llms.txt v2: What the Spec Says, and What 137,000 Domains Show
Originally published on angeo.dev . Checked against llmstxt.org v2, revised 10 August 2026, and against the published request data as of September 2026. We shipped a validator that could certify a broken llms.txt file as valid. The bug was simple. The spec recommends a short summary in a blockquote under the title. Our checker looked for a line starting with > . It never looked at what came after…
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.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
