Brandon Thomas, developer of ArtCraft, a suite of open-source creative tools meant to replicate Adobe applications for free, has now announced apps to replace Microsoft Office tools such as Excel, PowerPoint, and Word, respectively, named GridCraft, DeckCraft, and WordCraft, that are created with Claude. Thomas has shared his new clones to ArtCraft GitHub, making them free for all to download.
Man, imagine the financial crisis vibe-coded Excel usage will cause.
Okay. Do Unigraphics NX. I would totally use that.
I don’t think this is going to amount to anything; the rate he’s popping these out suggest he’s more motivated by making a point and/or prestige than getting something useful at the end, and turning these enormous codebases nobody has any intuition for into something maintainable is going to be grueling work that will make them wish they started from scratch. But if we imagine that this will go somewhere:
Wouldn’t that be bad for open source in the long run?
Businesses, certainly not the larger ones, are not going to touch this for various reasons. So while Adobe and Microsoft may take a hit, it’s not going to fundamentally harm their business models. Students, on the other hand, can’t afford the real thing. If that leads to them to alternatives like LibreOffice, GIMP, or Krita, then when they end up in the workforce, there’s going to be at least some pressure to let them use the tools they’re used to. In fact, I use LibreOffice at work. But if they can have something that looks and feels exactly like Adobe’s and Microsoft’s products, they’ll feel right at home with the real thing at work.
Creatorinstructor
Hmm, I see what you are going for but is “instructor” the proper term? To cut AI out of the picture, let’s say the guy instead of paying for tokens paid a team of developers who did the work for him. What would you call the guy then? He does exactly the same amount and type of work in both cases, but obviously noone would call him “instructor”.
That’s called hiring a team of developers. I believe this would fall under the term producer depending on the situation? If he paid a team of developers and claimed he coded it himself then he’d be called a liar
That’s called hiring a team of developers.
Yeah, and this is called “prompting some vibe coded software”, but we are looking a single word title that applies to such a person. “Producer” makes sense I guess, but did he really “produce” it or did he just tell someone or something to produce it?
Director could be a fitting word, because he directed them to do it. Or plain and simple: Client
None of them work as intended and we already have free options why is this a headline
Anything with AI in it gets clicks.
Exactly. If I needed something more powerful than google docs then I’d download LibreOffice.
True. I think it’s greater value is being an AI middle finger to specific proprietary software. Especially if they incorporate and mainly focus on AI these days. As well as encourage it’s use as a magical new tool.
most people do not even know that they exist to begin with.
As many free alternatives as there were before the rampant vibecoding, it seems that this growing collection of tools is not only functional, but a message to the large companies as well. Most of these apps are still far from what they intend to replace, however, so we’ll have to see how deep this message cuts.
Blood in the water for Adobe. Acrobat is a steaming pile of garbage. My org worked with their engineering team to track down a bug that we reported. They affirmed the bug (app hangs on launch) and then took four to five months fixing it.
I’ve worked in software engineering. I know that debugging, patching, testing, verifying is difficult. But the enterprise license costs a lot and that was a very long time with a crippling bug. The only satisfactory answer (to me) is that they don’t feel urgency because they are entrenched without real competition. They need to wake up.
(No, I don’t think vibe-coded Acrobat replacements will unseat them. I think LLM-powered real devs will come for them because the moat is smaller.)
Its a matter of priority. If you are big contract to them and threaten to cancel over this bug then it would move faster.
Yeah man but did you see the “Turn it into a podcast” button??? Great stuff!
The only satisfactory answer (to me) is that they don’t feel urgency because they are entrenched without real competition.
It’s where the lines intersects with how much it would cost to fix it and how significantly the bug impacts their revenue.
deleted by creator
“creator” my ass
Open source tools for all of these use cases have existed for over a decade and people still buy both adobe and Microsoft office. I don’t think some slop apps are going to change that.
I’m a Microsoft hater but I don’t think this will changes the wider publics opinion on them?
Open office and libreoffice have been around a good while now.
Pirating Adobe products was common practice for poor uni students, or occasional users that didn’t want to pay exorbitant rates to fix an image here and there. Adobe made that much more difficult. Then you have us Australians that have been getting charged well above the US retail price for years; at one point it was cheaper to fly to America and buy a physical copy.
These slop apps will absolutely let people go back to doing that, and get back at Adobe for overcharging, because the open source tools either don’t work with the file formats required, or they just don’t cut it. I use LibreOffice & GIMP and they’re great, I love them. However, I’m not a graphic designer, and tools like Photoshop leave GIMP in the dust for professional work.
