What is llms.txt and where does it go?

llms.txt is a proposed standard (documented at llmstxt.org) for a markdown file placed at the root of your domain — for example https://example.com/llms.txt. It gives AI tools a concise, curated list of the pages on your site that are most useful for answering questions, similar in spirit to robots.txt and sitemap.xml but designed for large language models rather than search-engine crawlers.

What is the required structure of an llms.txt file?

Only the H1 title is strictly required: a single "# Site name" heading. After that you can add an optional "> summary" blockquote, an optional free-form details paragraph in markdown, and any number of "## Section" headings, each followed by a markdown list of links in the form "- [Title](https://url): optional note". This generator produces exactly that structure and the audit panel tells you which optional parts are missing.

Why do my URLs need to be absolute?

AI crawlers fetch the links in llms.txt directly, often without knowing the page the file came from, so relative paths like /docs cannot be resolved reliably. The audit flags any link that is not a full http:// or https:// URL. Always use absolute URLs, and prefer https, so every entry can be fetched on its own.

What is the "Optional" section for?

The llms.txt convention reserves a section literally titled "Optional" for secondary links. Tools that have a limited context budget can skip everything under "Optional" and still get the core picture of your site from the other sections. Put nice-to-have links — changelog, RSS, archive — there, and keep your primary docs and product pages in regular sections.

Can I edit an llms.txt file I already have?

Yes. Switch to Import mode and paste your existing llms.txt. The tool parses the H1 name, the summary blockquote, the details paragraph, and every section and link back into the structured editor. You can then reorder, fix flagged issues, and export the corrected file. The parser round-trips its own output, so importing a file this tool produced reproduces it exactly.

Is llms.txt the same as robots.txt or a sitemap?

No. robots.txt tells crawlers what they may access, and sitemap.xml lists every URL for search indexing. llms.txt is different: it is a short, human-curated, markdown summary aimed at language models, highlighting only the pages most worth reading and adding a one-line note about each. You can and should keep all three — they serve different audiences.

llms.txt Generator

Build a spec-compliant llms.txt — the markdown file at /llms.txt that gives AI crawlers a curated map of your most important pages. Structured editor with add/remove/reorder sections and links, a live preview, an audit that flags non-absolute URLs and missing fields, ready-made templates, and an Import mode that round-trips an existing file.

About this ToolHow it works, benefits & use cases

An llms.txt file is a small markdown document you place at the root of your site (/llms.txt) that gives AI crawlers and assistants a curated map of your most important pages — exactly like robots.txt and sitemap.xml do for search engines, but written for language models instead. This generator is a full structured editor for the standard at llmstxt.org: you set a site name, a one-line summary blockquote, an optional details paragraph, and any number of titled sections, each holding a reorderable list of links with a title, URL, and an optional note describing what the page is. A live preview renders valid llms.txt as you type, an audit panel flags the issues that weaken it for crawlers — missing name, no summary, non-absolute URLs, empty sections — and an Import mode round-trips an existing file you paste back into the editor so you can fix and re-export it. Four realistic templates (SaaS product, documentation site, developer tool, and blog) give you a complete starting point, and the output copies, downloads as llms.txt, shares via URL, or pipes into another tool.

How to Use

1Start from a template (SaaS, Docs, Developer tool, or Blog) for a complete example, or build from scratch.
2Set the site name (the required H1), a one-line summary blockquote, and an optional details paragraph in markdown.
3Add sections like "Docs" or "Product"; give each a title and add link rows with a page title, absolute URL, and optional note.
4Reorder sections and links with the up/down controls so the most important pages come first.
5Watch the live llms.txt preview and the audit panel — fix any flagged warnings such as non-absolute URLs or a missing summary.
6Switch to Import mode to paste an existing llms.txt and round-trip it back into the editor, then copy, download, or share the result.

Key Benefits

Generates a spec-compliant llms.txt for the emerging AI-crawler standard at llmstxt.org
Structured editor with add, remove, and reorder for both sections and individual links
Live preview renders valid markdown as you type — no guessing the exact format
Built-in audit flags missing names, absent summaries, non-absolute URLs, and empty sections
Import mode parses an existing llms.txt and round-trips it back into the editor
Four realistic templates for SaaS products, docs sites, developer tools, and blogs
Runs entirely in the browser with shareable URLs and copy/download/pipe output

Common Use Cases

Publishing /llms.txt so ChatGPT, Claude, and Perplexity surface the right pages from your site
Pointing AI assistants at your docs quickstart and API reference instead of marketing pages
Maintaining a curated link map for a SaaS product, library, or developer tool
Auditing and fixing an existing llms.txt by importing it and resolving the flagged warnings
Giving an "Optional" section so crawlers can skip secondary links when context is limited

llms.txt

Place this at the root of your site as /llms.txt

# Acme Cloud

> Acme Cloud is a team workspace for planning, tracking, and shipping product work in one place.

Acme Cloud combines docs, issue tracking, and roadmaps. This file points AI assistants at the pages most useful for answering questions about features, pricing, and setup.

## Product
- [Features overview](https://acme.cloud/features): What Acme Cloud does and who it is for
- [Pricing](https://acme.cloud/pricing): Plans, limits, and per-seat pricing
- [Integrations](https://acme.cloud/integrations): Slack, GitHub, Figma, and Zapier connectors

## Docs
- [Getting started](https://acme.cloud/docs/quickstart): Create a workspace and invite your team
- [API reference](https://acme.cloud/docs/api): REST + webhook reference

## Optional
- [Changelog](https://acme.cloud/changelog)
- [Security & compliance](https://acme.cloud/security): SOC 2, data residency, SSO

Looks good — this is a solid llms.txt.

sections

links

Start from a template

Site

Name (required H1)

Summary (blockquote)

Details (optional markdown)

Sections (3)

What is llms.txt?

llms.txt is a proposed standard (llmstxt.org) for a markdown file at the root of your site — https://example.com/llms.txt — that gives AI assistants a curated map of your most useful pages. Like robots.txt and sitemap.xml, but written for language models: a single # Name heading, an optional > summary, and ## Sections of annotated links. Crawlers with a tight context budget can skip anything under an Optional section.

Was this tool helpful?

Share Your Experience

Help others discover this tool!

Share on

Related guide

Guide · 13 min readllms.txt and GEO in 2026: How to Get Your Site Cited by AI SearchA practical, honest guide to Generative Engine Optimization. The technical hygiene that gets you into AI answers, what an llms.txt actually does in 2026 (less than the hype), how to structure pages for extraction, and a checklist ordered by payoff.Read the guide

llms.txt Generator

How to Use

Key Benefits

Common Use Cases

Start from a template

Site

Sections (3)

What is llms.txt?

Was this tool helpful?

Share Your Experience

Related guide

Related tools

Frequently Asked Questions - llms.txt Generator