Multi Agent World Cup Simulator
Four-agent match simulation with in-browser TTS commentary via WebGPU.
An LLM-powered soccer simulation where every player on the field is an AI agent.
Every player is an LLM agent that evolves strategies between matches autonomously.
AI researchers, simulation enthusiasts, game developers
Google Research Football · Neural MMO · PettingZoo
Four-agent match simulation with in-browser TTS commentary via WebGPU.
Hands-on distributed ML simulator—gamified learning for tensor parallelism without spinning up clusters.
Fully observable multi-agent drama: every LLM call logged, every decision traceable, deterministic at scale.
82-0 basketball clone reskinned for baseball — fun but derivative.
Startup simulation game powered by Lenny's Podcast advice instead of generic mechanics.
Using 1980s Rogue as an LLM benchmark is genuinely novel and technically clever.