Pirating Adobe and MS products is a practice of Nerds which thought they were hackers, since the existence of alternatives which make useless the piracy of this products.
I don’t know where you got that idea. The vast majority of people I knew who passed around a copy of Adobe stuff or MS Office, along with a working key or keygen program back in the day, were most definitely not nerds who believed they were hackers.
I still use my copy of photoshop from time to time.
Photopea has been my go to alternative for opening actual psd docs for a while.
Paint.net was my go to for quick stuff back in windows. I’ve been learning Kirta on linux now.
But for certain work, the 10 year old copy of photoshop is still better at certain things. Specifically for editing actual photos (go figure).
We still don’t have a good alternative for prepress production media. I’ve seen some workarounds, but Adobe is the only actively developed option feature complete for this use case. Mostly because the chances that prepress workers and offset printer operators are also FOSS fiends and developers abysmally low. Prepress is such a small industry too since most people don’t really care if their print media looks like shit
30 years after switching to Linux, I still have to use Photoshop because the gimp is still trash.
I played with PhotoCraft, it launches on less than a second, and while still missing features and isn’t even a 1.0 release yet, it’s better than the gimp already.
And it opened all my psds perfectly.
I know it is aimed at digital artists but I highly recommend Krita as a photo editing alternative. Even with it not being the primary focus it knocks all the socks off Gimp. Unsure of psd support though!
Why doesn’t the dev rather work on specific features sets on one existing project instead of building half baked fleet of slop.
Yeah, ArtCraft is very poorly made. It’s a bunch of AI tools jumbled together and is basic at best. It also buys into the entire Tech feudalism bullshit by being a cloud service.
If this came to parity with any of the billion dollar apps it’s trying to replace we would have new laws banning it somehow within a month
If it comes at parity and businesses start using it, then not only it would be banned but also the dev will be sued to hell for “infringing” their “patents” and “revenue loss” caused because of it.
No business would ever use these due to the license nightmare these projects would create.
You don’t know Indian small-mid businesses lol. They already pirate a lot of stuff. Adobe and Corel are very strict here—if they find out you are using an unlicensed version of their software, they send legal notices to pay a shit ton for the damages and buy the licensed one for a lock-in period before even suing. Most, if not all, give in because there is no way out of this. Yet a lot of them are willing to take this risk as the potential savings are much higher than the losses if caught.
If these businesses get a grey zone free product, they will happily switch. Big corpos will mostly not.
Where’s the legal limit?
If I use AI to make and sell a Ford truck, will Ford sue and we can get precedent that AI use is still a copyright violation?
if you didnt call your truck ford or used patented stuff
I don’t really think that copyright is the major issue here, but patents. Adobe has a metric tones of patents and the rebuilds will most likely conflict with a some or even lots of them.
AI itself is theft
Only 99% of the time.
It’s possible to build models on only copyleft data, and include all relevant attribution
You wouldn’t download a car?
I have and I will
Just brand it fjord
Great, more slop
Well, if thanks to this we finally get open office to figure whatever tricks MS used to get documents to render fully correctly ONLY in office, consider me in.
Yeah, why would you waste time with these instead of Gimp, OpenOffice, etc? Except for the clicks.
i assume this person is making a statement more than anything. but gimp is not an adobe alternative. affinity is but not gimp. but since this is an open source commjnity i should point out affinity is not open source
Yeah, there are already good alternatives for the office package. I don’t see why anyone would use a slop version instead of them.
I can’t say anything about Photoshop and autodesk since I don’t use them.
You’ve obviously never used Photoshop or GIMP because if you have then you would immediately understand why. GIMP is a completely different experience, and its UX is far inferior to Photoshop. On top of that, anybody who is used to the workflow in Photoshop will have a very steep learning curve using GIMP.
Believe it or not, but most people just want a tool that works for what they’re trying to do. These apps have some bugs and rough edges still, but they’re very much usable and make it trivial to switch for anybody who’s used to Photoshop.
The venn diagram of what GIMP does and what Photoshop does isn’t the singular circle people assume. I, too, loathed my time with GIMP wondering how it ever got so popular in the OSS community, but then you realize it’s kind of all they have so of course they’ll support it no matter what.
I haven’t used it in years and based on that experience, I’m not rushing to try it again anytime soon. The UI felt like a UX designer’s prank on the world.
Yeah, you should definitely try using it again - especially since the big 3.0 release.
Menus and tool names/functions still do not map perfectly onto Photoshop’s (it is its own thing after all, so why should it?), but it is a serious and sophisticated piece of software. Easily adequate for my professional reproduction work.
