I think the software engineer types in this thread misunderstand what makes game developers tick. A lot of people here do game dev as a way to explore new ways to code. My sister is an indie dev and to her, code is an unavoidable means to an end (creating a game). So many games are absolutely spaghetti on the inside because the creator is deeply uninterested in the art of code. So to that end, LLMs are actually an awesome thing to enable creators to experiment more freely.
FWIW, I’m a platform engineer who is actively mourning the loss of reliability and care given to production code. I just think games aren’t an area where this is nearly as much of an issue.
This doesn't just generate the code though. It generates the "art" and everything else as well. Ideas are beyond cheap. It's the personal creativity that makes games good or bad.
And saying the code doesn't matter is just ignorant. In plenty of great games the art doesn't matter. In plenty of others the code doesn't matter. Or the dialogue. But the reverse is just as true. In a game with tight, fluid player controls, the code to make that happen takes just as much creativity and skill and human touch as any other form of art. A driving sim made by someone deeply uninterested in the code they write will never feel good to play.
It is just so disingenuous to say that people who focus more on the code side of game development aren't creators. If I can make a demo with a black rectangle jumping around on some red rectangles and hand it to someone and have them say it feels like they're jumping around as a cat, with no art or animations, I'd say that took creativity and a human touch that ai is nowhere near being able to emulate.
> I just think games aren’t an area where this is nearly as much of an issue.
That's news to me as a game dev. I only get a few milliseconds every frame in which all my calculations need to run. If my program is built on spaghetti code, performance suffers and it becomes very noticeable very quickly.
I saw the demo video, in all honesty, they felt really lifeless to me. The snowboard one was the one that most caught my attention but then the mechanics, and movements of the character, made it seem like it's really bad physics. Do you have a published game I could try rather than these demos? I'm curious
Personally, most of the time I spend prototyping is taken up by wrestling with tools, engines, and assets. Then I discover that my game design just isn't very fun. I've been experimenting with using LLMs to speed up building prototypes because I want to spend a higher percentage of my time adjusting game design and feel rather than solving problems that are irrelevant if the game's not fun to play.
If I was working on this full time the investment of learning an engine thoroughly would be worth it, I imagine. Game dev is a hobby for me, though, and what motivates me is making fun games. If I stumble across a game idea that's really fun and worth releasing to a wider audience there's nothing stopping me from building a better version of the game by hand at that point.
yes! you wrestle with it because the starting boilerplate is thpically a do-once operation. if you stay working on one project for a few years, you will no longer know how to start the next project, and with modern software, starting a new project in two years from now will be nothing like starting one now
I had the same issue where startup cost was a pain to get little prototypes going. I reduce the cost by making re-usable components. Even if I don't intend to reuse something I still make it a component-esque manner.
It helps that I mostly want to make certain types of games but I think everyone does. I have drop in CameraController, First Person rig, 2D inventory system, dialogue system etc. All flexible enough to get wired into the one off game manager or whatever it needs to plug into.
Curation is probably going to be king over the next years. A game simply existing is no guarantee that any effort has been put in or that even the developer played it.
You'll need to find a publisher, journalists, etc to market your game. You'll ask your friends what they are playing instead of scrolling the store page. Trusted platforms will promote games that are actually worth looking at. This problem already exists on modern platforms like Steam but AI is supercharging it.
This. I've been making a game in Godot with zero AI help. Because I enjoy it. I enjoy solving with weird coding problems you run into. I enjoy leaning as I fixed things. I do it out of love for the process, knowing competition right now from things like this means a flooded market. But I'm ok with that and must be because the other option is to quit.
Great work but why not use C# instead of GDScript?
LLMs are really good at C# (and tscn files for some reason), so that solves the "LLMs suck at GDScript" problem. Also, C# can be cheaper in terms of token usage (even accounting for not having to load the additional APIs): one agent writes the interfaces, another one fills in the details.
Saying this because I had really enjoyed vibecoding a Godot game in C# - and it was REALLY painful to vibecode with GDScript.
