// momentum

tracking since W47

// why it's here

  • Active: last commit today
  • Built almost entirely by one person
  • Health 100/100 with only 77 stars

// how to help

// readme

kicad-tools

Tools for AI agents to work with KiCad projects.

🌐 Live demo gallery: kicad-tools.org β€” explore example boards built end-to-end by these tools, with 2D/3D renders, routing & manufacturing metrics, downloadable fabrication packages, and an interactive in-browser PCB viewer.

This project provides standalone Python tools that enable AI agents (LLMs, autonomous coding assistants, etc.) to parse, analyze, and manipulate KiCad schematic and PCB files programmatically. All tools output machine-readable JSON and require no running KiCad instance.

Why Agent-Focused?

Traditional EDA tools require GUIs and manual interaction. kicad-tools bridges the gap by providing:

  • Structured data access - Parse KiCad files into clean Python objects
  • Machine-readable output - Analysis and query commands offer JSON output; check each command’s --help for supported formats
  • Programmatic modification - Edit schematics and PCBs without a GUI
  • LLM reasoning interface - Purpose-built module for LLM-driven PCB layout decisions
Read the full README on GitHub β†—

Health score

Is the project alive and maintained right now? A 0–100 pulse recomputed nightly from commit recency, rhythm, how fast issues close, and how quickly PRs get merged.

How it's calculated

Undervalued score

Activity relative to attention (stars + watchers). Above 50 means a lot of activity for a project its size. Recomputed nightly from commit velocity, contributor effort, issue resolution, fork utility, release cadence, and project maturity β€” divided by a logarithmic reach factor.

How it's calculated

Tags

Tags are independent behavioral signals computed nightly. A project can hold multiple at once. They drive the home page sections.

How it's calculated