I love making games, and I’ve been building a no-code game engine by extracting reusable components every time I ship a new game. It started as me scratching my own itch, and now it’s turning into a real platform.
Each game adds more building blocks to the editor: multiplayer, event systems, NPC behaviors, pathfinding, etc. I build a system once, and then anyone using the editor can use it in a click. For game logic, I recently added a visual event system I’m really excited about. It’s kind of like Unreal Blueprints, but focused on 2D. You pick a trigger, wire conditions, and chain actions in a node graph [1].
Big challenge right now: most people who want to make games needs assets, and don't know how to get/make them. So I’m building a marketplace where pixel artists can upload tilesets/characters, and unlike itch.io, assets are usable directly inside the engine. No ZIP downloads or import setup, just browse and drop into your game. A preview here[2].
Also, if you want to use the editor but ship elsewhere, you can export terrain, animations, and hitboxes to Godot 4. Nothing is locked in.
The engine/editor is at https://craftmygame.com if anyone wants to poke around! And you can test a games here[3][4], and 1 multiplayer game I've tested IRL in a bar [4]!
[1] https://youtu.be/8fRzC2czGJc
[2] https://www.youtube.com/watch?v=hScOK_naYnk
[3] https://craftmygame.com/game/e310c6fcd8f4448f9dc67aac/r/play
I'm a web developer and getting very interested in making games but obvuiouly have 0 ideas about it.
Can you recommend any cause to make using Claude Code.
As a web dev you're in a better spot than you think — state management, event handling, render loops... you already have the mental models.
Claude Code can genuinely help you with: - Scaffolding a game project (Phaser.js is great for web devs getting into 2D) - Writing boilerplate: input handling, collision detection, basic physics - Debugging weird edge cases in game logic - Generating utility code like sprite sheet parsers, tilemap loaders, etc.
What it can't do (and where most beginners hit a wall): - Game design. Knowing what makes a game actually fun is a skill Claude can't shortcut. You need to playtest, iterate, and develop taste. - Art and assets. This is the #1 blocker for most solo devs. Claude can't draw your sprites or design your tilesets. - Feel and polish. Tweaking jump curves, screen shake timing, hit feedback — that's all manual iteration. AI will give you "technically correct" values that feel lifeless. - Architecture decisions. Claude will happily generate an ECS system or a scene manager, but it doesn't know your game's actual needs. Bad architecture early on will cost you weeks later.
Start with a tiny scope (like a single-screen platformer), use Claude Code to move fast on the code side, but spend most of your energy on the parts AI can't help with — design and feel.
Also, shameless plug, if you want to skip the code entirely and just focus on making the game, that's what CraftMyGame is for. Everything is visual, no coding needed. Might be a good way to prototype ideas fast before deciding if you want to go deeper on the code side ;)
CraftMyGame can make something like retro street fighter(not need to be perfect) ? If it can, and allow me to export the code(I would like to add those game to some of the apps I'm planning), you'll get paying customer.