Context: I've been using agents (both Claude Code and Codex) for my daily work and for personal projects, but always in domains where I had some knowledge and I'm currently happy with them.
I tried using Claude Code to build an RPG game with Godot and GDScript, using free to use assets: a total failure :/
The game was supposed to be many implementation steps long but I asked Claude to first produce a one area demo, so I could test the assets and choose the one I liked. First it produced some garbage using the assets randomly. Then it tried to copy from an existing demo but it had not idea where a door or a path were and at a certain point it even admitted it with something like: "I can't design an usable and nice area: I either make it functional and ugly or I copy and adapt the existing demo but I will have no clue about what is what"
I've never even attempted to develop games before so I'm sure I don't even know the basic concepts, but this use case definitely didn't work for me.
Maybe it could generate the code of the game if I provided the full design?
I think this is pretty cool, all things considered. I think it’s unrealistic to expect anything that’s been one-shot to have much polish or charm.
Something I’m surprised about is the lack of unit testing. Agents are remarkably good at creating tests and GUT testing is pretty well developed; having some good unit tests would really assist in the subsequent steps where you polish controls, add features, etc. Without these, I think things will get off the rails pretty quickly.
This will do poorly with the HN crowd because they can write or understand code. This is an incredible tool for TikTok/nontechnical people who don’t know anything about ai, and want to see their random idea turned into a game. Really cool!
Everything about this feels like AI slop, including the post which is very clearly AI written. I'm sorry but if you aren't even willing to put any effort into writing a post showcasing what you have worked on what is the point of anybody taking a serious look? And the tools are clearly AI generated as well, I can even tell where you used Gemini in some places because you left in it's distinctive comments. Not to mention the showcase games are meme-tier.
I feel like this could be a real positive thing if you had spent some effort writing about how and why this is useful, and targeted this more for learning + artist assistance versus just generating a complete game. Gamers universally do not want more AI slop, but tools that artists and programmers could use to automate busywork or learn the engine would have been much better.
Very interesting. Have to admit, I assumed Godot was just out of the realm of agentic dev. I decided to actually build a game a few months ago, and went with Raylib (with C#), and it worked out pretty well (https://github.com/alexwlsnr/neo-arena)
I had assumed with the complex mix of scripts and the scene graph in Godot wouldn't be a good fit (personally trying and failing to make games in it by hand in the past may have been a factor)
Perhaps I'll give this approach a go if inspiration strikes!
As a Godot user, GDScript's unique syntax often trips up standard LLMs, so your custom language reference is a game changer. Integrating Claude Code directly into the game dev pipeline like this shows where the future of 'Agentic Workflow' is heading.
This actually produces more impressive results than I expected. My understanding was that models are quite poor at spatial reasoning/understanding, so I'm surprised it can generate such good assets. Do you use different models for the 3d generation?
The lazy-loading approach for the API reference is clever. Did you consider embedding a smaller, distilled subset of the most-used classes permanently in context, and only lazy-loading the long tail? Curious whether the overhead of deciding what to load ever causes cascading errors where the wrong API gets pulled in.
Also interested in the visual QA separation - using a model that sees only screenshots and never the code is a genuinely good idea for avoiding confirmation bias. Did you try using Claude for that role too, or was Gemini Flash specifically chosen for cost reasons?
I am not a game developer but a platform developer. The custom reference approach is spot on and that's a massive job.
I compiled 202 tips from 10 'important' CC users into a repo and plugin. You might want to ask CC to review it and see if any of it is worth implementing in your skills as well: https://github.com/4riel/cc-bible
The 2D sprites in the bike riding scene are a bit of a mess. Honestly consistent 2D animation is difficult.
You've basically got two approaches right now - use a openpose style controlnet representing a walk cycle in conjunction with img2img OR you can try using a walk LoRA with WAN to generate video and then clip out 4-8 frames that represent a good loop from the video.
I can't decide if this is impressive or not. At first I think it is, but also the best demos you could find were not good games, and likely not even good bases for further iteration. It seems pretty likely that this tool would increase the speed of shipping a salable game by zero minutes. So it's kind of impressive but at the same time not.