I switched to it from Photoshop two or three years ago and had to spend a few hours watching tutorials and reading the manual to make the transition. But now there is hardly anything I can’t do in GIMP at least as fast, easily and reliably as I could in Photoshop.
I’ve been using the recent versions of GIMP and it’s surprisingly usable. Of course tools are a bit different and in different places compared to Photoshop, but that goes for any software.
Yeah, these are very different tools. And yeah UX in GIMP is something else.
I agree, then I remember those infuriating pricks asking “Can I draw a circle in GIMP yet?” in every thread about updates. The slop is for those people.
Is OpenOffice still maintained?
Is OpenOffice still maintained?
The descendant of it called LibreOffice has been the well-maintained thing to use for the last 15 years.
about OpenOffice:
Sadly something called OpenOffice is also sort-of still maintained but should not be used under any circumstances. It has basically been a zombie project since Oracle bought Sun Microsystems in 2010 and (as the Apache OpenOffice wikipedia article explains) is not safe to use:
Difficulties maintaining a sufficient number of active developers and code contributors to keep the project viable have persisted for several years. This has led to persistent problems providing timely fixes to security vulnerabilities since 2015. In March 2026, the Apache Security Team raised OpenOffice’s security risk status to “red” due to unfixed vulnerabilities over 365 days old.
There is a somewhat complicated history about why the fork from the old
OpenOffice.orgto LibreOffice was necessary and how/why something else called “Apache OpenOffice” came to exist after the fork; the tldr is that Larry Ellison is a real-life comic book villain so his companies strive to do the worst thing possible at every turn.Yeah, I know about LibreOffice as I use it myself. That’s why I was wondering why OpenOffice was brought up.
It’s very obviously better to have open tools than closed ones. This whole screeching about slop is both incredibly tiresome and irrational in the extreme. These are new tools that make software development easier, people are making useful things with them, and they’re helping people move off proprietary software. That’s obviously a net positive.
If you don’t like the tools people are using go ahead and make something comparable by hand, except we both know that you can’t. So, you’re adding nothing constructive to the discussion here.
LibreOffice?
For an office suite LibreOffice is fine, although compatibility with MS Office is still spotty. But for graphics there really aren’t drop in replacements for Adobe apps right now.
At the end of the day, I don’t really care what tools software is made with. Either it works well or it doesn’t. You can make quality projects using LLMs and you can make really shitty software without them. The deciding factor in both cases is skill ans knowledge of the developer building the app.
LibreOffice is fine, although compatibility with MS Office is still spotty
Have you seen anyone claiming that this brand-new vibe-coded thing has better compatibility (and/or feature parity) with the proprietary applications it claims to replace than the mature free software solutions currently do?
I would be surprised if it actually does anytime soon.
It’s very obviously better to have open tools than closed ones.
I agree, if it works well and it’s freely licensed it’s a good thing. It isn’t clear how well this actually works though, and the fact that the author is disparaging existing free software solutions to advertise his business selling genAI tokens is not a good indicator.
This whole screeching about slop is both incredibly tiresome and irrational in the extreme. These are new tools that make software development easier […]
It’s made it so easy that there is currently a deluge new projects which often seem plausible at first but mostly turn out to actually be garbage upon closer inspection.
It’s irrational not to be skeptical of a two-week-old project claiming to be ready (or “almost” ready, lmao) to replace multiple 30-year-old suites of software.
Let me know if I’m mistaken, and anyone other than the author tries it and credibly claims that this thing is actually a better (in any way whatsoever) replacement for MS Office than LibreOffice is.
Have you seen anyone claiming that this brand-new vibe-coded thing has better compatibility (and/or feature parity) with the proprietary applications it claims to replace than the mature free software solutions currently do?
Given that people are literally just reverse engineering these applications by having the LLM decompile it and observe what it does in memory, yeah I expect these will be compatible much faster than manual efforts. I did something similar recently where I had an LLM figure out the proprietary format for the way my Nikon camera stores RAW files. There’s currently no open source implementation for it, and now I can read them using my own library. So, something that used to be a herculean effort before, is something you can now do in a few days using an LLM.
I haven’t played with the Office stuff, but I am using his PhotoCraft and LightCraft, and they work fine for what I need. I can process my photos using completely open source tools now that have a UX I’m used to. Yet, I’m aware that LightTable exists, and I’ve tried using it, and it was not a great experience. Given how fresh these projects are, it’s absolutely incredible to me. And with LLMs it’s possible for me to fix whatever issues I have with the app myself. The reality is that most people don’t really need to do anything incredibly complex with these tools. So, if they do what you need you have an app you can keep using indefinitely. The hard part has always been to build out the initial features and the UX which was just too hard to do by hand.
