Continuous early access builds
These unofficial early access desktop builds are mirrored as the continuous public release for Windows, macOS, and Linux.
The artifacts include the Electron desktop runtime and app dependencies. Local AI is optional and built in: the app can download a small model and run it on its bundled llama.cpp runtime, or connect to an Ollama, LM Studio, or llama.cpp server you already run. The generator itself never needs a model.
Compare the available version shown below with your installed version in the app's About dialog or Help menu update check.
New here? Start with the first dungeon quickstart, then return for downloads and known issues.
Looking for the overworld sibling? Hexes on Automatic has its own site and downloads, mirrored the same way as the hexes-continuous release; the first-run steps below apply to it too. The whole family is listed on the On Automatic page.
View SHA-256 checksum files, updater metadata, and all mirrored release assets.
These builds are unsigned, so every OS challenges the first launch. First-run steps for each platform and the current known issues are below.
Foundry VTT monster module
The whole monster library installs into Foundry VTT as a compendium for the GURPS Game Aid — every monster an Actor with its portrait, hex token, stat block, and armour. It installs from a manifest URL rather than Foundry's module browser.
How to install the Foundry VTT module — the URL, the steps, and what you need first.