# lab451.org > Lab451 — complete site content for LLM ingestion. This file contains the full text content of lab451.org, compiled into a single document. It is intended for use by large language models and AI-powered tools that need deep context about this website. ## Main Pages ### Home Source: https://lab451.org/ Retrieved: 2026-09-06 ⚡ Generate My Files Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode 4 files agents read. Generated, verified. llms.txt , llms-full.txt , sitemap.xml , and robots.txt Every package reference and hostname checked before you publish. Free for most sites. Takes about 30 seconds. Lab451 Generator — Ready Tip https:// Select: Select All llms.txt llms-full.txt sitemap.xml robots.txt Generate ⚡ Page limit: 50 · Sign up for more pages + history crawling: 0 pages found Saved Outputs Download All (zip) Reset All Would you like to generate a robots.txt file? Generate robots.txt Dead simple Three steps. Done in under a minute. 01 Paste your URL Drop in any public website URL. We handle the rest — no plugins, no code, no OAuth dance. 02 We crawl & structure Our crawler maps your site, pulls out the content a human actually sees, and builds all four files to spec — then checks every reference in them. 03 Upload & verify You get the four files, plus a report on anything inside them that doesn't resolve — a package name nobody registered, a dead link, text hidden from human readers. See the full walkthrough → What you get Four files. One job each. Two of them get read by pretty much every crawler on the web. The other two are what coding agents and retrieval pipelines reach to easily find, read, and understand key site content. We build all four, then check what's inside them. article llms.txt A short map of your site for agents. Coding assistants like Cursor and Claude Code fetch this on demand when you point them at your docs - File example: lab451/llms.txt → article_person llms-full.txt The full text of every page in one document. Built for RAG pipelines and agents that want the whole picture, not just a link list - File example: lab451/llms-full.txt → file_map_stack sitemap.xml Real lastmod dates read from your server, not today's date stamped on every URL. This one gets read by every search engine there is - File example: lab451/sitemap.xml → robot_2 robots.txt Built from what's actually on your site: platform detected, sitemaps confirmed live before we list them, retrieval bots kept separate from training bots - File example: lab451/robots.txt → Pricing Free for most. Powerful for the rest. If your site has under 50 pages, it's completely free. No credit card, no trial period, no gotchas. Otherwise: See full pricing details → ✓ copied! ©lab451.org· FAQ· Docs· Terms· Privacy. --- ### How It Works Source: https://lab451.org/how-it-works Retrieved: 2026-09-06 ⚡ Generate My Files Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Under the hood How Lab451 works From URL to four production-ready files in about 30 seconds. Here's exactly what happens in between. 01 You paste your URL Enter any publicly accessible website URL. Lab451 accepts root domains, subdomains, and specific path prefixes. No authentication, no API key, no installs required on your end. 02 Our crawler maps your site structure We send a polite crawl bot (identifiable by its user-agent Lab451Bot/1.0 ) to walk your site's link graph. It respects your existing robots.txt — even the one it's about to replace. add_link Link graph walking Follows internal links to discover all public pages folder_code Content extraction Strips nav/footer/boilerplate, extracts main content page_info Metadata parsing Reads title tags, meta descriptions, Open Graph data edit_calendar Date detection Finds publish dates for accurate sitemap lastmod values 03 We generate your four files With your site fully mapped, Lab451 compiles each file individually. Each is built to a specific spec: llms.txt llmstxt.org spec A concise, Markdown-formatted document describing your site: its purpose, main sections, key topics, and preferred AI interaction guidelines. Think of it as a README for AI models. llms-full.txt Extended spec A full-content companion that includes the actual text of every page (cleaned and structured). Used by RAG pipelines and AI systems that do deep document retrieval rather than just crawling. sitemap.xml Sitemaps.org protocol A standards-compliant XML sitemap with accurate lastmod dates, appropriate changefreq hints, and canonical URLs. Submitted-ready for Google Search Console. robots.txt RFC 9309 Configured to welcome major AI crawlers (GPTBot, ClaudeBot, Googlebot, etc.) while blocking known scrapers. Auto-references your new sitemap.xml location. 