Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

FreeCAD in the Browser

magik.net

Post reply on HN
Print view View original

21–30 of 40 posts

Re: FreeCAD in the Browser

#21

Post by cui »

SequoiaHope wrote: post #18
throwup238 wrote: post #11

Earlier quoted context omitted.

> It’s a professional system from the founders of Solidworks that competes with all the top CAD tools. Because it's built on Parasolid, the same geometric kernel as everyone else. With ACIS pretty much out the door, almost all the professional CAD packages are just window dressing on the same CG implementation.

Agreed. I’m not OP but for six months I’ve been using Claude to build a from-scratch CAD kernel based on Rust and WASM, MIT licensed. The actual UI still needs a lot of work, but I’ve been focused on the kernel. Fable has helped a lot though Opus was already making great headway. I’m an OnShape power user going back about ten years, Solidworks before that. I need a CAD system that absolutely works. There is a lot of…

How long have you been building this?

Re: FreeCAD in the Browser

#22

Post by SequoiaHope »

27183 wrote: post #20
SequoiaHope wrote: post #18

Earlier quoted context omitted.

Agreed. I’m not OP but for six months I’ve been using Claude to build a from-scratch CAD kernel based on Rust and WASM, MIT licensed. The actual UI still needs a lot of work, but I’ve been focused on the kernel. Fable has helped a lot though Opus was already making great headway. I’m an OnShape power user going back about ten years, Solidworks before that. I need a CAD system that absolutely works. There is a lot of…

> It’s serverless, local, and browser based. uhh what..

The app consists of a wasm (web assembly) binary and JavaScript. The wasm runs locally on your machine in your browser and communicates with the JavaScript frontend. There is no backend server to handle any part of the program. The URL just loads the binary in to your local browser. I don’t know exactly how one would set this up but this would work for example fully offline. The browser basically just becomes a universal compute and rendering engine for it.

Re: FreeCAD in the Browser

#23

Post by SequoiaHope »

cui wrote: post #21
SequoiaHope wrote: post #18

Earlier quoted context omitted.

Agreed. I’m not OP but for six months I’ve been using Claude to build a from-scratch CAD kernel based on Rust and WASM, MIT licensed. The actual UI still needs a lot of work, but I’ve been focused on the kernel. Fable has helped a lot though Opus was already making great headway. I’m an OnShape power user going back about ten years, Solidworks before that. I need a CAD system that absolutely works. There is a lot of…

How long have you been building this?

Six months. Basically when Claude code started to hit that inflection point I chose a project that seemed potentially impossible but was also something I care deeply about. (I have a lot of history with open source and CAD and I even made an open source CAD forum on GitHub a few years ago to discuss options.)

I set up remote tmux access to my phone right at the beginning so I have been advancing it rather continuously during my waking hours. Especially the last few months which have been a very focused push on a new kernel architecture.

Re: FreeCAD in the Browser

#25

Post by devttyeu »

emmelaich wrote: post #15

Amazing. How much did it cost?

I made the port, roughly ~one maxed out Claude Max 20x sub, at the bottom of the article I've shared the full claude code transcripts, so you can probably to some rough math on token usage with that.

Edit: to be precise 'maxed out' means one weekly limit on fable used over those 4 days

Re: FreeCAD in the Browser

#26

Post by devttyeu »

devttyeu wrote: post #24
dd8601fn wrote: post #8

Sounds cool. Doesn't work.

Author of the port here, you need a browser with JSPI support, which means recent Chrome, or Firefox Nightly with the feature flag flipped, or Firefox from the future.

I will also note that it's possible to compile this with wasm asyncify, but the result iirc is a ~400MiB Wasm binary that will crash the browser tab before you will be able to do anything useful in it.

Re: FreeCAD in the Browser

#27

Post by cui »

SequoiaHope wrote: post #23
cui wrote: post #21

Earlier quoted context omitted.

How long have you been building this?

Six months. Basically when Claude code started to hit that inflection point I chose a project that seemed potentially impossible but was also something I care deeply about. (I have a lot of history with open source and CAD and I even made an open source CAD forum on GitHub a few years ago to discuss options.) I set up remote tmux access to my phone right at the beginning so I have been advancing it rather continuousl…

Respect.

Re: FreeCAD in the Browser

#28

Post by devttyeu »

techbro92 wrote: post #2

Why would I want to run this in the browser vs locally?

(I made this port) Fwiw I personally had no reason to do this port beyond using it as a benchmark of the agentic capability of Fable, where something of this shape is IMO a way better gauge than those dumb X.com 'I oneshot game with models X/Y/Z this is how it compares'

I published the actual prompts, and you can see quite clearly that vs Opus which is ok at implementing one big feature, Fable was really able to push through a good chunk of the port. That said it definitely didn't one-shot the port, it also didn't figure out a broken docker sbx sandbox by itself, and also later needed some gaslighting into thinking that the port is not really that hard (by any human measure it was quite hard given the scope of code involved.. The nearly 200MB wasm binary is mostly code afaict..). So there are some clear patterns of how the model was trained and also roughly the scope of task visible in those traces. What I see is that it likes prompts that would take an L4/L5 2-4 weeks to do with Cursor ~2 years ago, more needs some direction and deliberate prompting.

Re: FreeCAD in the Browser

#29

Post by SequoiaHope »

cui wrote: post #27
SequoiaHope wrote: post #23

Earlier quoted context omitted.

Six months. Basically when Claude code started to hit that inflection point I chose a project that seemed potentially impossible but was also something I care deeply about. (I have a lot of history with open source and CAD and I even made an open source CAD forum on GitHub a few years ago to discuss options.) I set up remote tmux access to my phone right at the beginning so I have been advancing it rather continuousl…

Respect.

Aww thank you so much! It has felt really good to work on as I have started to see something real come together.

Re: FreeCAD in the Browser

#30

Post by throwup238 »

SequoiaHope wrote: post #18
throwup238 wrote: post #11

Earlier quoted context omitted.

> It’s a professional system from the founders of Solidworks that competes with all the top CAD tools. Because it's built on Parasolid, the same geometric kernel as everyone else. With ACIS pretty much out the door, almost all the professional CAD packages are just window dressing on the same CG implementation.

Agreed. I’m not OP but for six months I’ve been using Claude to build a from-scratch CAD kernel based on Rust and WASM, MIT licensed. The actual UI still needs a lot of work, but I’ve been focused on the kernel. Fable has helped a lot though Opus was already making great headway. I’m an OnShape power user going back about ten years, Solidworks before that. I need a CAD system that absolutely works. There is a lot of…

Heh, me too. I'm on my third rewrite after a bunch of promising false starts.

Unfortunately geometric kernels are one of those things where unknown unknowns will bite you in the ass really hard because none of the content is really in the training data for LLMs and pathological/degenerate cases aren't just common but expected. IME it's not something that can be vibe coded with current models, if ever, without intimately understanding the algorithms.

I can't do a thorough review of waffle iron right now but just off the top of my head: it doesn't look like you have a tolerance context? The tolerances look like hard coded constants (TAU_MODEL/TAU_WORK/MATCH_TOLERANCE/etc) but that's fundamentally unworkable. Each operation and vertex/edge/etc needs to track accumulating errors and apply them to downstream point classification. Interfaces like Kernel::boolean_union(a, b) are the wrong abstraction because it's missing tons of information/functionality like accumulating FP errors, evidence/proofs, rollback, etc.

Keep working at it! It's worth the challenge.

Post reply on HN