simulator for taxiway path planning, conflict resolution, and RL research.

ppage

A minimalist, discrete multi-agent predator-prey archytype environment.

vacuumworld

A multi-agent platform built on the top of the pystarworldsturbo library. Part of the Intelligent Agents course taught at Royal Holloway University of London.

gym-mage

Multi-Agent Grid Environment (MAGE)