There's understandably a lot of negativity in here, myself included. But isn't this at least good to create a "jumping off" point for building a game? The demos might be shit but using them to create a basis for an idea seems like it could remove a lot of the headaches of prototyping and early-stage burnout.
Thanks for not cherry picking the output. The demos look great for a single prompt output. I can see myself playtesting a mechanic that I just thought of but would probably take longer to implement in my own WIP game etc.
I think this has great value just now, can't wait for it to get better. Keep at it.
Very cool. Thanks for sharing! This introduced me to Godot, gave me an excuse to use Claude code and a few hours later had it all installed and created my first game/simulation.
Experimenting each night with a new game idea, genre, style, etc. Really fun. Thanks again!
What is the development loop like with this? There’s a lot of folks successfully building games with agents already on the AI gamedev Discord server. So I’m wondering if there were some shorter paths to your goal. You might want to exchange notes with folks there.
This thing is spot on for me as I'm evaluating trying to build games in Godot using Claude Code, but in C# (I have hacks to make it run on NativeAOT), but the result is...mixed. I see only GDScript option is available and that's kinda sad.
Woah! This is very timely. My 9-year-old has been playing around with Claude Code and creating games, mostly with Phaser. He's dabbling with some 3D games and I was just looking at Godot as an option yesterday.
Interesting. But if you claim "prompt in Godot game out", how do you deal with assets? I think assets pipeline is one of the most challenging parts in game dev. Is there anything similar but for Bevy?
I think this is a cool tech demo. But the commonality I see in all of these "let the agent run free" harnesses is that the output is never something I would want to use/watch/play.
I think minimizing the amount of human effort in the loop is the wrong optimization, and it's the reason we end up with "slop".
It's the dream of a lot of people to have a magic box that makes you things you can sell, or enjoy for personal leisure. But LLMs are not the magic box. And there may not ever be a magic box. The sooner we can accept that the magic box isn't in the room with us, then the sooner we can start getting real utility out of LLMs.
TLDR: Human taste is more important than building things for the sake of building them.
this is great, specially the evaluation loop. the worst part of using AI to make games is testing things work as intended after every modification specially if its a complex game.
Nice work, must have been a pain to get Godot's formats working with Claude. As another commenter suggested the demo videos don't do any justice to this project - yeah it's the magic that you can generate playable (wouldn't say complete myself) games with a single prompt, but the quality of those is exactly why people are so put off by AI slop. If this was a better harness that acted more like a tool I think it would be seen as more useful.
Btw: Have you looked at Tripo3D models' topology? Is it still so bad that if you want to make small edits you have to retopologize the whole thing first?
FWIW as a disclaimer I'm making my own game not using AI since I value learning the skills myself, but I am interested to see how fast AI tools adopt to gamedev. For now they've been more of a false shortcut in anything else than prototyping and semantic search ("I need to achieve this visual effect, what algorithms should I look up").
205 comments
FWIW, I’m a platform engineer who is actively mourning the loss of reliability and care given to production code. I just think games aren’t an area where this is nearly as much of an issue.
And saying the code doesn't matter is just ignorant. In plenty of great games the art doesn't matter. In plenty of others the code doesn't matter. Or the dialogue. But the reverse is just as true. In a game with tight, fluid player controls, the code to make that happen takes just as much creativity and skill and human touch as any other form of art. A driving sim made by someone deeply uninterested in the code they write will never feel good to play.
It is just so disingenuous to say that people who focus more on the code side of game development aren't creators. If I can make a demo with a black rectangle jumping around on some red rectangles and hand it to someone and have them say it feels like they're jumping around as a cat, with no art or animations, I'd say that took creativity and a human touch that ai is nowhere near being able to emulate.
> I just think games aren’t an area where this is nearly as much of an issue.
That's news to me as a game dev. I only get a few milliseconds every frame in which all my calculations need to run. If my program is built on spaghetti code, performance suffers and it becomes very noticeable very quickly.
Let there be games! And games there shall be, millions of generated games.
Can I go back to the 80's please?