04 We check every reference before you publish This is the part most generators skip. Your docs are full of things that point somewhere — install commands, links, deploy URLs — and any of them can quietly stop resolving. A package gets renamed. A domain lapses. Someone's AI assistant invents a plausible-looking package name and it lands in a README. Once that's sitting in a file agents treat as authoritative, it stops being a typo and starts being a security problem. So before you get your files, we resolve what's in them: inventory_2 Package names Checked against npm, PyPI, crates.io, RubyGems, NuGet, Packagist and the Go proxy travel_explore Hostnames Resolved, with dangling CNAMEs to unclaimed deploy targets flagged visibility_off Hidden text Content invisible to human readers is stripped and reported, never published rule Severity report Findings graded critical to info, with the source page for each We report, we don't rewrite. Your docs are yours. If we find a package name nobody has registered, we tell you where it is and why it matters — we don't silently edit your content. 05 You download, upload, and you're done Download all four files in a single ZIP, then upload them to your web server's root directory. That's literally it. No ongoing maintenance required on the free plan. 06 How often should I re-generate my files? When significant content changes, such as new product features, updated API documentation, or updated FAQs. For active sites, a weekly or bi-weekly update cadence is recommended. Tip: The point of these files is to stop agents describing your product the way it worked eight months ago. That's the win you can actually measure, and it only holds if the files keep up with the site. Re-running also re-checks every reference, which matters more than it sounds — packages get deprecated and domains expire on their own schedule, so a file that verified clean in March isn't necessarily clean in September. The honest version Will anything actually r… --- ### Pricing Source: https://lab451.org/pricing Retrieved: 2026-09-06 ⚡ Generate My Files Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Pricing Simple pricing. No surprises. Free for the vast majority of sites. Scale when you need. Cancel anytime. Monthly Annual Save 20% Free $0/mo Perfect for personal sites, blogs, and small businesses Start Generating What's included: Up to 3 sites per day 4 files generated per site (llms.txt, llms-full.txt, sitemap.xml, robots.txt) llms.txt up to (50 pages deep) llms-full.txt up to (50 pages deep) sitemap.xml up to (50 pages deep) robots.txt (comprehensive) Copy or manual download History Crawl statistics Pro $12/mo For agencies, SaaS products, and content-heavy sites Get Pro What's included: Up to 200 sites per day 4 files generated per site (llms.txt, llms-full.txt, sitemap.xml, robots.txt) llms.txt up to (3000 pages deep) llms-full.txt up to (3000 pages deep) sitemap.xml up to (3000 pages deep) robots.txt (comprehensive) Copy or manual download Download as ZIP History Crawl statistics Pricing FAQ Quick Money Questions Is the free plan really free forever? Yes. We believe every website should have basic AI discoverability. The free plan has no time limit, no watermarks, and generates fully functional, production-ready files. What counts as a "site" for the daily limit? A site is one unique domain. Subdomains count as separate sites — blog.example.com and shop.example.com are two sites. Generating multiple file types for the same domain on the same day only counts as one site. Can I cancel Pro anytime? Yes absolutely, cancel anytime — no questions asked. Your Pro features stay active until the end of your current billing period, then you drop back to free. Your generated files remain yours forever. ©lab451.org· FAQ· Docs· Terms· Privacy. --- ### Docs Source: https://lab451.org/docs Retrieved: 2026-09-06 ⚡ Generate My Files Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Documentation Lab451 Docs File specs, integration guides, and everything in between. Getting Started Quick Start Uploading Files File Specs llms.txt llms-full.txt sitemap.xml robots.txt Security Why we validate What we check Hidden content Crawler safety Your data Reporting an issue Quick Start Getting started with Lab451 takes about 30 seconds. Here's the fastest path from zero to all four files: Single URL — all four file types in one click. Enter your URL, click Select All, then click Generate. Lab451 queues all four file types and runs them in sequence. You can download them individually or as a zip. Single URL — one file type at a time. Enter your URL, choose llms.txt , llms-full.txt , sitemap.xml , or