It’s made it so easy that there is currently a deluge new projects which often seem plausible at first but mostly turn out to actually be garbage upon closer inspection.
You’re saying this as if NPM ecosystem didn’t exist before LLMs. The reality is that there has always been a ton of garbage projects. Over time people gravitate towards projects that actually work and are useful to them. And this isn’t hard problem people keep making it out to be. You look at the number of stars a project has, how long it’s been developed, how many users it has, and so on. This gives you an idea of whether it has legs or not. I’ll certainly trade having to rely on proprietary software for the problem of having too many open source options.
It’s irrational not to be skeptical of a two-week-old project claiming to be ready (or “almost” ready, lmao) to replace multiple 30-year-old suites of software.
Seems to me that the rational thing is to try the project, see if it does what you need and decide based on that. But that’s just me.
people are literally just reverse engineering these applications by having the LLM decompile it and observe what it does
Have you seen the creators of this particular project claim anywhere that they decompiled anything? I’ve seen several commenters claiming that but I think they’re incorrectly assuming that that’s what they did.
For one thing, decompiling and recompiling Adobe or Microsoft code would surely be viewed as copyright infringement if there isn’t a clearly-documented “cleanrooming” process in the middle (having an LLM write a spec (in English) from the decompiled code, and having another session without access to the copyrighted code write new code from that spec - a fun LARP many people are doing lately).
But also, if they were actually doing that then I’d expect more feature parity than I’ve seen in the few youtube videos I’ve skimmed through showing these apps. I’m too lazy to find the link now but I watched one comparing PhotoCraft to Photoshop, and one example was that PhotoCraft’s Levels diagram is very primitive in comparison to Adobe’s (or to GIMP’s for that matter).
I did something similar recently where I had an LLM figure out the proprietary format for the way my Nikon camera stores RAW files. There’s currently no open source implementation for it, and now I can read them using my own library. So, something that used to be a herculean effort before, is something you can now do in a few days using an LLM.
Congratulations, that’s awesome (and I don’t doubt it). But implementing a RAW format is a lot easier than re-implementing all of the Photoshop features which are required to be able to say (honestly, a least) “this has .PSD file format compatibility” without a long list of caveats.
I am using his PhotoCraft and LightCraft, and they work fine for what I need. I can process my photos using completely open source tools now that have a UX I’m used to.
I am curious how much you’ve actually used it. Eg, can you confirm what I saw on youtube showing the Levels adjustment dialog lacking most of the features found in Photoshop’s and GIMP’s? (Is that still the case in the current version?)
And have you noticed it having compatibility with (or at least some support for) any modern PSD file format features which GIMP lacks?
You’re saying this as if NPM ecosystem didn’t exist before LLMs.
yes there was a lot of crap before 😭 but don’t you agree it’s 1000x worse now?
You look at the number of stars a project has, how long it’s been developed, how many users it has, and so on. This gives you an idea of whether it has legs or not.
This project has a lot of stars but only because it just got a ton of clickbait press grossly exaggerating its completeness. I assume the vast majority of the stars are from people who have not tried running it. How long it’s been developed is… two weeks, as of today. How many users? It’s far too soon to say.
I’ll certainly trade having to rely on proprietary software for the problem of having too many open source options.
I agree with you here! But I’m assuming (perhaps incorrectly) that this particular one is not likely to ever become a particularly good option.
Given how close the project matches the original, I have a hard time imagining this could’ve been done without examining how the original functions. And whether it’s copyright infringement or not is of little interest to me since I view copyrights as being inherently harmful. However, since the implementation is using a different language, that does make the implementation itself a clean room one.
Ultimately, it’s a moot point whether they decompiled or wrote a spec from scratch though. What matters is that the apps work and it mimics what Adobe ones do sufficiently well to be useful.
And it still takes time to add features using LLMs. It’s not magic, and I’m more amazed how much they managed to add already rather than it not having parity yet.
Reimplementing Photoshop is obviously a much bigger effort, but I’m just using that as an illustration that LLMs are pretty good at reverse engineering work. Which makes it plausible to me that they could get a lot of the features figured out quickly.
I’m not a designer, so my needs are meagre. I want layers, to be able to select objects, add text, do color correction, and so on. Both GIMP and Photoshop are huge, so I haven’t had a chance to explore the depths. All I can say is that I was able to get the things I normally do without any real friction. It does appear to work with PSDs fairly well, but again I don’t have really complex ones because I use the tool in an amateur way to begin with.
What I can definitively say is that the UX is strictly superior to GIMP. Doing stuff like text manipulation like changing size or selecting fonts has always been a pain in GIMP, and as much as I want to like it, I find it painful to use. Photocraft apes Photoshop UX which I find to be superior. So, the feature parity isn’t really the stumbling point for me, it’s the UX.
