Docs for LLMs

Feed the MultiSet documentation to ChatGPT, Claude, Cursor, or any other AI tool, without pasting pages in by hand.

Building with MultiSet alongside an AI assistant? The whole documentation set is published in machine-readable form, so your assistant can read it directly.

File	Use it when
llms-full.txt	You are pasting context in by hand. Every page (portal, REST API, Unity, WebXR, Quest, native iOS/Android) concatenated into one file, roughly 450 KB. Drop it into the chat or attach it as a file.
llms.txt	Your tool fetches pages itself. An index of every page with a one-line summary and a link, so the agent reads the index first and pulls only the pages it needs. Point Cursor, Claude Code, or any MCP-style fetcher at this URL.

Any page as Markdown

Append .md to any documentation URL to get the raw Markdown instead of the rendered page:

https://docs.multiset.ai/basics/localization/hint-floor-height.md

Ask a page a question

Add an ask query parameter to a page URL and the response is a direct answer, with excerpts and links to the pages it came from. Useful when an agent needs one specific fact rather than a whole page:

GET https://docs.multiset.ai/basics/localization/hint-floor-height.md?ask=what+units+is+hintFloorHeight+in

Keep the question specific and self-contained, since each request is answered on its own.

These files are regenerated automatically whenever the documentation is published, so they always match the live docs. There is nothing to download or keep in sync.