{
  "id": 16295846,
  "title": "llms.txt v2: what an agent actually reads",
  "url": "https://urgent.news/2026/10/24/llms-txt-v2-what-an-agent-actually-reads",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-24T07:30:39.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/richicodes/llmstxt-v2-what-an-agent-actually-reads-3c43"
  },
  "original_language": "en",
  "account": "llms.txt v2 is the latest revision of the llms.txt proposal, published in August 2026. It addresses the question of how an agent finds the llms.txt file for a given page. The llms.txt file is a Markdown file that serves as a curated entry point for agents to access LLM-friendly content on a site. It includes a name, short summary, context, and a list of links to relevant content. Jeremy Howard published the original proposal in September 2024, and llms.txt is meant for on-demand inference, not training.\n\nIn v2, the changes include allowing any path, with the most specific file taking precedence. The file can now be located at /docs/llms.txt or any subpath, and agents should use the most specific file if multiple exist. Two Markdown URL forms are introduced: appending .md to the path (e.g., page.html.md) and replacing the extension with .md (e.g., page.md). URLs without a file name fallback to index.html.md or index.md.\n\nDiscovery through link relations is another improvement, using rel=alternate type=text/markdown to point to the Markdown version of a page and rel=describedby to link to the relevant llms.txt file. This can be implemented using link elements in the page's head or as an HTTP header.\n\nThe optional header form of llms.txt is no longer special and is now just a convention for secondary links. The header format allows adding the link information to server or CDN configurations without modifying individual pages. The demo in the proposal showcases how an agent walks from a page to its llms.txt and Markdown version using these new rules.",
  "summary": "This note has an interactive demo. Try it in the original The llms.txt proposal got its first big revision in August 2026, and the changes answer the obvious question nobody could answer before: given a page, how does an agent find the llms.txt that describes it? I read the new text, ran this site's own /llms.txt through the small reference parser that lives in the proposal's repository, and it…",
  "key_points": [
    "llms.txt v2 published in August 2026, addressing agent file discovery",
    "Allows any path, with most specific file taking precedence",
    "Introduces two Markdown URL forms and rel=alternate/rel=describedby link relations"
  ],
  "editors_take": "Standardizing discovery through specific file paths and link relations transforms the proposal from a simple file format into a robust navigation system for autonomous agents seeking machine-readable content.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}