alt/repo
alternative-repository

llms.txt Generator & Validator

Build a curated Markdown index that helps LLMs find the right docs, API references, examples, policies, and optional context without crawling your whole site.

1. Project Setup

Seeds sections for searches like nextjs llms txt, tailwind llms txt, shadcn llms txt, and pydantic ai llms txt.

2. Resource Planner

One per line: section | title | URL | notes.

3. Generated llms.txt

Sections0
Links0
Optional0
StatusDraft

4. Structure Report

    Better than URL-only generators: this tool does not blindly dump every page. It helps you choose the URLs an LLM should actually read: overview, docs, API, examples, policies, and lower-priority optional context.

    What an llms.txt file actually does

    /llms.txt is a proposed standard for giving language models a concise, Markdown-readable map of your site. The official proposal describes it as a way to help LLMs use a website at inference time: when a user or AI tool needs context, the file points to the most useful public resources instead of forcing the model to parse your whole HTML site.

    The important distinction: llms.txt is not an access-control file. It does not replace robots.txt. Use robots.txt for crawler permissions, sitemap.xml for broad URL discovery, and llms.txt for curated explanation.

    Official llms.txt proposal opens new tabThe canonical explanation of the format, required order, file-list sections, and the special meaning of Optional.
    How this tool follows itThe generator outputs the spec shape: H1 title, blockquote summary, optional notes, H2 sections, Markdown links, and an Optional section for skippable resources.
    How llms.txt fits with robots.txt and sitemap.xml Diagram showing robots.txt for permissions, sitemap.xml for broad discovery, and llms.txt for curated LLM context. robots.txtcrawler permission sitemap.xmlbroad URL inventory llms.txtcurated LLM context Crawlerchecks allow / disallow Search Enginediscovers indexable pages LLM / Agentreads selected docs Your ContentHTML pagesMarkdown docsAPI referencesPolicies

    The required shape

    The official format is intentionally simple Markdown. A valid file starts with one H1 title. Then it usually has a blockquote summary, optional plain Markdown notes, and H2 sections that contain file lists. Each list item should be a Markdown link, optionally followed by a short note.

    • 1. H1 title
      # Project Name
    • 2. Summary
      > One short explanation
    • 3. Details
      Notes that help interpret the linked files.
    • 4. H2 file lists
      ## Docs, ## API, ## Examples
    • 5. Markdown links
      - [Title](https://...): Why it matters
    • 6. Optional section
      Lower-priority links that can be skipped for shorter context.
    llms.txt file anatomy Diagram showing the order of title, summary, notes, core links, docs links, examples links, and optional links. H1name Quotesummary Notesguidance Coremust read Docs/APIdetails Optionalskippable

    Example: developer tool website

    Scenario

    A developer tool site has a homepage, docs index, API docs, examples, and a robots policy. A crawler can discover many URLs from the sitemap, but an LLM needs the few pages that explain the project clearly.

    The goal is not to expose private pages or stuff every URL into the file. The goal is to point AI tools at the canonical docs that answer real questions.

    # ExampleDev

> ExampleDev is a JavaScript toolkit for building fast UI utilities.

Use public documentation as source material. Avoid account,
admin, changelog drafts, and generated search pages.

## Core
- [Overview](https://example.com/index.html.md): Product overview
- [Quick start](https://example.com/docs/start.html.md): First setup path

## API
- [API reference](https://example.com/docs/api.html.md): Public API options

## Examples
- [Recipes](https://example.com/docs/recipes.html.md): Common use cases

## Optional
- [Sitemap](https://example.com/sitemap.xml): Full canonical URL list
- [Robots policy](https://example.com/robots.txt): Crawler permissions

    How to make an llms.txt file that is useful

    1. Start with a clear H1 project name and one-sentence blockquote summary.
    2. Add only public, canonical resources. Prefer Markdown versions such as .html.md when your docs can provide them.
    3. Separate must-read resources from Optional links so short-context tools can skip secondary material.
    4. Include framework-specific setup, API references, examples, and policy pages when they help an LLM answer accurately.
    5. Review quarterly or whenever your documentation, product, pricing, API, or major navigation changes.

    llms.txt FAQ

    What is an llms.txt file?

    It is a Markdown file, usually placed at /llms.txt, that gives LLMs a concise summary and curated links to the most important machine-readable resources for a site or project.

    What is the difference between robots.txt and llms.txt?

    robots.txt is about crawler permissions. llms.txt is about context and comprehension. They work together, but one does not replace the other.

    Should I include every URL?

    No. A good llms.txt file is curated. Link the pages that explain the project best, and put secondary references under an Optional section.

    Where should I put it?

    The standard location is the site root: https://example.com/llms.txt. Some projects may also publish scoped files in subpaths for large documentation areas.

    Why include framework presets?

    Developers often search for framework-specific llms.txt examples. Presets help seed sections for docs, setup, API, examples, components, configuration, and migration notes.