1. Supply Your Crawl Input
Choose your preferred scan method. Point to your sitemap XML (best for full site coverage), enter your homepage domain to let the crawler follow internal links, or paste a custom list of prioritized URLs.
llms.txt Generator
Scan your sitemap or website to automatically build, edit, and download an official, categorized llms.txt knowledge map with real page summaries.
Input Route
Live Output
Choose an input route to begin.
Modern AI systems like ChatGPT, Claude, and Perplexity crawl the web looking for authoritative answers. When you publish a file created with our llms.txt file generator, you provide language models with an explicit roadmap of your products, tutorials, APIs, and business terms.
Core Standard
An llms.txt file is a structured Markdown document placed at the root of a domain to help language models quickly discover and comprehend website content.
Standard webpages are designed for graphical web browsers. When an automated AI bot visits a website, it must parse megabytes of HTML, CSS, JavaScript frameworks, tracking scripts, and cookie banners.
Because language models operate within strict token limits, processing raw website code wastes valuable context on navigation bars, advertisements, and footer menus.
XML sitemaps help bots locate page URLs, but sitemaps provide zero textual context or descriptions. An AI system reading an XML sitemap cannot determine whether /pricing or /terms contains the specific data an end user requested.
The community proposal documented at llmstxt.org (championed by Jeremy Howard and Answer.ai) standardizes a clean Markdown index hosted at https://yourdomain.com/llms.txt.
The specification requires a single top-level H1 header containing the project or website name, an optional blockquote summary, and categorized H2 sections with Markdown links. Each link includes a concise description following a colon.
Building this file by hand for dozens of pages is tedious and prone to formatting mistakes. Our free llms.txt generator automates the entire discovery, extraction, summarization, and formatting process.
Workflow Breakdown
Our online engine delivers a streamlined workflow: real page content in, clean structured Markdown out.
Choose your preferred scan method. Point to your sitemap XML (best for full site coverage), enter your homepage domain to let the crawler follow internal links, or paste a custom list of prioritized URLs.
Our Cloudflare Workers edge engine fetches your pages, strips layout chrome, and organizes content into logical groups like Docs, Products, Pricing, and Company. AI summarization produces factual one-sentence descriptions.
Inspect the live Markdown preview. Edit summaries, remove unnecessary links, adjust headers, and click Download. You receive a clean, ready-to-publish plain text file named llms.txt.
Specification Comparison
Understanding how llms.txt fits alongside traditional web standards helps you optimize for both human search engines and autonomous AI agents.
| Feature | llms.txt | robots.txt | sitemap.xml |
|---|---|---|---|
| Primary Purpose | Curated index of key pages with descriptions for AI models | Access permissions and crawl directives for all bots | Full inventory of indexable URLs for traditional search engines |
| Target Audience | LLMs, AI agents, RAG systems (ChatGPT, Claude, Perplexity) | Search engine spiders, general web crawlers | Googlebot, Bingbot, search indexing crawlers |
| Standard File Format | Standard Markdown (.md / plain text) | Plain text key-value directives | Structured XML schema with <urlset> |
| Domain Location | /llms.txt | /robots.txt | /sitemap.xml |
| Page Descriptions | Yes (factual 1-sentence summaries) | No (directives only) | No (lastmod and priority only) |
| Optional Sections | Supports "## Optional" section for secondary resources | Crawl-delay, specific User-agent blocks | Image sitemaps, news extensions |
Step-by-Step Deployment
Once your file is generated and reviewed, place it at the root of your web domain. Here are platform-specific instructions for the most popular web hosting environments:
Option A (FTP / File Manager): Connect to your web hosting control panel (cPanel, Plesk, or SFTP). Navigate to your root directory (/public_html/) and upload llms.txt directly alongside wp-config.php.
