Skip to content

For AI agents

This documentation is built to be read by agents as much as by people. If you are an LLM or operate one, everything here is available in machine-friendly form — no HTML parsing needed.

The one-request orientation

Fetch /llms.txt — an annotated map of every page with links to raw-markdown versions.

Raw markdown for any page

Append .md to any page URL:

Every HTML page also carries a <link rel="alternate" type="text/markdown"> head tag pointing at its twin.

The whole docs in one request

  • /llms-full.txt — all pages concatenated (small enough for any context window).
  • /agent-corpus.json — structured JSON: [{ id, section, title, url, text }] per page, regenerated on every deploy.

Give your agent Framehood itself

The docs describe the product; the product is also agent-native. Connect Framehood to Claude or any MCP client and generate image, video and audio from inside the agent: see the MCP guide and the quickstart.

Framehood