robots.txt , then click Generate. Repeat for each additional file you want. Download or zip them together when you're done. Multiple URLs in one session. Enter your first URL, pick a file type, click Generate. Then enter the next URL and repeat. Note: When outputs span more than one site, Download All (zip) is disabled to prevent filename collisions — download each file individually instead. Upload the files to your domain's root: yourdomain.com/llms.txt , etc. That's it. No account needed for the free plan. Files are instantly ready for production. Uploading Files All four files should live at the root of your domain — the same directory as your homepage. Here's where each file goes: yourdomain.com/llms.txt yourdomain.com/llms-full.txt yourdomain.com/sitemap.xml yourdomain.com/robots.txt Most web hosts let you upload via FTP, SFTP, or a file manager in the control panel. If you're on a platform like Webflow or Squarespace, check their custom file hosting documentation. If you're using a static site generator (11ty, Next.js, Hugo, Gatsby, etc.), drop the files into your public/ or static/ directory. For WordPress, upload them via FTP or your hosting panel's file manager to the root public_html/ folder. llms.txt — File Spec Lab451 generates llms.txt following the llmstxt.org specification. The file is Markdown-formatted and structured as follows: # Site Name > One-sentence description of the site. Extended description explaining the site's purpose, target audience, and main content areas. ## Main Sections - [Section Title](URL): Brief description - [Section Title](URL): Brief description ## Key Topics - Topic 1 - Topic 2 - Topic 3 ## Guidelines for AI Instructions for how AI models should use this content. Lab451 generates this structure automatically by analyzing your site's content, navigation, and metadata. llms-full.txt — File Spec llms-full.txt extends the standard with the full cleaned text of every indexed page. It's used by RAG pipelines and AI systems that retrieve document content at query time. # Site Name — Full Content Index ## [Page Title](URL) > Meta description Full page content, cleaned and stripped of navigation, footers, and boilerplate. Markdown formatting preserved where possible. --- ## [Next Page](URL) [content continues...] Large sites should be aware that llms-full.txt can grow quite large. Lab451 applies smart deduplication and content filtering to keep file sizes reasonable. sitemap.xml — File Spec Generated according to the sitemaps.org protocol. Includes , , , and for every discovered page. robots.txt — File Spec Generated according to RFC 9309. Lab451 does not write a generic template — it inspects your site first and tailors the file. Platform detection. Lab451 fingerprints your homepage and adds rules for WordPress, WooCommerce, Shopify, Drupal, Joomla, Magento, BigCommerce, Ghost, Squarespace, Wix, Webflow, Next.js, or Nuxt. Verified sitemaps. Candidate sitemap URLs are fetched and confirmed to return XML before being listed, so you never advertise a broken sitemap. Si… --- ### Terms Source: https://lab451.org/terms Retrieved: 2026-09-06 Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Legal Terms of Service Effective date: 5 May 2026 · Lab451 · hello@lab451.org Welcome to Lab451 ("we," "us," or "our"), accessible at lab451.org. These Terms of Service govern your access to and use of our website, tools, and services — including our free and paid llms.txt / llms-full.txt generator. By using Lab451 you agree to these Terms. If you do not agree, please do not use the service. 1. The Service Lab451 provides a web-based tool that analyses a URL or supplied content and produces machine-readable llms.txt and llms-full.txt files in accordance with the open llmstxt.org specification. The service is available in two tiers: Free tier — limited generation quota per day, no account required. Paid tier — higher quotas, priority processing, and additional features, billed via Stripe. We may modify, suspend, or discontinue any aspect of the service at any time with reasonable notice where practicable. 2. Eligibility You must be at least 13 years of age (or the minimum digital-consent age in your jurisdiction, whichever is higher) to use Lab451. By using the service you represent that you meet this requirement. 3. Accounts and Access Some features may require you to create an account or authenticate. You are responsible for keeping your credentials secure and for all activity that occurs under your account. Notify us immediately at hello@lab451.org if you suspect unauthorised access. 