{
  "id": 8755527,
  "title": "llms.txt v2: What the Spec Says, and What 137,000 Domains Show",
  "url": "https://urgent.news/2026/09/20/llms-txt-v2-what-the-spec-says-and-what-137-000-domains-show",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-20T19:17:36.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/angeo/llmstxt-v2-what-the-spec-says-and-what-137000-domains-show-48bh"
  },
  "original_language": "en",
  "account": "A recent study analyzed the llms.txt specification and the usage of llms.txt files across 137,210 domains, finding that most files receive no requests. The study, which was based on data from Ahrefs, reveals that 97% of valid llms.txt files received zero requests in May 2026, and only about 1,100 files received any traffic. Additionally, 19.5% of fetches came from AI tools, primarily coding assistants. The study also found that most published llms.txt files are malformed, with only about 55% following the recommended shape. The study examined the changes made in llms.txt v2, which introduced link relations and allowed for files to be declared as Markdown or HTML. Despite these changes, the study notes that only about 55% of the existing files follow the recommended shape. The study concludes that llms.txt, while not intended for search optimization, is still not universally ignored and is primarily used by AI coding assistants.",
  "summary": "The article discusses the llms.txt specification, focusing on the evidence from 137,210 domains tracked by Ahrefs in May 2026. The analysis found that 97% of valid llms.txt files received zero requests during that month, with only around 1,100 files experiencing any traffic. The majority of fetches (19.5%) came from AI tools, primarily coding assistants seeking documentation, rather than search engines retrieving information. The article also highlights that llms.txt is not intended for search engines but serves as a temporary solution to reduce token usage for AI coding tools.",
  "key_points": [],
  "editors_take": null,
  "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."
}