---
title: "llms txt Generator — Free, Spec-Compliant"
description: "Free llms.txt generator. Create a spec-compliant llms.txt for ChatGPT, Claude, and Perplexity — copy or download instantly. No signup."
canonical: "https://lemwatch.com/tools/llms-txt-generator"
source: "https://lemwatch.com"
---

# llms txt generator

> Generate a spec-compliant llms.txt file in 30 seconds. Help ChatGPT, Claude, Perplexity, and other AI systems understand your site so they cite it correctly.

llms.txt is the emerging standard for telling Large Language Models what your site is and where to find the content worth citing. Proposed by Jeremy Howard in September 2024 and adopted within weeks by Anthropic, Cloudflare, and a growing list of doc platforms, it's already in use by hundreds of major sites. This generator produces a spec-compliant file in under a minute.

 ## Why llms.txt exists

 Large language models have a context window problem. Even the biggest models can only hold a fraction of your site in working memory at any one time. When ChatGPT or Claude is asked a question about your product, they have to decide which of your pages to fetch — and they have seconds to decide. Without a guide, they fall back to whatever Google indexed, which is often blog posts and marketing pages rather than the canonical documentation that would actually answer the question. llms.txt is the guide.

 ## How llms.txt differs from robots.txt and sitemap.xml

 - **robots.txt** is permission — what crawlers may and may not access
- **sitemap.xml** is inventory — every URL you want indexed, in machine-readable form
- **llms.txt** is editorial — what an LLM should prioritise to actually understand your site

 All three coexist. llms.txt is intentionally short (typically under 5KB) because it's meant to fit in a model's context window alongside the user's question.

 ## The spec at a glance

 An llms.txt file is Markdown with a strict structure:

 1. **H1** with the project or site name (required)
2. **Blockquote** with the canonical URL (recommended)
3. **Free-form paragraph** describing what the site is for (recommended)
4. **`## Docs` H2** with a Markdown bullet list of `[Title](URL)` links to core docs (recommended)
5. **`## Optional` H2** with secondary resources (blog, changelog, examples) (optional)

 No other top-level headings. The file is parsed by LLM toolchains that expect this exact shape — extra sections may be ignored.

 ## What to put in the Docs section

 Think "if a model could only read 5 pages of my site to answer questions about it, which 5?" That's the Docs list. For most sites this is: getting-started, core concepts, the API reference (or feature reference), pricing, and a FAQ. Resist the urge to dump your entire sitemap — that defeats the purpose.

 ## Optional links: what to add and what to leave out

 Use the Optional section for context-broadening resources: the changelog (helps LLMs answer "what's new" questions accurately), the blog index (gives editorial voice), a public roadmap, public case studies. Leave out anything gated, anything outdated, and anything that contradicts your Docs section — LLMs penalise contradictions by citing less.

 ## Where to publish it

 Upload the generated file to `https://yourdomain.com/llms.txt` — the root of your site, same convention as robots.txt. Some platforms also publish `llms-full.txt` (a single concatenated document version of all the linked docs) for models that want the full corpus in one fetch. The generator above produces the index file; the full version is a content task you do later.

 ## Adoption today

 As of mid-2026, llms.txt files are live on the documentation sites of Anthropic, Cloudflare, Stripe (developer docs), Mintlify, Fly.io, and dozens of others. Major LLM vendors have confirmed they read it: Anthropic's web crawler uses it, Perplexity factors it into source ranking, and OpenAI has indicated their crawler respects it. Publishing one today is low-effort, no-downside, and demonstrably improves how AI systems cite your site.

 ## Common mistakes

 - **Skipping the canonical URL blockquote** — LLMs use it to disambiguate when your site has many subdomains
- **Too many links in Docs** — keep it under 10, ideally 5–8
- **Pasting full content into Optional** — link to it, don't inline it; the file is meant to be small
- **Forgetting to update after a re-architecture** — broken links here erode trust like 404s in your sitemap

## What this tool checks

- A clean H1 with your site/brand name
- A canonical URL block-quoted under the title
- A short summary paragraph describing what your site is for
- A `## Docs` section listing core documentation pages
- An optional `## Optional` section for changelog, blog, examples
- Spec-compliant Markdown formatting (no surprises)

## Why it matters

 AI search engines (ChatGPT, Claude, Perplexity, Google AI Overviews, Bing Chat) increasingly drive discovery — and they need a clean, machine-readable map of your site to cite it accurately. llms.txt is becoming the robots.txt of the AI era: a single file at your root that tells LLMs what your site is, where the canonical docs live, and which URLs to prioritise.