4. Paid Plans and Billing Paid subscriptions and one-time purchases are processed by Stripe, Inc., a third-party payment processor. By subscribing you agree to Stripe's terms of service. The following apply to paid plans: Pricing. Current pricing is displayed at checkout. We reserve the right to change prices with at least 14 days' notice to existing subscribers. Billing cycle. Subscriptions renew automatically at the end of each billing period unless cancelled before renewal. Cancellation. You may cancel at any time from your account settings. Access continues until the end of the current paid period. Refunds. Our policy on digital memberships and downloads emphasize that sales are final, non-refundable, and non-transferable due to the immediate, non-tangible nature of the products except where required by applicable law. This policy applies to the selected paid period only. See above 'Cancellation' policy for termination of membership. If you have concerns contact us at: hello@lab451.org. 5. Acceptable Use You agree not to use Lab451 to: Generate files for websites or content you do not own or have explicit authorisation to represent. Scrape, stress-test, or probe our infrastructure in any way that disrupts normal operation. Circumvent rate limits, quotas, or other access controls. Reproduce, resell, or redistribute the service or its outputs as a competing product without written consent. Violate any applicable law or regulation. We reserve the right to suspend or terminate access for violations of these rules without prior notice. 6. Intellectual Property The Lab451 platform, its code, design, and branding are owned by us and protected by applicable intellectual property law. The llms.txt and llms-full.txt output files generated from your content belong to you. We claim no ownership over content you supply or the files we generate from it. 7. Third-Party Services and Links Our service may integrate with or link to third-party services (including Stripe for payments and AI providers for processing). We are not responsible for the content, privacy practices, or terms of those services. Your use of any third-party service is governed by their own terms. 8. Disclaimer of Warranties The service is provided "as is" and "as available" without warranties of any kind, express or implied, including but not limited to merchantability, fitness for a particular purpose, or non-infringement. We do not warrant that the service will … --- ### Privacy Source: https://lab451.org/privacy Retrieved: 2026-09-06 Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Legal Privacy Policy Effective date: 5 May 2026 · Lab451 · hello@lab451.org This Privacy Policy explains how Lab451 ("we," "us," or "our") collects, uses, and protects information when you visit lab451.org or use our llms.txt / llms-full.txt generator. We aim to be direct and human about this — no legalese walls. 1. Who We Are Lab451 is an independent project operated from British Columbia, Canada. You can reach us at hello@lab451.org. 2. Information We Collect We collect the minimum needed to operate the service: Category What it includes Why we collect it Usage data IP address (anonymised), browser type, pages visited, timestamps Service analytics, security, abuse prevention Input content URLs or text you submit for llms.txt generation Generating your requested output files Account data Email address and password hash (if you create an account) Authentication, service communications Payment data Billing details processed by Stripe (we never see raw card numbers) Processing paid subscriptions and one-time purchases Cookies / local storage Session tokens, preference flags Keeping you logged in, remembering UI settings We do not sell your data. We do not build advertising profiles. We do not share your content with third parties except as described in Section 4. 3. How We Use Your Information We use the data we collect to: Provide, maintain, and improve the llms.txt generation service. Process payments and manage your subscription via Stripe. Enforce our Terms of Service and prevent misuse. Send transactional emails (receipts, password resets, service notices). We will only send marketing emails if you opt in. Analyse aggregate, anonymised usage patterns to improve the product. 4. Data Sharing and Third Parties We share data with third parties only in the following limited circumstances: Stripe — processes payment information. Your card details go directly to Stripe and are never stored on our servers. See Stripe's Privacy Policy. AI / inference providers — if your submitted content is processed by an underlying language model API to assist in generating llms.txt output, it is transmitted to that provider under a data-processing agreement. We select providers who do not use submitted content to train their models. Infrastructure providers — hosting, CDN, and logging services necessary to run the platform. These act as data processors under our instructions. Legal compliance — if required by law, court order, or to protect the rights and safety of Lab451 or others. 