htdt/godogen

Autonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex

What it solves

Godogen automates the entire process of game development, allowing users to describe a game and have an AI agent build it from scratch. It removes the manual effort of scaffolding projects, writing engine-specific code, and creating assets, while ensuring the final product actually works through visual verification rather than just successful compilation.

How it works

The system acts as a generator that produces a dedicated game repository. Once published, an AI agent (Claude Code or Codex) operates within that repo using engine-specific guides (for Godot, Bevy, or Babylon.js) to build the game. The agent generates 2D images and animated sprites using Gemini or xAI Grok, and 3D models via Tripo3D. Crucially, the agent validates its progress by running the game and analyzing live URLs or recorded video clips to identify and fix visible defects.

Who it’s for

It is designed for developers or creators who want to rapidly prototype games across different engines without manually handling the boilerplate, asset creation, and iterative debugging process.

Highlights

  • Multi-Engine Support: Works with Godot 4 (C#/.NET), Bevy (Rust), and Babylon.js (TypeScript/Vite).
  • Automated Asset Pipeline: Integrates Gemini, xAI Grok, and Tripo3D for images, 3D models, and rigged animations.
  • Visual Proofing: Iterates based on actual gameplay footage and live renders rather than just code logs.
  • Flexible Interaction: Supports both attended steering (live interaction) and unattended runs that produce a final proof recording.

Related

  • Project
    OpenDCAI/GameFactory-3A

    An open-source framework that uses coding agents to transform game requirements into production-ready assets and engine-specific code for UE5, Unity, Godot, Blender, and three.js.

  • Project
    RandallLiuXin/GodotMaker

    An autonomous AI workflow that transforms natural language game ideas into playable 2D Godot engine prototypes, handling everything from GDD planning to implementation and visual QA.

  • Project
    majidmanzarpour/threejs-game-skills

    A skill pack for Codex and Claude Code that lets AI agents build, polish and verify full Three.js browser games. Install via `npx skills add …` (or the provided `install.sh`), then prompt the `threejs‑game‑director` with a natural‑language request (e.g., “create a futuristic tower‑defense game”). The director orchestrates specialist sub‑skills for gameplay, AAA graphics, UI, asset generation (optional Tripo/Gemini/ElevenLabs APIs), debugging, and QA, using a bundled Vite+TypeScript scaffold and Playwright‑based test harnesses. Demos include Neon Ridge Drift, Snooker Arena, Starship Dogfight, etc. MIT‑licensed.

  • Project
    HorizonRobotics/EmbodiedGen

    A generative 3D world engine that converts text and images into simulation-ready 3D assets and environments for embodied AI, deployable across multiple robotics simulators.