Godogen
Dev tools
game generation pipeline
SHOW HN2026
How HN took it
24 positive, 23 neutral or asking, 4 mixed, 26 critical, out of 77 comments about the project. Thread score +0.02.
Execution: 6 for, 15 againstIdea: 10 for, 5 againstDocs: 1 for, 2 againstDesign: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful for prototyping and jumping-off points for game ideas
From 3 comments
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…
Underphil on HNThanks 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…
sacredSatan on HNThis is a really good idea. Image all the game devs that hate writing actual code but sits on some seriously good ideas. This will help so many to get the initial MVP thats…
SilentEditor on HN
Evaluation loop with visual QA is a good idea
From 2 comments
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…
dahrkael on HNThe 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…
martinvalchev on HN
Custom GDScript reference system is valuable
From 2 comments
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…
saltynews on HNI 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…
4riel on HN
Objections
Demo games look lifeless, buggy and not good quality
From 4 comments
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…
hmokiguess on HNGamedev here. I looked at the video, awful results, better start with a template.
stephc_int13 on HNI 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…
eudamoniac on HN“Real games” the most incomplete bullshit you ever saw passed off as a game. The starting points of Three.js examples are more of a game than anything here. Stop saying AI is…
twelvevaginas on HN
Generated games are slop and lack human taste or passion
From 3 comments
The problem is your passion is for the LLM workflow and not the games, and the end result is going to be a powerful way to generate mediocre games.
krapp on HN>Acting like most people made good and enjoyable games when it was handcoded is just not right. Every good and enjoyable game made was handcoded, with art, music, dialogue and…
krapp on HNI 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…
rybosworld on HN
Lacks unit testing
From 1 comment
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…
scumblr on HN
Should use C# instead of GDScript
From 2 comments
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…
bhu8 on HNThis 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.…
stevefan1999 on HN
Requests
Publish a full playable game made with the pipeline
From 1 comment
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…
hmokiguess on HN
Support C# instead of only GDScript
From 1 comment
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.…
stevefan1999 on HN
Better 2D animation and rigging for 3D assets
From 3 comments
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…
vunderba on HNHey bro, been working with the Godot MCP for about a year now myself. This is really cool! The two loops I think you should add / address: 3D assets / rigging. This is the…
gneuron on HNNice 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…
guitarlimeo on HN
Let the QA agent play the game, not just view screenshots
From 1 comment
Hey bro, been working with the Godot MCP for about a year now myself. This is really cool! The two loops I think you should add / address: 3D assets / rigging. This is the…
gneuron on HN
Questions
What does the asset generation pipeline use
From 2 comments
Awesome stuff, what does it use to generate the assets?
yagizdagabak on HNthis 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…
dahrkael on HN
How the lazy-loaded API reference handles wrong lookups
From 1 comment
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…
martinvalchev on HN
Cost of running a full game generation
From 1 comment
Can you speak to the total api costs to create one such game? Not looking for exact numbers but I'm curious if to create, say, that snowboarding game, it cost closer to $5, $50,…
chrisshroba on HN
How it compares to Tesana
From 1 comment
How does this stack up against something like Tesana [1], which is also Godot based? Would it be accurate to say that it's like "Tesana but local"? [1] https://tesana.ai/
avaer on HN
Alternatives named
Google Playables Builder
From 1 comment
Here's Google's: https://www.youtube.com/playablesbuilder/
socalgal2 on HN
Tesana
From 1 comment
How does this stack up against something like Tesana [1], which is also Godot based? Would it be accurate to say that it's like "Tesana but local"? [1] https://tesana.ai/
avaer on HN
Godot MCP servers with Claude Code
From 1 comment
Hey bro, been working with the Godot MCP for about a year now myself. This is really cool! The two loops I think you should add / address: 3D assets / rigging. This is the…
gneuron on HN
Raylib with C# built by hand
From 1 comment
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#),…
c0m47053 on HN