5. Cookies We use strictly necessary cookies (session management) and, with your consent, optional analytics cookies to understand how the service is used. You can adjust cookie preferences via the banner shown on first visit, or in your browser settings. Disabling analytics cookies does not affect core functionality. 6. Data Retention We retain your data only as long as necessary: Generated output files — cached temporarily (up to 24 hours) to allow re-download, then deleted. Account data — retained while your account is active, and for up to 90 days after deletion to enable recovery. Billing records — retained for 7 years as required by Canadian tax law. Server logs — anonymised and purged after 30 days. 7. Security We use industry-standard measures — HTTPS/TLS in transit, hashed passwords, least-privilege access controls — to protect your data. No system is perfectly secure; if you suspect a breach, please contact us immediately at hello@lab451.org. 8. Your Rights Depending on your location, you may have rights including: Access — request a copy of the personal data we hold about you. Correction — ask us to fix inaccurate data. Deletion — ask us to erase your personal data (subject to legal retention obligations). Portability — receive your data in a structured, machine-readable format. Objection / restriction — object … --- ## Blog ### Articles Source: https://lab451.org/blog/articles Retrieved: 2026-09-06 Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Lab451 Blog Guides on GEO & getting cited by AI Practical, opinionated writing on llms.txt , llms-full.txt , sitemap.xml , robots.txt , and the wider craft of making your site legible to ChatGPT, Claude, Perplexity, and Gemini. The complete llms.txt guide for 2026 What llms.txt is, why it exists, who actually reads it, and how to write one correctly — including the mistakes that quietly tank the whole exercise. Read guide → llms.txt vs llms-full.txt One is a map, one is the territory. Here's when to use each, how they work together, and which AI models read which file. Read comparison → How to add llms.txt to WordPress Four working methods, ranked from least-technical to most. SFTP, plugin, functions.php, or native WordPress.com — pick what matches your hosting. Read tutorial → How to add llms.txt to Shopify Shopify now serves the file natively (and redirects to /agents.md ). Here's how to override the default with your own content. Read tutorial → ©lab451.org· FAQ· Docs· Terms· Privacy. --- ### Llms Txt Complete Guide 2026 Source: https://lab451.org/blog/llms-txt-complete-guide-2026 Retrieved: 2026-09-06 Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Guide · GEO · llms.txt The complete llms.txt guide for 2026 Everything you need to know about llms.txt — what it is, where it came from, what AI models actually do with it, how to write one correctly, and the mistakes that quietly tank the whole exercise. May 20, 2026 · 22 min read · Lab451 On this page What is llms.txt? Why it exists (the actual problem) Who actually reads llms.txt The spec, line by line llms.txt vs llms-full.txt How it relates to robots.txt and sitemap.xml Writing a good llms.txt Real examples worth copying Common mistakes Hosting, caching, and deployment Measuring whether it works Where this is heading in 2026 and beyond Frequently asked questions What is llms.txt? llms.txt is a plain-text file you put at the root of your domain — at https://yoursite.com/llms.txt — that tells large language models what your site is about, which pages matter, and how to navigate it. It's written in Markdown. It's small. It exists for one reason: AI models have very limited context windows, and they can't read your whole site, so you give them a curated map instead. The standard was proposed by Jeremy Howard of Answer.AI in September 2024, and over the following eighteen months it became the de facto convention for what's now called Generative Engine Optimization, or GEO — the practice of getting your site cited by ChatGPT, Claude, Perplexity, Gemini, and the other large language models that have started to replace the traditional search box. If you've ever written a robots.txt or a sitemap.xml , you already understand the shape of llms.txt . It's the same idea — a small file at a well-known URL that gives automated systems structured hints about your site — except the audience is language models rather