## How to fix what it finds

- Fill in your site name, canonical URL, and a one-paragraph summary
- List your top 5–10 documentation or core content pages
- Add optional resources (changelog, blog, API reference) for richer context
- Download the generated file and upload to `https://yourdomain.com/llms.txt`
- Link to it from your robots.txt with a comment for discoverability

## Methodology

 This is a pure client-side generator. No edge function is called, no data leaves your browser, and the file is built deterministically from the form inputs using the llms.txt spec from llmstxt.org. We render an H1 for the site name, a blockquote for the canonical URL, the summary as a free-form paragraph, and Markdown bullet lists under `## Docs` and `## Optional` sections — each entry parsed from your `Title | URL` lines (we also accept `Title: URL`). The preview updates live as you type. The download produces a UTF-8 text/markdown file named `llms.txt` that you upload to the root of your site. No telemetry is captured; this tool works fully offline once the page is loaded.

## This tool also answers

### What is an llms.txt file?

 A plain Markdown file at /llms.txt that gives large language models a curated map of your site: what the product is, and which pages hold the canonical answers. It is to AI assistants roughly what a sitemap is to a crawler.

### Where do I put the llms.txt file?

 At the root of your domain, served as text/plain or text/markdown at https://yourdomain.com/llms.txt. On most stacks that means dropping it in the public or static folder so it ships untouched with the build.

## Frequently asked questions

### What is llms.txt?

 A Markdown file at the root of your site that tells Large Language Models (ChatGPT, Claude, Perplexity, etc.) what your site is and which pages contain the canonical content. Proposed by Jeremy Howard in September 2024.

### Do major LLMs actually read it?

 Yes. Anthropic, Perplexity, and OpenAI have confirmed their crawlers respect llms.txt. Cloudflare also factors it into how AI Crawlers see hosted sites. Adoption is still early but growing fast.

### How is it different from robots.txt?

 robots.txt controls access — what crawlers may fetch. llms.txt controls priority — which pages a model should read first to understand your site. Both should exist; they serve different purposes.

### Where do I put the file?

 Upload it to the root of your site at `https://yourdomain.com/llms.txt`. Same convention as robots.txt and sitemap.xml — must be at the root, not in a subdirectory.

### Should I also publish llms-full.txt?

 Optional. llms-full.txt is a concatenated single-document version of all your core docs, for models that want everything in one fetch. Most sites start with just llms.txt and add the full version later.

### Will this hurt my regular SEO?

 No. llms.txt is invisible to traditional search engines (they ignore it). It only affects AI systems that explicitly look for it. There is no downside to publishing one.

### How often should I update it?

 Whenever your top docs structure changes — typically a few times a year. Stale llms.txt files with broken links signal a poorly maintained site to LLMs and reduce citation frequency.

### What is an llms.txt file?

 A plain Markdown file at /llms.txt that gives large language models a curated map of your site: what the product is, and which pages hold the canonical answers. It is to AI assistants roughly what a sitemap is to a crawler.

### Where do I put the llms.txt file?

 At the root of your domain, served as text/plain or text/markdown at https://yourdomain.com/llms.txt. On most stacks that means dropping it in the public or static folder so it ships untouched with the build.


## Related

- [All free tools](https://lemwatch.com/tools)
- [Free SEO Audit](https://lemwatch.com/tools/free-seo-audit)
- [Meta Tags](https://lemwatch.com/tools/meta-tag-analyzer)
- [Sitemap Checker](https://lemwatch.com/tools/sitemap-checker)
- [Bulk SSL Certificate Checker](https://lemwatch.com/tools/bulk-ssl-checker)
- [Bulk Security Header Checker](https://lemwatch.com/tools/bulk-security-headers)
- [Lemwatch pricing](https://lemwatch.com/pricing)
- [All monitoring checks](https://lemwatch.com/features)