Option B (Nginx / Apache Rewrite): If using a managed host like WP Engine, upload the file to your uploads directory and add a rewrite rule in your .htaccess file:
Shopify manages the root directory directly, but you can serve an llms.txt file using URL redirects or Theme liquid assets:
1. In your Shopify Admin, go to Settings → Files and upload your downloaded llms.txt file.
2. Copy the resulting CDN file URL.
3. Go to Online Store → Navigation → View URL Redirects.
4. Create a redirect from /llms.txt to your uploaded file CDN address.
For modern JavaScript frameworks like Next.js (App Router or Pages Router), Nuxt, Vite, or SvelteKit, static files belong in the public directory:
1. Copy your generated file to /public/llms.txt in your repository.
2. Next.js automatically serves everything inside public/ at the root URL during production builds.
3. Run npm run build and deploy to Vercel, Netlify, or AWS.
Static site generators like Astro, Hugo, Eleventy, or Jekyll serve files from their designated asset folder:
1. Place your file into the public/llms.txt directory of your project.
2. Ensure your build output maps static files directly to root.
3. Verify deployment by opening https://yourdomain.com/llms.txt in any web browser.
Verification Command
Run this terminal command to confirm your live file returns a 200 OK status code and readable Markdown:
Standard Syntax
Below is a real-world example of an optimized llms.txt file showing proper H1 naming, blockquote summaries, categorized H2 headings, and markdown links with descriptions.
# Acme Analytics
> Acme Analytics provides privacy-first website analytics and conversion tracking without cookie banners or personal data collection.
Use the resources below to understand our API endpoints, tracking methods, pricing tiers, and integration guides for modern web frameworks.
## Core Products
- [Event Tracking API](https://example.com/docs/api): REST and GraphQL endpoints for streaming custom user events in real time.
- [Cookieless Tracking Script](https://example.com/docs/script): Lightweight 1.2KB script that collects traffic metrics without storing cookies.
- [Pricing and Usage Limits](https://example.com/pricing): Tier comparisons, event quotas, and enterprise volume discounts.
## Integration Guides
- [Next.js Integration](https://example.com/guides/nextjs): Step-by-step tutorial on adding analytics to App Router layouts.
- [Shopify Integration](https://example.com/guides/shopify): Instructions for deploying script tags inside Shopify theme.liquid.
- [WordPress Plugin](https://example.com/guides/wordpress): Official plugin setup and multi-site configuration.
## Optional Resources
- [Privacy Policy and GDPR Compliance](https://example.com/privacy): Detailed legal disclosures and data protection certifications.
- [System Status Dashboard](https://example.com/status): Live API uptime and regional latency reports.
Frequently Asked
Everything you need to know about creating, validating, and publishing knowledge files for AI models.
An llms.txt file is a standardized Markdown document placed at the root of your domain (https://yourdomain.com/llms.txt). It provides large language models and AI search agents with a concise, human-readable index of your highest-value webpages, complete with page descriptions and categorized links.
Our tool accepts a sitemap XML URL, homepage address, or manual URL list. Our edge engine crawls the pages, extracts clean text, uses AI to create factual one-sentence summaries, and outputs a valid Markdown file that you can edit and download directly in your browser.
Upload the downloaded file directly to the root public directory of your web host or framework so it is accessible at https://yourdomain.com/llms.txt. Common server paths include /public_html/, /public/, or /www/.
No. The three files serve complementary roles. robots.txt instructs web crawlers which URLs they may or may not access. sitemap.xml provides search engines like Google and Bing with an inventory of all indexable URLs. llms.txt provides language models like ChatGPT, Claude, and Perplexity with a curated, high-context map of core documentation, products, and articles.
Yes. Simply enter your store sitemap (such as yourstore.com/sitemap.xml for Shopify or yoursite.com/sitemap_index.xml for WordPress). Our crawler parses products, collections, pages, and blog posts to produce a clean knowledge map.
llms.txt is a lightweight index of URLs and brief summaries designed for discovery. In contrast, llms-full.txt bundles the complete readable text of selected key pages into a single knowledge file for direct ingestion into AI context windows.
Switch Tools Anytime