hanshiyingbing

hanshiyingbing / numcraft

Public

NumCraft - Multi-Agent Collaborative System for Intelligent G-Code Generation

artificial-intelligence automation cnc g-code langgraph
12
0
69% credibility
Found Mar 22, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

NumCraft is an AI assistant that generates safe, optimized G-code for CNC machines from plain-language descriptions of parts to machine.

How It Works

1
🔍 Discover NumCraft

You hear about NumCraft, a friendly helper that turns your simple descriptions of metal parts into ready-to-use instructions for your CNC machine.

2
📥 Set it up

You grab NumCraft and prepare it on your computer with easy steps, so it's ready to help.

3
🗣️ Describe your part

You tell NumCraft what you want to make in everyday words, like 'a plate with 10mm holes and slots in aluminum'.

4
🧠 Watch it plan

NumCraft thinks through the best way to make it, choosing tools, paths, and steps just like an expert machinist.

5
🔧 Review the safety check

It double-checks everything for safety, so your machine runs smoothly without surprises.

6
📄 Get your instructions

You receive complete machine instructions, optimized and tested, ready to copy into your CNC control.

🎉 Make your part

Load the instructions and watch your CNC create the exact part you imagined, perfectly every time.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is numcraft?

Numcraft is a Python multi-agent collaborative system for intelligent G-code generation. Describe a part—like "drill 10mm holes and mill 50x20mm slots in aluminum"—and it outputs FANUC-compliant G-code via specialized agents handling feature recognition, process planning, tool selection, path optimization, and safety validation. Run it locally with scripts or via FastAPI endpoints including OpenAI-compatible chat completions.

Why is it gaining traction?

Its hook is turning natural language into production-ready G-code without CAM software, using collaborative agents that iterate on plans like a human team. Python devs appreciate the LangGraph orchestration, HTTP/streaming APIs, and easy local testing, standing out from manual scripting or rigid CAD tools. Even tying into fun merges like com.numcraft.merge 2048 or Minecraft-style builds, it automates real CNC workflows.

Who should use this?

CNC programmers tired of hand-coding G-code for simple three-axis jobs on mills. Manufacturing engineers prototyping aluminum/steel parts with holes, slots, pockets, contours. Python scripters integrating AI into shop floors for quick iterations.

Verdict

Solid concept for multi-agent G-code generation, but early-stage: 12 stars, 0.7% credibility score, sparse docs, and limited tests mean verify every output. Try for prototypes if you're in LangChain/Python; skip for mission-critical production until more battle-tested.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.