than search-engine crawlers, and the format is Markdown rather than text directives or XML. Why it exists (the actual problem) When you ask ChatGPT "what is FastHTML and how do I get started," ChatGPT might do three things behind the scenes: search the web, pick a handful of pages, and try to read enough of them to give you a sensible answer. The second and third steps are where modern sites fall over. A typical modern web page is 200KB to several megabytes of HTML, CSS, JavaScript, third-party scripts, cookie banners, navigation chrome, and ads. An LLM's context window — even a generous one — is small relative to that. The model has to either render the page through some kind of browser-like pipeline (slow, expensive, fragile) or strip the markup down to text (loses structure, mangles tables, drops semantics). Either way, by the time the actual content reaches the model, it's degraded. Worse, the model has no idea which pages on your site are important. Is your homepage the canonical statement of what you do? Is the About page the one to read for context? Is your documentation under /docs , /help , /wiki , or somewhere else? Without explicit guidance, the model guesses. It often guesses wrong. llms.txt solves both problems at once. It's a small, pre-cleaned, Markdown-formatted document that says: "This is what this site is. Here are the pages that matter. Here's where to go for deeper information." The model spends a fraction of its context budget and walks away with an accurate picture of your site. Who actually reads llms.txt This is the question every skeptical post about llms.txt opens with, and it deserves an honest answer. As of mid-2026, support is uneven but growing. Here's the realistic state of play: Crawler User-agent Status ChatGPT / OpenAI GPTBot , OAI-SearchBot Fetches llms.txt Claude / Anthropic ClaudeBot , Claude-Web Fetches llms.txt Perplexity PerplexityBot Fetches llms.txt Google (Gemini, AI Overviews) Googlebot , Google-Extended Indexes the file; weight unclear Microsoft Copilot / Bing Bingbot Indexes the file; weight un… --- ### Llms Txt Vs Llms Full Txt Source: https://lab451.org/blog/llms-txt-vs-llms-full-txt Retrieved: 2026-09-06 Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Guide · GEO · llms-full.txt llms.txt vs llms-full.txt: what's the difference? They sound nearly identical. They live next to each other at the root of your site. They serve the same broad audience. But they do fundamentally different jobs — and knowing which one to ship (or whether to ship both) is the difference between AI models understanding your site and AI models actually answering questions about it. May 27, 2026 · 18 min read · Lab451 On this page The TL;DR Two files, two jobs Side by side Format differences in detail Size, budget, and context windows Which AI models read which file When to ship just llms.txt When to ship both How they work together at inference time Generating llms-full.txt without going insane Common mistakes Frequently asked questions The TL;DR If you only read one paragraph: llms.txt is a small Markdown file that tells AI models what your site is and where the important pages live. llms-full.txt is a much larger Markdown file that contains the actual text of those pages already extracted, cleaned, and concatenated. The first is a table of contents; the second is the book. Marketing sites and small blogs usually only need llms.txt . Documentation sites, API references, knowledge bases, and anything technical where you actually want models to be able to answer questions about your content should ship both. Two files, two jobs The reason there are two files instead of one comes down to a tradeoff every LLM has to make: context window space is expensive, but fetching pages is slow. Different situations call for different sides of that tradeoff. When a user asks ChatGPT "what does Lab451 do," the model needs the smallest possible amount of context to answer accurately. It doesn't need your full pricing page, your terms of service, or every blog post — it needs a sentence or two. llms.txt is exactly that: a tiny file the model can fetch in milliseconds, parse in a few tokens, and use to give a quick, accurate one-paragraph answer. When a user asks ChatGPT "what's the best way to set up llms-full.txt for a 500-page documentation site," the model needs much more. It needs to understand your full documentation, find the relevant sections, and synthesize specifics. Following links one by one from llms.txt would mean ten or twenty separate fetches and a lot of wasted context. llms-full.txt sidesteps that entire dance: download once, answer in detail. The two files don't compete — they