WojciechMichna

Godot Agent Arena — AI skill for Claude Code

AI community

Dockerized Godot Engine accessible via browser (noVNC + Guacamole) — a testbed for benchmarking browser-based AI agents (Copilot, Claude, Comet) on real GUI tasks.

How to install Godot Agent Arena

This entry records only its repository, not the path inside it, so there is no exact command to give. Open WojciechMichna/godot-agent-arena and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Godot Agent Arena does

Dockerized Godot Engine accessible via browser (noVNC + Guacamole) — a testbed for benchmarking browser-based AI agents (Copilot, Claude, Comet) on real GUI tasks. Spin up multiple isolated instances in parallel and let each agent build a game project from scratch.

Alternatives in AI

Omniget — Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents 13.9k ★
Claude Squad — by smtg-ai - Claude Squad is a terminal app that manages multiple Claude Code, Codex (and other local agents i 6.5k ★
Desktop Cc Gui — Multi-engine AI coding desktop client (Tauri) 4.4k ★

README

godot-agent-arena

A Docker container that runs the Godot Engine with noVNC and Apache Guacamole, making it accessible directly from a web browser — built specifically for testing browser-based AI agents.

What is this?

This project spins up a Docker container with Godot 4.6.2 running inside a virtual display (Xvfb), exposed via two different browser access methods:

noVNC (lightweight, websocket-based) — connect directly on port 9488
Apache Guacamole (full remote desktop gateway) — connect on port 8080

You open a browser, connect to the container, and get a fully interactive Godot editor — no local installation needed.

Why two access methods?

Testing revealed that **the access method matters for AI agent performance**. Guacamole renders the remote session differently than noVNC, and some agents handle one much better than the other. In particular, Copilot performs significantly better when connected through Guacamole compared to noVNC.

Purpose

This is a testbed for evaluating how well **browser-based AI agents** can operate as general-purpose GUI automation tools. The agents being tested:

Copilot (Edge)
Comet (Perplexity)
Claude in Chrome (Anthropic)

The workflow: start the container, open Godot in the browser, and instruct a browser agent to click through the editor and build a project from scratch.