AIAny
Icon for item

ScanRuler by CNC Kitchen

Inspect and measure 3D scans in the browser, compare them with CAD models, and reverse-engineer them into STEP solids. An optional MCP connection lets AI agents operate the workflow; without it, files stay local.

Introduction

Turning a scan into a useful CAD model is not just a meshing problem: the hard part is recovering dimensions, design intent, and what the scan cannot show. This project brings measurement and reconstruction into one browser workflow, while making AI assistance optional rather than a prerequisite.

What Sets It Apart
  • Metrology feeds modeling: fitted geometric features, dimensions, tolerances, and deviation checks help distinguish a plausible-looking model from one that agrees with the scan where it matters.
  • Reconstruction is editable: sketches and fitted surfaces can become a solid STEP body, with the resulting model checked against the source scan. This is more useful for downstream CAD than simply smoothing or exporting a mesh.
  • Agent control is an add-on: an MCP bridge lets an external AI agent operate the open app and perform multi-step reconstruction. The agent makes design judgments, so results still need review; reported scan agreement does not prove the real part's nominal dimensions are correct.
Who It Suits

A good fit for makers, inspectors, and engineers who need browser-based scan measurement, CAD comparison, or editable reverse-engineered parts without installing a full inspection suite. Look elsewhere if you need certified metrology, dependable recovery of hidden geometry, or hands-off AI modeling: scan quality limits accuracy, freeform reconstruction is less reliable, and connecting an agent may send measurements and files to its model provider. The AGPL license also matters for modified hosted or closed-source use.

Information

  • Websitegithub.com
  • OrganizationsCNC Kitchen
  • Published date2026/08/13

Categories

More Items

Hugging Face
AI Video2026

Remakes existing footage from text instructions, changing characters, props, or scenes while preserving the original motion, camera, cuts, and sound. Use it in the Viggle app or run it on your own GPUs.

GitHub
AI Infra2026

Builds a semantic context layer for enterprise data that helps agents interpret metrics, entities, and relationships consistently. It validates generated queries against certified definitions and lineage, and returns provenance with answers.

GitHub

Lets AI assistants control and administer Home Assistant through natural language, from devices and automations to dashboards and troubleshooting. It goes beyond the built-in MCP integration with broader system-management tools.