complement each other. The model can grab whichever is the right tool for the question being asked. Some models check both in sequence; some pick one based on the query depth. Either way, having both available means you've covered both ends of the tradeoff. Side by side llms.txt llms-full.txt Purpose Map of your site Full text of your site Format Structured Markdown (H1 + blockquote + H2 link lists) Free-form Markdown (concatenated page bodies) Typical size 1–10 KB 100 KB – several MB Token cost when read ~250 – 2,500 tokens ~25,000 – 1,000,000+ tokens Update frequency When site structure changes Every meaningful content change Best for Any site (marketing, blog, SaaS landing) Docs, API references, knowledge bases, technical content Model behavior Read once, follow links as needed Read once, answer from memory Hosted at /llms.txt /llms-full.txt Required? Recommended for everyone Recommended for content-heavy sites Format differences in detail Both files are Markdown, both are plain text, both live at the root of your domain. The differences are structural. llms.txt: prescriptive structure llms.txt follows a tight, parseable shape. There's exactly one H1, an optional blockquote summary, optional free-form Markdown, and then H2 sections each containing nothing but link lists. A spec-compliant parser can extract these elements determinis… --- ### How To Add Llms Txt To Wordpress Source: https://lab451.org/blog/how-to-add-llms-txt-to-wordpress Retrieved: 2026-09-06 Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Tutorial · WordPress · GEO How to add llms.txt to WordPress Four working methods as of mid-2026, ranked from least-technical to most-technical. Pick the one that matches your hosting and your tolerance for poking around the file system. The whole process takes about ten minutes once you've picked your path. June 3, 2026 · 11 min read · Lab451 On this page Before you start: generate the file Which method to pick Method 1 — WordPress.com (Business plan and up) Method 2 — Plugin (easiest for self-hosted) Method 3 — SFTP / file manager upload Method 4 — functions.php rewrite (most flexible) Verify it's actually working Troubleshooting the common failures Maintenance: keeping it fresh Frequently asked questions Before you start: generate the file All four methods below assume you already have an llms.txt file ready to upload or paste in. If you don't, you have two options: Generate it automatically. Lab451 produces a spec-compliant llms.txt in about 30 seconds — paste your domain, click Generate, download the file. Free for sites under 50 pages. Write it by hand. If your site is small or you want full editorial control, copy the spec from the complete guide and write 30–60 lines of Markdown yourself. Either way, you should end up with a plain-text file named llms.txt (lowercase, no .md extension, no BOM) that starts with an # heading and contains your site name, a one-paragraph summary, and a few H2 sections of Markdown links. Hold onto it — you'll need it in a minute. Which method to pick WordPress is a sprawling ecosystem and the right answer depends on which flavor you're running. Quick decision tree: WordPress.com Business plan or higher? → Method 1. Built in. Self-hosted (WordPress.org) and you'd rather not touch files? → Method 2. Plugin. Self-hosted and you have SFTP access? → Method 3. Direct upload. Self-hosted and you want the file generated dynamically? → Method 4. functions.php. WordPress.com Free, Personal, or Premium plan? → none of these work. You'd need to upgrade to Business, or move to self-hosted WordPress. Method 1 — WordPress.com (Business plan and up) WordPress.com shipped native llms.txt support in January 2026. If you're on Business, Commerce, or Enterprise, it's the easiest path — no plugin, no file uploads, no code. Log into your WordPress.com dashboard. Navigate to Tools → Marketing → llms.txt. (The path moved twice in early 2026; if you don't see it there, search the help docs for "llms.txt" — it's somewhere in the sidebar.) Either let the platform auto-generate your file from your site structure, or paste in custom content (e.g. the file you got from Lab451). Save. The file is now live at yourdomain.com/llms.txt . Note: this feature is limited to Business and above. Free, Personal, and Premium plans can't add static root files and can't install plugins, which means there's no path to llms.txt on those tiers without upgrading or migrating. Method 2 — Plugin (easiest for self-hosted) For self-hosted WordPress.org sites, a dedicated plugin is the lowest-friction option. Three are worth knowing about: Website LLMs.txt — purpose-built plugin, free in the WordPress repository. Generates