Multi-Agent-CAD — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Pan-Chera · Agent Tool · ★ 955

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

🔒 Is Multi-Agent-CAD safe to install? View the security audit →

About Multi-Agent-CAD

🛠️ MAC (Multi-Agent CAD): Generate printable 3D models with 1% the tokens Tsinghua University · IEI Lab 4 agents collaborating · 116× fewer tokens · 99.3% feature pass rate — turn concise natural language directly into printable 3D models. Same CAD generation capability, 1/116 the tokens, 1/13 the inference cost. 🎬 Web UI walkthrough Below is a screen recording of one full pipeline run through the Web UI. 📖 Table of Contents 📸 Real-World Gallery 🚀 Quick Start 💡 Introduction [4. ✨ Core Features](#4-core-f

3d-modeling3d-printingagent-pipelineaiderassemblybuild123dcadgenerative-designlanggraphllm

Quick Facts

Stars955
Forks87
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score70.8476761888155/100
Open Issues1
Last Updated2026-09-16
Created2026-07-30
Platformspython
Est. Tokens~19k

Compatible Skills

These tools work well together with Multi-Agent-CAD for enhanced workflows:

  • cad-cae-copilot — semantic(0.65)+complementary+rare_topics+same_lang+shared_platform (78%)
  • agentcad — semantic(0.43)+complementary+rare_topics+same_lang+similar_pop+shared_platform (74%)
  • CAD-MCP — semantic(0.45)+complementary+rare_topics+same_lang+similar_pop+shared_platform (70%)

Multi-Agent-CAD alternative? Top 6 similar tools

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

  • helix by helixml · ⭐ 809

    ♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex,

  • partmode by BOMWiki · ⭐ 457

    Open-source, local-first parametric CAD in the browser for people and permissioned typed agents, powered by Op

  • step.parts by earthtojake · ⭐ 325

    12,000+ open source STEP parts for your next CAD project

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • forgent3d by forgent3d · ⭐ 220

    Using AI to generate 3D models

  • casibase by casibase · ⭐ 4.5k

    ⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-a

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Multi-Agent-CAD?

Multi-Agent-CAD is MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute. It is categorized as a Agent Tool with 955 GitHub stars.

What programming language is Multi-Agent-CAD written in?

Multi-Agent-CAD is primarily written in Python. It covers topics such as 3d-modeling, 3d-printing, agent-pipeline.

How do I install or use Multi-Agent-CAD?

You can find installation instructions and usage details in the Multi-Agent-CAD GitHub repository at github.com/Pan-Chera/Multi-Agent-CAD. The project has 955 stars and 87 forks, indicating an active community.

What license does Multi-Agent-CAD use?

Multi-Agent-CAD is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to Multi-Agent-CAD?

The top alternatives to Multi-Agent-CAD on Agent Skills Hub include helix, partmode, step.parts. 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 Agent Tool tools