It helps that I mostly want to make certain types of games but I think everyone does. I have drop in CameraController, First Person rig, 2D inventory system, dialogue system etc. All flexible enough to get wired into the one off game manager or whatever it needs to plug into.
Things will change rapidly in the nest 12-36 months and people with vision will outlast "craftsman" 100 to 1.
You'll need to find a publisher, journalists, etc to market your game. You'll ask your friends what they are playing instead of scrolling the store page. Trusted platforms will promote games that are actually worth looking at. This problem already exists on modern platforms like Steam but AI is supercharging it.
>A minute of silence to mourn the lost art of making games with passion.
There are still... dozens of us left!
LLMs are really good at C# (and tscn files for some reason), so that solves the "LLMs suck at GDScript" problem. Also, C# can be cheaper in terms of token usage (even accounting for not having to load the additional APIs): one agent writes the interfaces, another one fills in the details.
Saying this because I had really enjoyed vibecoding a Godot game in C# - and it was REALLY painful to vibecode with GDScript.
I looked at the video, awful results, better start with a template.
I tried using Claude Code to build an RPG game with Godot and GDScript, using free to use assets: a total failure :/
The game was supposed to be many implementation steps long but I asked Claude to first produce a one area demo, so I could test the assets and choose the one I liked. First it produced some garbage using the assets randomly. Then it tried to copy from an existing demo but it had not idea where a door or a path were and at a certain point it even admitted it with something like: "I can't design an usable and nice area: I either make it functional and ugly or I copy and adapt the existing demo but I will have no clue about what is what"
I've never even attempted to develop games before so I'm sure I don't even know the basic concepts, but this use case definitely didn't work for me.
Maybe it could generate the code of the game if I provided the full design?
Something I’m surprised about is the lack of unit testing. Agents are remarkably good at creating tests and GUT testing is pretty well developed; having some good unit tests would really assist in the subsequent steps where you polish controls, add features, etc. Without these, I think things will get off the rails pretty quickly.
I feel like this could be a real positive thing if you had spent some effort writing about how and why this is useful, and targeted this more for learning + artist assistance versus just generating a complete game. Gamers universally do not want more AI slop, but tools that artists and programmers could use to automate busywork or learn the engine would have been much better.
I had assumed with the complex mix of scripts and the scene graph in Godot wouldn't be a good fit (personally trying and failing to make games in it by hand in the past may have been a factor)
Perhaps I'll give this approach a go if inspiration strikes!
Claude’s the only one I’ve got working with GoDot.
[1] https://tesana.ai/
I compiled 202 tips from 10 'important' CC users into a repo and plugin. You might want to ask CC to review it and see if any of it is worth implementing in your skills as well: https://github.com/4riel/cc-bible
You've basically got two approaches right now - use a openpose style controlnet representing a walk cycle in conjunction with img2img OR you can try using a walk LoRA with WAN to generate video and then clip out 4-8 frames that represent a good loop from the video.
https://imgpb.com/ELJfWpi
[1] https://drive.google.com/file/d/1ozZmWcSwieZQG0muYjbj7Xjhhlz...
I think this has great value just now, can't wait for it to get better. Keep at it.
Experimenting each night with a new game idea, genre, style, etc. Really fun. Thanks again!
He and I will give this a spin this weekend.
I think minimizing the amount of human effort in the loop is the wrong optimization, and it's the reason we end up with "slop".
It's the dream of a lot of people to have a magic box that makes you things you can sell, or enjoy for personal leisure. But LLMs are not the magic box. And there may not ever be a magic box. The sooner we can accept that the magic box isn't in the room with us, then the sooner we can start getting real utility out of LLMs.
TLDR: Human taste is more important than building things for the sake of building them.
whats the art creation pipeline?
Btw: Have you looked at Tripo3D models' topology? Is it still so bad that if you want to make small edits you have to retopologize the whole thing first?
FWIW as a disclaimer I'm making my own game not using AI since I value learning the skills myself, but I am interested to see how fast AI tools adopt to gamedev. For now they've been more of a false shortcut in anything else than prototyping and semantic search ("I need to achieve this visual effect, what algorithms should I look up").