An AI agent that works inside a Godot project

The difference between an assistant and an agent is not the model. It is the surface. An assistant answers about your project. An agent acts on it — it can look at the world, change files, and see whether the change worked.

For a game, that surface has to include the world itself. Reading the scripts is not enough, because most of what a game is lives in the scene: what is placed where, how the ground is shaped, where the water is, what a character is standing on. An agent that can only read text is reconstructing the world from a shadow of it.

Director 1 works against a world it can actually address. Terrain, water, weather, buildings and characters are things it can reason about directly rather than infer from a folder of scripts. That is the difference between an agent that composes reliably and one that produces confident nonsense.

Director 1 writes code. You describe behaviour — the door needs a key, the wolves hunt at night, falling in the river costs you a life — and it writes the GDScript into your project. The code is visible. You are not asked to read it, and nothing stops you.

What it does not do is build the world for you. That is you, by hand, in the builder: shaping ground, outlining water, placing things. This is a deliberate division rather than a missing feature. A sentence is a bad instrument for a hillside, and taste does not compress into a prompt.

It also does not decide whether the game is good. You play it and say. That handoff is the normal loop, not a failure of the agent.

Stage Engine is a desktop app for Mac and Windows with Godot inside it. The agent is operating on files on your disk, in a real Godot project, and when you press play the game runs on your machine at your framerate. Nothing is streamed and nothing is rendered elsewhere.

That matters for an agent specifically, because the feedback loop is short. It writes, you run it locally, you see it fail, you say so. A round trip through someone else's render queue would make that loop slow enough to stop being a loop.

Building does need an internet connection, since Director 1, asset generation and world data all come over the network. Playing the result does not.

Stage Engine exposes its capabilities over MCP, which means you are not required to use Director 1 as the only agent in the loop. If you already work with an agent you like, it can drive the same surface. Access to that from outside the app is part of the paid plans.

The point of that is not novelty. It is that the valuable part is the capability layer — the fact that the world is legible and operable at all — rather than any particular model. If the layer is right, a cheaper model composes reliably against it, and that is the design being aimed at.

The download is free with a free plan. Indie is $10 a month and Pro is $50, and both buy more usage rather than a different engine.