llms.txt Validator
Paste your llms.txt or check a live URL to validate its structure: H1 title, blockquote summary, H2 sections, and well-formed link lists that AI assistants can actually use.
How it works
Enter your site URL and the tool fetches llms.txt from your domain root, or switch modes and paste the file content directly.
It parses the file against the llms.txt convention: an H1 title, a blockquote summary, and H2 sections containing link lists.
Each link is validated — URLs must be absolute http(s) or root-relative, and in URL mode a sample of links is spot-checked to confirm they actually respond.
Review the pass/warning/fail checks and fix anything flagged, then re-run to confirm.
Frequently asked questions
What is llms.txt?
llms.txt is a community convention (documented at llmstxt.org) for a Markdown file that gives AI systems a curated overview of your site—who you are, what matters, and which pages or docs to read next. It sits at your domain root (https://yoursite.com/llms.txt), similar to how robots.txt and sitemap.xml live at well-known paths. Unlike a full HTML crawl, it is meant to be concise and LLM-friendly so assistants and agents can load useful context without parsing navigation, ads, and scripts.
Why does llms.txt matter for AI search and LLM discovery?
As more people discover brands through ChatGPT, Claude, Perplexity, and similar tools, sites need a clear, machine-readable summary AI can use on demand—not only pages built for classic Google crawlers. llms.txt complements sitemaps by highlighting the handful of URLs and notes that actually fit an LLM context window. It is especially useful for documentation, APIs, and product sites where coding agents and assistants need a fast map of authoritative content. It is not a guaranteed ranking or citation boost, but it is a low-effort signal of AI readiness as the agentic web grows.
What structure should an llms.txt file follow?
Per the llmstxt.org convention, start with a single H1 for the project or site name (the only required section), then a blockquote summary with the key context an LLM needs. Optional paragraphs can follow, then H2 sections that hold Markdown link lists: each item is a [name](url) link, optionally followed by a colon and a short note. A special H2 named "Optional" marks secondary links that may be skipped when a shorter context is enough. Keep language concise and prefer absolute or clearly resolvable URLs to markdown-friendly pages when you have them.
Do ChatGPT, Claude, and Perplexity actually read llms.txt?
Adoption is uneven and still evolving. Major AI search surfaces do not publicly treat llms.txt as a proven ranking or citation factor the way Google treats sitemaps, and many crawler-log studies show limited fetching of /llms.txt by named bots. Where it shows up more clearly is in documentation and agent workflows—tools and assistants that fetch a URL on demand can load llms.txt (or linked .md pages) as context. Treat it as helpful infrastructure for AI discovery, not as a substitute for strong content, crawlability, and traditional SEO.
How is llms.txt different from robots.txt, and what mistakes should I avoid?
robots.txt tells crawlers what they may or may not fetch; llms.txt does not grant or deny access—it curates guidance and links for LLMs and agents when they need to understand your site. Publish llms.txt at the site root as plain text/Markdown, not buried in a subfolder or CMS-only path crawlers never see. Common mistakes include missing the H1, skipping the blockquote summary, using broken or relative links without a clear base, stuffing the entire sitemap instead of a curated set, and expecting the file alone to improve AI citations without clear, high-quality destination pages.
Get help fixing this
Fortitude builds fast, search-friendly websites. Leave your email and we'll help you fix what's holding your site back.
More free tools
SERP Snippet Preview
Preview how your title and meta description will look in Google search results.
Meta Description Checker
Check any page’s meta description for length, clarity, and click-worthiness.
H1 Checker
Find missing, duplicate, or weak H1 headings on any page.
Canonical Checker
Verify canonical tags are present, absolute, and pointing to the right URL.
Robots.txt Checker
Check your robots.txt for syntax issues and crawler access, including AI bots.
Robots.txt Generator
Generate a clean robots.txt with sitemap and AI-crawler rules in seconds.
Sitemap Checker
Discover and validate your XML sitemap, including sitemap index files.
llms.txt Generator
Generate a draft llms.txt from your site’s pages and description.
AI SEO Audit
A full AI-readiness SEO report: crawlability, metadata, structure, and fixes.
GEO Audit
Check how ready a page is for AI search and answer engines — not just Google.
Schema Markup Checker
Find and validate the JSON-LD structured data on any page.
AI Readability Checker
Check how easily AI assistants can parse, summarize, and quote your page.
FAQ Generator
Generate FAQ questions and answers from your page content, ready for FAQPage schema.
Citation Readiness Checker
Check how clearly your page states facts an AI assistant could reference.
Entity Clarity Checker
Check how clearly your page identifies who or what it is about.
AI Overview Readiness
Check how ready a page is to answer a specific query in an AI-generated answer block.
PageSpeed & Core Web Vitals Checker
Check Core Web Vitals — LCP, INP, and CLS — for any page via Google PageSpeed Insights.