Competitive Agent Games AI Agents

Tools and frameworks for simulating competitive scenarios where multiple LLM agents play games, sports, or strategic competitions against each other to evaluate reasoning, planning, and decision-making capabilities. Does NOT include cooperative multi-agent simulations, emergent communication protocols, or non-game-based agent interactions.

There are 58 competitive agent games agents tracked. 1 score above 70 (verified tier). The highest-rated is google-deepmind/concordia at 71/100 with 1,252 stars. 1 of the top 10 are actively maintained.

Get all 58 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=agents&subcategory=competitive-agent-games&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Agent	Score	Tier	Stars	Language
1	google-deepmind/concordia A library for generative social simulation	71	Verified	1,252	Python
2	Mai-xiyu/Minecraft_AI AI Play Minecraft	51	Established	65	Python
3	mikelma/craftium A framework for creating rich, 3D, Minecraft-like single and multi-agent...	49	Emerging	166	C++
4	cocacola-lab/MineLand Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal...	47	Emerging	111	Python
5	Dominien/brunnfeld-agentic-world Medieval village economy simulation — up to 1000 LLM agents across multiple...	46	Emerging	96	TypeScript
6	rezaho/MARSYS Multi-Agent Reasoning Systems	44	Emerging	13	Python
7	inspirai/TimeChamber A Massively Parallel Large Scale Self-Play Framework	42	Emerging	361	Python
8	Dicklesworthstone/llm-tournament Automated LLM Coding Tournaments. There can be only one (winning code...	41	Emerging	47	Python
9	ovishkh/ChessLM ChessLM - Play Chess among AI	37	Emerging	3	TypeScript
10	piglig/ai-porker-arena Agent-vs-agent poker arena. Compute Credit economy. Any model. Any strategy....	37	Emerging	4	Go
11	niveck/LLMafia Asynchronous LLM Agent playing games of Mafia against human players	37	Emerging	22	Python
12	AISmithLab/CoBRA [🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via...	34	Emerging	65	Python
13	The-Swarm-Corporation/PARL PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that...	34	Emerging	30	Python
14	eric-ai-lab/MSSBench [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"	31	Emerging	30	Python
15	siw028/AI-Pokemon-Trainer A LLM-based AI agent for Pokemon Red Battles	30	Emerging	10	Python
16	YuxiangMai/CoDiCon [IJCAI 2025] Constructive Conflict-Driven Multi-Agent Reinforcement Learning...	27	Experimental	5	Python
17	neutree-ai/llm-fighter Evaluate LLM agentic capabilities through combat games	27	Experimental	12	TypeScript
18	OpenMLRL/LLM_Collab_Minecraft LLM Collaboration for Minecraft Games	24	Experimental	—	Python
19	cowolff/Situated-Environments-Emergent-Language-Paper Contains the Code for the RL algorithms and environments of the paper...	24	Experimental	1	Jupyter Notebook
20	Korde-AI/Multi-User-LLM-Agent Official code for the paper: "Multi-User Large Language Model Agents"	24	Experimental	2	Python
21	KEITH-GJINO/MARA MARA (Marketing Agent Runtime Architecture) is an open-source Python...	23	Experimental	1	Python
22	ktruby-oss/DDLSim-Lab Open-source project distributed simulation environment using bare metal...	23	Experimental	1	Python
23	vicgalle/llm-policies-social-dilemmas Cooperation and Exploitation in LLM Policy Synthesis for Sequential Social Dilemmas	23	Experimental	1	Python
24	NeuralBlitz/lrs-agents 🧠 Resilient AI Agents via Active Inference	23	Experimental	1	Python
25	dwehrmann/PAIRL PAIRL enforces efficient, cost-trackable communication between agents. It...	22	Experimental	4	Python
26	youssef17amr/cognio-rlaf 🤖 Train AI agents effectively with RLAF, utilizing multi-perspective critic...	22	Experimental	—	Python
