Claw3D — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by iamlukethedev · Codex Skill · ★ 2.2k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Claw3D safe to install? View the security audit →

About Claw3D

Claw3D A 3D workspace for AI agents. Unofficial project: Claw3D is an independent community project and is not affiliated with, endorsed by, or maintained by the OpenClaw team. OpenClaw is a separate project, and this repository is not the official OpenClaw repository. Claw3D turns AI automation into a visual workplace where agents collaborate, review code, run tests, train skills, and execute tasks inside a shared 3D environment. Built and maintained by LukeTheDev. Follow on X: @iamlukethedev. Think of it as: An office for your AI team. What you can do with Claw3D • Watch your AI agents work in real time • Run standups with agents connected to GitHub and Jira • Review pull requests from inside the office • Monitor QA pipelines and logs • Train agents in the gym to develop new skills • Reset sessions and clean context with the janitor system Instead of managing automation through dashboards and logs… You walk through your AI workplace. Vision · Architecture · Contributing · Security What Claw3D Is Claw3D is the visualization and interaction layer.

3d-engineclaw3dgame-enginegamedevgraphicsjavascriptopen-sourceopenclawrenderingthreejs

Quick Facts

Stars2,178
Forks588
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score70.5201660278494/100
Open Issues47
Last Updated2026-08-21
Created2026-03-15
Platformsbrowser, node
Est. Tokens~17k

Compatible Skills

These tools work well together with Claw3D for enhanced workflows:

  • cesium-mcp — semantic(0.32)+complementary+rare_topics+similar_pop+shared_platform (51%)
  • flyto-core — semantic(0.21)+complementary+similar_pop+shared_platform (47%)

Claw3D alternative? Top 6 similar tools

Looking for a Claw3D alternative? If you're comparing Claw3D with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • traktor by apistol78 · ⭐ 575

    Traktor Game Engine

  • voltagent by VoltAgent · ⭐ 10.4k

    AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

  • img2threejs by hoainho · ⭐ 3.5k

    Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js mo

  • VibeUE by kevinpbuckley · ⭐ 691

    Unreal Engine Vibe Coding tool

  • claude-ads by AgriciDaniel · ⭐ 9.4k

    Claude-first paid-media operations skill for Claude Code across 12 ad platforms (Google, Meta, YouTube, Linked

  • Upsonic by Upsonic · ⭐ 8.0k

    Build autonomous AI agents in Python.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Claw3D?

Claw3D is Claw3D is an open source 3D engine built on OpenClaw for creating games, simulations, and high-performance 3D applications.. It is categorized as a Codex Skill with 2.2k GitHub stars.

What programming language is Claw3D written in?

Claw3D is primarily written in TypeScript. It covers topics such as 3d-engine, claw3d, game-engine.

How do I install or use Claw3D?

You can find installation instructions and usage details in the Claw3D GitHub repository at github.com/iamlukethedev/Claw3D. The project has 2.2k stars and 588 forks, indicating an active community.

What license does Claw3D use?

Claw3D is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to Claw3D?

The top alternatives to Claw3D on Agent Skills Hub include traktor, voltagent, img2threejs. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools