Claude of Duty: Fully Procedural Browser FPS Built by AI Agents Using Three.js

Repositorymshumer/Claude-of-DutyDemo

Claude of Duty is an open-source first-person shooter running in the browser on Three.js r180 and WebGL2. Spanning roughly 55,000 lines of code across 11 subsystems, it was constructed by an orchestrated fleet of AI agents. The game contains zero pre-baked art assets: every texture, 3D mesh, animation, and sound effect is generated procedurally from code at runtime.

Key points

  1. Zero asset files: No pre-rendered images, 3D models, or audio clips; Three.js is the only runtime dependency.
  2. Custom engine subsystems: Features an in-house physics engine with Binned-SAH BVH, Web Audio synthesis, and an advanced HDR/post-processing pipeline (TAA, GTAO, AgX tone mapping).
  3. Multi-agent AI creation: Built by autonomous agents working against a shared architecture contract (ARCHITECTURE.md).
  4. Robust testing harness: Includes headless Chromium scripts for deterministic, pixel-identical visual capture and regression testing.

Why it matters

This project offers a compelling case study on the boundaries of multi-agent software engineering. Rather than writing trivial scripts, coordinated agents implemented a complex, modular 3D graphics application from scratch.

Analysis

Claude of Duty acts primarily as a proof-of-concept demonstrating agentic coding orchestration and procedural generation in WebGL. Author Matt Shumer highlights that the custom test harness and architectural boundaries were key to letting agents generate production-grade graphics, physics, and gameplay mechanics. While feature-rich with character controllers, dynamic AI, and spatial audio, it remains an experimental demonstration rather than a finished commercial title.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:img2threejs/img2threejs

    img2threejs: Procedural Code-Only Image-to-3D for Three.js

    img2threejs turns reference images into procedural, animation-ready Three.js models generated purely as code, avoiding traditional mesh extraction or photogrammetry.

    15.1kstarsPython

    AI & LLMs· Tool

  • Link:Matt Shumer

    The Gauntlet Loop: The Prompting Method Behind Claude of Duty

    Matt Shumer explains the 'Gauntlet Loop', the prompting technique used to build a 55,000-line 3D game using Claude Opus 5 inside Claude Code from a single prompt. The method delegates decomposition to a lead agent and pairs independent builders with isolated critics that evaluate outputs against an ambitious reference standard.

    AI & LLMs· Tutorial

  • Repository:nirholas/three.ws

    three.ws: Browser-Native 3D AI Agents via Three.js and MCP

    three.ws is an open-source platform designed to create and embed interactive 3D agents directly in the browser. It allows developers to turn text, images, or sketches into rigged GLB avatars, attach LLM reasoning via the Model Context Protocol (MCP), and embed them anywhere using a single Web Component.

    224starsJavaScript

    AI & LLMs· Tool

  • Repository:MengTo/Skills

    Agent Skills: Reusable Playbooks for AI Coding Agents

    The GitHub repository MengTo/Skills provides a curated collection of Markdown-based 'agent skills'. It enables designers and builders to guide AI coding agents like Codex, Claude, and Cursor through complex web design, interaction, and 3D rendering tasks.

    6.2kstarsHTML

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.