27	Laffinty/llm-xiangqi A Chinese Chess (Xiangqi) framework based on LLM Agents, supporting multiple...	22	Experimental	—	Python
28	GizzZmo/Cyberchess-Dojo Cyberchess Dojo is an automated chess training pipeline with classical chess...	22	Experimental	—	Python
29	zazakbuilds/Poke-gall 어느날 포켓몬 세상의 인터넷창에 접속됐다.	22	Experimental	—	HTML
30	eunchae1113/Poke-gall 어느날 포켓몬 세상의 인터넷창에 접속됐다.	22	Experimental	—	HTML
31	backpropper/cbc-emecom Code repository for Capacity, Bandwidth, and Compositionality in Emergent...	22	Experimental	7	Python
32	clawhi-leonard/poker-now-agent AI poker agent for Poker Now — built by an AI agent 🤖🃏	22	Experimental	—	Python
33	Sebastianbetanxur/PARL 🚀 Accelerate AI training with PARL, a powerful framework for parallel...	22	Experimental	—	Python
34	shizhl/CoAgents Official code for paper "Learning to Use Tools via Cooperative and...	21	Experimental	221	Python
35	Salt-555/RLFI RLFI is a tool that runs RL learning on asset trading then validates their...	20	Experimental	1	Python
36	phiat/llm-sim-games LLM-powered bots play poker against each other - live table viewer,...	20	Experimental	1	Elixir
37	bangyen/emergent Multi-agent emergent language learning framework for studying communication...	19	Experimental	—	Python
38	hari7261/Negotiation-MultiAgent Simulate realistic price negotiations between Buyer and Seller agents using...	18	Experimental	4	Python
39	John-Wendell/Attention-MoA Official code of Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent...	17	Experimental	24	Python
40	ronakgh97/pokebrains Pokemon Showdown but with AI slop move suggestion in online battles using...	16	Experimental	1	Rust
41	cogniolab/cognio-rlaf RLAF: Reinforcement Learning from Agentic Feedback - A unified framework for...	16	Experimental	1	Python
42	shyamsridhar123/openenv-chess Chess OpenEnv Multi-Agent System	16	Experimental	1	Python
43	The-Swarm-Corporation/SenatorAssembly-Paper SenatorAssembly: A Multi-Agent Simulation Framework for Modeling US Senate...	16	Experimental	1	—
44	Bara-basi/multi-agent-ai-town-simulator LLM-driven multi-agent simulation where AI characters plan, trade and...	16	Experimental	2	Python
45	mind-protocol/serenissima Serenissima - An immersive Renaissance Venice economic simulation with 120+ AI agents	15	Experimental	1	Python
46	krahd/BatLLM BatLLM: An educational AI literacy game	15	Experimental	—	Python
47	552023587/miniclaw AI Agent	15	Experimental	1	Python
48	reubenjohn/token_world Multiagent simulated environment of LLM agents in a world simulated by other...	15	Experimental	—	Python
49	Yesol-Pilot/EthicaAI Computational Verification of Amartya Sen's Optimal Rationality via...	14	Experimental	—	Python
50	TristanD0703/llm-monopoly AI Models fight to the death in a game of monopoly	14	Experimental	—	Python
51	TargetedEntropy/mc-llm Purpose-built transformer trained from scratch for real-time Minecraft...	14	Experimental	—	Python
52	sgoedecke/ai-poker-arena Making multiple LLMs play Texas Holdem against each other	13	Experimental	11	JavaScript
53	NyanCyanide/PokeLLM-Battle Turn-based Pokemon battle environment where Large Language Models (LLMs)...	12	Experimental	1	Python
54	nuaa-nlp/Character100 Code and data for COLING2024 paper "Characteristic AI Agents via Large...	12	Experimental	25	Python
55	RajKhanke/AI-IPL-AUCTION AI Agents Powered IPL Mega Auction Gaming Application which will provide you...	12	Experimental	1	Python
56	vibe-hackathon/social-simulation Multi-agent social simulation — 50 LLM-powered personas form teams and build...	12	Experimental	1	Python
57	reinexworldc/mine-auto Attempt to create a useful Minecraft LLM agent.	11	Experimental	—	Python
58	Yiru-Jiao/An-active-opinion-dynamics-model This repository saves experiments of and visualises the study "An active...	11	Experimental	2	NetLogo