AI Resources

llms.txt

Machine-readable documentation — the index, the JSON catalogue, the full dump, per-page markdown, and the agent contract this site serves.

This documentation site serves machine-readable twins of every page, following the llms.txt convention — so an agent can pull exactly the docs it needs (or all of them) instead of scraping HTML.

EndpointContainsPull it when
/llms.txtSpec map — H1, summary, curated links, Optional restThe agent needs the map
/llms.jsonSame catalogue as JSON (slug, html, markdown)Structured clients
/llms-full.txtAll pages concatenated; teaching figures as blockquotesWhole-docs context
/llms.mdx/docs/⟨slug⟩.mdOne page as source markdownOne page — e.g. Vault
/changelogIndex of minor-version release-note pagesRecent history
/llms/agentsThe AGENTS.md contractSession bootstrap
/robots.txtAllow-all, including named AI crawlersCrawler policy
/sitemap.xmlHTML pages plus the machine endpointsCrawler map

Use them

curl https://oke.omqkhafi.dev/llms.txt
curl https://oke.omqkhafi.dev/llms.json
curl https://oke.omqkhafi.dev/llms-full.txt
curl https://oke.omqkhafi.dev/llms.mdx/docs/elements/vault.md
curl -H "Accept: text/markdown" https://oke.omqkhafi.dev/docs/elements/vault
curl https://oke.omqkhafi.dev/llms/agents

Which one first?

Start with /llms.txt. Fetch /llms-full.txt only when breadth matters more than tokens. Per-page /llms.mdx is the precise instrument. /llms.mdx/docs/⟨slug⟩/content.md still works.

The homepage Onboard AI button copies a one-line prompt that points an agent at /llms.txt plus /llms/agents on this origin — project-wide context, not a single docs page.

HTML docs pages advertise rel="alternate" type="text/markdown" to the twin. Accept: text/markdown on the same URL returns that twin and sets Vary: Accept.

/llms.txt opens with When to use this — The Problem, The Model, AGENTS.md, MCP, CLI, errors, npm, GitHub — then the curated map.

Crawlers that honor robots.txt are allowed; /sitemap.xml lists the handbook and the machine entry points.

How it pairs with the docs MCP

These endpoints serve the published docs of the framework. During oke dev, the docs MCP server also runs on :6536 (oke.docs.search / oke.docs.get), answering from the same content over the MCP protocol — pick the plain HTTP endpoints for one-shot context, the MCP tools when the agent is already connected as a client.

Learn more

  • MCP — runtime and docs MCP servers
  • Agent contracts — teaching agents the vocabulary these pages use
  • Reference — the most-cited pages for config questions

Next

On this page