cad-agent-1-0-0Run build123d CAD code inside a container to create, render, and iteratively modify 3D models via HTTP with returned rendered images for visual feedback.
Install via ClawdBot CLI:
clawdbot install zhangyingzhuangk/cad-agent-1-0-0Grade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:8123/model/createCalls external URL not in known-safe list
https://github.com/clawd-maf/cad-agent.gitAudited Apr 17, 2026 · audit v1.0
Generated May 5, 2026
Design and iterate 3D-printable mechanical parts by sending build123d code, viewing renders, and refining geometry until requirements are met. Ideal for engineers needing quick visual feedback without leaving the terminal.
Create custom electronic enclosures with parametric dimensions. Adjust parameters via code, re-render to verify fit, and export STL for 3D printing. Eliminates manual CAD software dependencies.
Teach build123d modeling by having students submit code, view rendered results, and debug visually. The agent provides immediate feedback, making it suitable for online courses and workshops.
Modify existing CAD models by sending code patches and instantly viewing updated renders. Useful for maintenance scenarios where legacy models need quick adjustments without full CAD suites.
Charge a monthly fee for access to the CAD Agent API with usage limits (e.g., number of renders or models). Tiered plans based on render resolution and concurrent sessions.
Bill customers per render request, ideal for occasional users. Pricing varies by render type (multiview, 3D, 2D) and export format (STL, STEP).
Offer a fully managed deployment with dedicated CAD Agent containers, custom integrations, and support. Pricing includes setup fee and annual contract.
💬 Integration Tip
Run the CAD Agent in a separate Docker container on the same network as your agent. Use HTTP calls to create, modify, render, and export models, treating renders as visual feedback for iterative design.
Scored May 5, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...