Story AI on the desktop
The Story AI choice belongs to the computer, not to a campaign: pick once and every campaign on your device world follows it, new or old. The Story AI button on the home screen reopens the screen. Inside a campaign, the Setup tab shows the device's choice and sends you here to change it.
A human Dungeon Master
No AI. You or a friend runs the table from the DM seat with the console, the binder and assisted mode off. Choose this to try the app with nothing to configure.
AI Dungeon Master via your OpenAI API key
Paste a key from platform.openai.com. The form has three fields: the key (sk-...), the Dungeon Master model (default gpt-5.1) and a cheaper utility model for summaries and bookkeeping (default gpt-5-mini). The key is stored by your local server, never sent to players, and is the one key for this whole device: narration and pictures for every campaign. Once saved, the field reads "Saved on this device. Blank keeps it", so switching models is one field. Usage is billed by OpenAI to your account. What leaves your machine: the prompt, which includes the story so far, the sheets and the scene. See OpenAI and compatible keys.
An agent you already have
If Claude Code, Codex, opencode or Grok Build is installed and signed in on this computer, it can narrate on its own plan. The screen lists the four with their state (ready, sign in needed, not installed, not available here), the version, and how well each is locked down. Pick one, choose a story model and a bookkeeping model from what it offers, and play. The app never asks for the agent's password or key, and the agent gets none of its own tools: no shell, no files, no web, only the table's rules turn by turn. Not installed or not signed in? The screen shows the one command to run, with a copy button (a PowerShell command on Windows), and finds the program even when the app was started from a launcher without your terminal's PATH. Not available in the Flatpak build. See Bring your own agent.
Local AI on this machine
Free and private. The app measures memory and graphics hardware, then offers a storyteller sized to it:
| Tier | Download | Needs about |
|---|---|---|
| Qwen3.6 35B, Q8 | 38.5 GB | 45 GB of memory |
| Qwen3.6 35B, Q6 | 31.9 GB | 38 GB |
| Qwen3.6 35B, Q4 | 22.2 GB | 28 GB |
| Qwen3.6 35B, Q3 | 16.9 GB | 22 GB |
| Qwen3.6 35B, Q2 | 12.3 GB | 17 GB |
| Small machine fallback: Gemma 4 12B | 6.8 GB | 10 GB |
| Utility model: Qwen3.5 4B | 2.9 GB | 5 GB |
The engine is a pinned llama.cpp server the app installs and runs for you, with tool calling and a 64K context already set. Expect a full turn to take one to three minutes on a single GPU, longer in combat. The memory figures are GPU memory, or unified memory on a Mac or an integrated GPU. Optionally, on Windows and Linux, Install image generation (ComfyUI) adds Stable Diffusion XL for scene art: about 15 GB including Python packages, and it needs Python 3 and Git installed first. Uninstall either from the same screen; campaigns and their art stay.
Switching
Any door can be swapped for another at any time. Campaigns keep their chronicle; the next turn uses the new narrator. A key you saved is kept until you replace it.
What is not on the desktop
ComfyUI at a custom address, narration (Kokoro, or any OpenAI-compatible speech server), the built-in Whisper for dictation and push-to-talk, and OpenRouter as a text backend are configured through the world's own admin panel (account menu, Admin), the same as on a self-hosted server. The Story AI screen covers the common cases; the admin panel covers the rest. An administrator signed in to a self-hosted server can also run that server's guided setup as a native screen in the app.