# Farama-Foundation/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.

Repository: https://github.com/Farama-Foundation/ChatArena
Canonical: https://ross.abutalabs.com/products/chatarena
Language: Python
License: Apache-2.0
License Family: permissive
Topics: large-language-models, multi-agent, natural-language-processing, multi-agent-reinforcement-learning, multi-agent-simulation, ai, python, artificial-intelligence, chatgpt, gpt-4
Last push: 2025-08-11T20:19:17+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 36, release rhythm 8, longevity 91
- inputs: {"age_days": 1276, "days_push": 387, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1558, forks 148 (observed 2026-08-28T04:05:03.447574+00:00)

## What it is
ChatArena is a Python library providing multi-agent language game environments for large language models, built around a Markov Decision Process abstraction for players, environments, and their interactions. It supports research on autonomous LLM agents and their social interactions, with Web UI and CLI interfaces.

## Use cases
- run multi-agent language game environments for LLMs
- benchmark autonomous LLM agents in social interactions
- train or evaluate LLM agents on communication and collaboration tasks
- prompt engineer LLM agents via a web UI or CLI
- simulate multi-agent conversations and games with GPT models

## When to choose
- you need a ready-made multi-agent language game framework for LLM research
- you want to study social interactions between autonomous LLM agents
- you want a simple MDP-based abstraction for LLM player environments

## When to avoid
- you need actively maintained software - the project was deprecated in August 2025
- you need production-grade multi-agent orchestration rather than research environments
- you need support for the latest LLM providers or features

## Facets
- artifact type: library
- maturity: abandoned
- function: agent-framework, llm-inference, machine-learning, cli, gui
- domain: artificial-intelligence, large-language-models, reinforcement-learning
- platform: python, cli
- tags: multi-agent, language-games, llm-agents, social-simulation, deprecated, markov-decision-process, prompt-engineering, ai-agents, natural-language-processing, web-server

## Member repositories
- Farama-Foundation/ChatArena (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:03.447574+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:29:52.231916+00:00, confidence not recorded.
  - readme: https://github.com/Farama-Foundation/ChatArena (fetched 2026-08-28T04:05:03.447574+00:00, sha 4fb2cbf947df)
- Data as of 2026-08-30T08:39:29.467469+00:00.