But that’s my whole point here, most people are in the same boat as me. They do a few specific things with a tool, and if those things work then the tool solves the problem.
How long it’s been developed is… two weeks, as of today. How many users? It’s far too soon to say.
But this is something that’ll sort itself naturally over the coming months. If the developer stays active and continues working on it, then it’ll keep getting better. If they abandon it and move on then it’ll either die or somebody else picks it up. But it is in a fairly usable state as is from my experience, and I’d argue a lot of the hard work has already been done. So, we’ll have to just wait and see what happens with it.
Another point to mention though, is that it is becoming viable to maintain your own tools now. For example, if Photocraft got abandoned. It works well enough for me, and I could have an LLM fix any gaps in the way I’m using it. I don’t have to maintain a general tool that everyone can use, I can just have one that does what I need.
The barrier before was that you had to spend a lot of time to figure out how any one app works to make meaningful changes to it. And you only have so much time in a day, so you can’t really take ownership of a bunch of tools like that. But with LLMs it is becoming much more practical. Grab an open source app, adopt it to work the way you want, and just keep using it. If you ever need new features, you just have the LLM add them in for you.
And if we get to the point where all this stuff can be done using local models, then we really could see Stallman’s vision for GNU become a reality. Regular people, who aren’t developers, could use fully open source stacks, and they could modify software to work exactly the way they want. If we’re lucky this might kill closed source software entirely in the long run.
I don’t understand why anyone is interested in using these. They simply look like the real thing. There is nothing indicating they work remotely the same under the hood.
If you were to generate a bug for bug copy that would be one thing, this is just a doppelganger.
Were it made with Ai or not, its just not something that has any real value.
Decompilations do work the same under the hood.
I don’t think any decompiling was involved here; if it was, Adobe and Microsoft would have DMCA’d it off of github already.
Have you tried it to say that it just looks like the real thing and that it doesn’t work the same?
It isnt even written in the same language. It won’t be a bug for bug copy. Just slop.
I don’t need to buy the Temu knockoff to know it’ll be s shitty knockoff that looks good on the storefront.
Buy?
It’s a metaphor.
Ok
Massive nothing burger, those sloppy clones are fucking terrible in production, and dont believe me, look it up yourself.
Id love for it to be really of substantial value as it is now though.
It is funny though. Microsoft being undermined by the very thing they’re using to undermine working class people.
Funny seeing people losing their shit yet again in front of “AI” claims…
Like all the other spectacular previous claims that is not mentioned: it’s a bird with half wings - it does not fly.
I also created a Photoshop clone, the only caveat is it crashes at start, BUT I TOTALLY DID IT!
Did you try it? No. You concluded that if it works, your worldview breaks, so it cannot work.
But someone tried it.
https://lemmy.ml/post/53794973
(Don’t look at the post I linked, your fragile worldview can’t handle that)
I watched the video (partially because I can’t stand it, such annoying video).
So what’s your point?? Go use it if that’s your turf, don’t come around insulting me for no reason.
Do you have a skin in that fame? Why are you so uptight about a vibecoded project? And you are all on the defensive while telling me I have a fragile worldview he he… Projection? Maybe?
There are ton of missing features, buggy ones, crashes… What’s the point of your dummy doing some tests on the slop?
My point was/is: it seems easy to claims victory these days with half a winning battle.
My point still hold, while yours seem moot.
Good day my little world shattering wannabe ;)
I have a simple reason, I hate closed software, I hate adobe, I hate microsoft. Like every real free software advocate.
Did it crash on startup? No? Well then you lied. You lied for adobe, bootlicker.
And of course your worldview won’t fall apart that easily, you can always just apply another layer of cope.
Did it crash on startup? No? Well then you lied
If you read again, you realize I am not talking about what they slopped, I was saying that I did mine and it is crashing at start, see by yourself:
I also created a Photoshop clone, the only caveat is it crashes at start, BUT I TOTALLY DID IT!
That’s text comprehension, I am just going to end this charade right aboutttt… Here.
Tbf they’re replacing other vibecoded slopware… Can’t be much worse than what it’s going after - and at least it’s free.
I think they’d eat their own dogfood?
I’m pretty happy with libre office. Not keen on AI code
Not going to use this one either, but I wish I could use LibreOffice.
It’s really laggy for me on Windows. Particulary when interacting with the window, moving or resizing it. It’s not smooth at all. As someone who uses everything windowed and moves windows around all the time, I tried using it, but it’s unusable for me imo.
