#5 · Primary category: Agent-Based Modeling & Simulation
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.
Project last updated:08/11/25
GitHub Stars
1.6K
Forks
150
Contributors
16
License
Apache-2.0
Why we included this project
Researchers and engineers studying how large language models coordinate and collaborate with one another will find a useful test bed here. ChatArena is a Python library for defining multi-agent "language games": structured environments where you set up multiple LLM players, give them roles and rules, and let them converse under controlled conditions. It ships with several ready-made game environments plus both a web UI and a CLI, so you can run and observe agent interactions without much glue code. One caveat: the project is now officially deprecated and no longer receives updates or support, so treat it as a stable reference for building your own multi-agent simulation and evaluation setups rather than a foundation for fresh production work.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
mesa
Mesa is an open-source Python library for agent-based modeling, ideal for simulating complex systems and exploring emergent behaviors.
MiroFish-Offline
Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama local stack.
cultivation-world-simulator
基于 AI Agent 工作流的修仙世界模拟器,旨在还原智能、开放的仙侠世界。| An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world.
WorldX
One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own.
MAgent
A Platform for Many-Agent Reinforcement Learning