Point an agent at llms.txt

Point an agent at this site's auto-generated llms.txt and per-page llms.mdx instead of scraping rendered HTML — it discovers the docs from a clean index and pulls just the page it needs into context, no markup, no token waste.

Example

Fetch the index to discover structure, then pull a single page as Markdown:

# The curated index of every docs page, one line per page.
curl https://stitchapi.dev/llms.txt

# The clean Markdown form of one page — just this feature, into context.
curl https://stitchapi.dev/docs/agents/run-stitch-tool/llms.mdx

# When the agent needs everything at once, the whole docs concatenated.
curl https://stitchapi.dev/llms-full.txt

Each page already stands on its own — restating its premise rather than leaning on neighbors — so the Markdown the agent pulls reads correctly in isolation. The stitch it documents is the same one-source-of-truth definition the runtime uses.

Options

The site emits three machine-readable outputs automatically; you never hand-author them.

/llms.txt is the curated index — one line per page, title plus description — so an agent maps the docs structure before pulling anything.

A page's llms.mdx variant is the same page as clean Markdown, with rendered chrome stripped. Because guides are fine-grained — one page per feature — an agent pulls exactly one feature's page into context (say, just run_stitch) rather than the whole manual. That fine-grained, self-contained-pages design is what makes each llms.mdx a focused, extractable unit.

/llms-full.txt is every page concatenated, for when an agent genuinely needs the entire corpus in one fetch.

See also