from your post/page structure, lets you override content, serves the file at the correct path. Rank Math (experimental) — the popular SEO plugin added experimental llms.txt support in early 2026. If you already use Rank Math, look under Rank Math → General Settings → llms.txt. Yoast SEO — has signalled it's coming but isn't shipped as of this writing. Worth checking the changelog if you already use Yoast. For the general workflow with Website LLMs.txt: From your WP admin, go to Plugins → Add New and search for "llms.txt". Install and activate the plugin. Visit the plugin's settings page (usually under Settings or its own top-level menu item). Eith… --- ### How To Add Llms Txt To Shopify Source: https://lab451.org/blog/how-to-add-llms-txt-to-shopify Retrieved: 2026-09-06 Lab451 dark_mode home How it works Pricing Docs Blog Login dark_mode Tutorial · Shopify · GEO How to add llms.txt to Shopify The Shopify situation changed twice in spring 2026 and most guides on the internet are out of date. Here's what's actually true as of mid-2026: Shopify now serves llms.txt natively for every store, with auto-generated default content. You can override it, you can replace it with a plugin, or you can leave it alone — but you can't ignore it. Here's how to handle each path. June 10, 2026 · 13 min read · Lab451 On this page What's different about Shopify What's already there: check first Should you override the default? Method 1 — Leave Shopify's default in place Method 2 — Override with a Liquid template Method 3 — Use a dedicated app (Yoast, AdNabu, 10x GEO) A note on the /agents.md redirect Verify it's working Shopify-specific gotchas The bigger picture: Agentic Storefronts Frequently asked questions What's different about Shopify On most platforms, adding llms.txt means writing or generating a file and uploading it. On Shopify, that approach does not work — Shopify's platform architecture doesn't let merchants put arbitrary files in the root directory. For years, this meant llms.txt required workarounds: Cloudflare Workers, URL redirects, third-party apps. Most of those workarounds are now obsolete. Two things changed in spring 2026: February 2026: Shopify started serving /llms.txt natively for every store, auto-generated from the platform's data (best-selling products, collections, store policies, recent blog posts). The file is live by default — you don't have to enable it. May 2026: Shopify began redirecting /llms.txt to /agents.md . The content is the same; the canonical URL changed. Crawlers that request the old URL get a 301 to the new one. The practical upshot: every Shopify store already has an llms.txt , whether the merchant set it up or not. Your job isn't to add one — it's to decide whether the auto-generated default is good enough, and if not, how to replace it. What's already there: check first Before doing anything else, open yourstore.com/llms.txt in a browser. You'll either be redirected to /agents.md (newer stores) or land directly on the file. What you see is Shopify's default for your store. Shopify's default content typically includes: Links to your homepage and the /collections/all page Links to your /search page Your store's contact information References to "Agents & Developers" pages — these point at Shopify's own developer docs, not yours Links to the Shop app and Shopify-platform-level pages Two things to notice. First: it's quite bare-bones — far less than the rich, curated map the spec encourages. Second: it leads with Shopify itself, not your store. The "Agents & Developers" section often appears before your products, which means an AI agent reading the file meets Shopify's pitch before yours. Should you override the default? Honest answer: it depends, and as of mid-2026 the answer is leaning toward "yes, but cautiously." The case for leaving Shopify's default alone: It's maintained by Shopify automatically — best-selling products update, deleted products disappear. Shopify has direct relationships with major AI platforms, so its format is informed by what works. The feature is still in active iteration; overriding may break when Shopify changes the implementation again. The case for overriding: The default is generic and Shopify-centric — it doesn't tell your story. If you have cornerstone content (buying guides, comparison articles, brand-story pages), the default ignores them. The blockquote summary at the top — the single most important sentence for AI citation — is usually generic in the default. Our recommendation: override if you have content beyond products — blog posts, buying guides, brand stories, FAQs. Leave the default if you're a pure-product st… --- # Prepared by: lab451.org