惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

IT之家
IT之家
博客园 - 聂微东
雷峰网
雷峰网
Microsoft Azure Blog
Microsoft Azure Blog
WordPress大学
WordPress大学
Hugging Face - Blog
Hugging Face - Blog
S
SegmentFault 最新的问题
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
T
Tailwind CSS Blog
博客园 - 三生石上(FineUI控件)
V
Visual Studio Blog
博客园 - 司徒正美
爱范儿
爱范儿
月光博客
月光博客
阮一峰的网络日志
阮一峰的网络日志
博客园_首页
博客园 - 【当耐特】
Jina AI
Jina AI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
酷 壳 – CoolShell
酷 壳 – CoolShell
大猫的无限游戏
大猫的无限游戏
小众软件
小众软件
人人都是产品经理
人人都是产品经理
V
V2EX

Mintlify Blog

22 UX improvements to the web editor Introducing the Mintlify Help Center Starter Kit Introducing the collaborative editor built for teams and agents Workflows, rebuilt Is your documentation agent-ready? Mintlify raises $45M Series B led by Andreessen Horowitz and Salesforce Ventures 5 things you didn't know you could do in the Mintlify web editor The improved Mintlify CLI Docs on autopilot: From zero to self-maintaining with Mintlify The state of agent traffic in documentation (March 2026) How we built a virtual filesystem for our Assistant We Replaced Our Internal Wiki With a Slack Bot. You Should Too. 8 ways teams use Mintlify to keep docs updated automatically Documentation is your AI interface What three years of watching AI in production taught us Bridging two JSX runtimes: How we solved Astro's React children problem AI agents are shipping faster than anyone can document Knowledge management systems for technical teams Workflows: Automate documentation maintenance Mintlify acquires Helicone to redefine AI knowledge infrastructure Why more product managers are switching to Mintlify Auto-generating documentation sites from GitHub repos Your docs, your frontend, our content engine Take control of your documentation system Almost half your docs traffic is AI, time to understand the agent experience @mintlify for better docs, faster Mintlify for Enterprise Real llms.txt examples from leading tech companies (and what they got right) Mintlify + Claude Opus 4.6: Powering AI-native knowledge management Declaring Clankruptcy: An experiment in agent orchestration
How to generate llms.txt
Tiffany Chen · 2025-07-25 · via Mintlify Blog

If you're trying to set up an llms.txt file, you're probably already familiar with the standard: a lightweight way to help AI tools better index your site's content.

But knowing what it is and knowing how to write and host the file are two different things.

In this guide, we'll walk through exactly how to create an llms.txt file, including what it should contain, how to create one with Mintlify's free llms.txt generator, and where to host it.

llms.txt is a plain Markdown file, usually placed at the root of your website.

It gives LLMs a low-noise summary of your most important content and links without needing to parse complex HTML or bloated sitemaps.

There are a few different ways you can use it. Some teams add it to their marketing site to give answer engines a clear overview of their product and messaging.

But llms.txt is especially valuable for product documentation. If your users are turning to tools like ChatGPT, Perplexity, or Gemini to get help, llms.txt helps ensure the answers they see are accurate, contextual, and grounded in your actual docs.

If you're on Mintlify, we auto-generate llms.txt (and llms-full.txt) for you out of the box.

The anatomy of an llms.txt file follows this structure:

  • Title: Site or company name (required)
  • > Blockquote: Short summary, e.g. description or key benefits
  • ## Sections: Key content areas
  • [Link](url): Description: List important pages under each section
  • ## Optional: For helpful but lower-priority resources

Here's an example of how it looks:

# PulseMetrics

> PulseMetrics helps growth teams track user behavior and campaign performance in real time.

## Product
- [Features](https://pulsemetrics.io/features): What PulseMetrics can do
- [Use Cases](https://pulsemetrics.io/use-cases): How teams use PulseMetrics

## Resources
- [Pricing](https://pulsemetrics.io/pricing): Compare plan tiers
- [Blog](https://pulsemetrics.io/blog): Product updates and analytics tips

## Optional
- [Careers](https://pulsemetrics.io/careers): Open roles at PulseMetrics

The easiest way to get started is with our free llms.txt file generator.

Just paste in your docs site URL, and we'll generate a starter file based on your structure.

With that template, you can make adjustments such as:

  • Customize the section names to reflect your actual product experience
  • Add brief, human-readable descriptions to help models interpret the page's purpose
  • Reducing URLs - you don't need to include every URL, just the most useful and representative ones

You can treat the generated file as a starting template, then fine-tune it to match how you want your product understood by AI.

ManualAutomatic (Mintlify)
Setup effortWrite and maintain the file yourselfGenerated from your docs on every deploy
Stays in syncRequires manual updates when content changesAlways reflects your latest published docs
Content controlFull control over ordering, descriptions, and structureGenerated structure follows your docs navigation
Includes llms-full.txtYou'd need to build a script to concatenate pagesAuto-generated alongside llms.txt
Markdown versions (.md)Requires custom build stepEvery page gets a .md version automatically
Best forSites where you want precise control over what AI seesDocumentation that changes frequently across many pages

Manual generation gives you full control and works well for marketing sites or docs with stable content. Automatic generation makes more sense when your documentation changes frequently and you don't want the llms.txt file falling out of sync.

Once you have the file, you need to host it so that it's discoverable by LLMs.

Place the raw Markdown file in the root directory of your site, such as example.com/llms.txt. Just like robots.txt or sitemap.xml, this file should be accessible via a direct URL.

Some tips:

  • Ensure it serves as plain text or Markdown, not wrapped in HTML
  • If you're using a static site generator, configure a public folder or route to expose the file
  • If your docs live under a subpath (e.g., example.com/docs), you can also serve it at /docs/llms.txt

After creating your file, verify it works correctly:

  1. Check accessibility: Visit yoursite.com/llms.txt in a browser. You should see raw Markdown, not an HTML page.
  2. Verify the format: The file must start with a # title. A blockquote summary is recommended but optional.
  3. Test all links: Every URL in your llms.txt should return a 200 status. Broken links mean the AI gets incomplete context about your product.
  4. Check file size: Keep llms.txt concise. As a rough guideline, aim for under 50KB. Use llms-full.txt for comprehensive content.

Common mistakes to avoid:

  • Wrapping the file in HTML instead of serving raw Markdown
  • Including every URL on your site instead of curating the most important ones
  • Forgetting to update llms.txt when you add or remove documentation pages
  • Using relative URLs instead of absolute URLs
  • Missing the required H1 title at the top of the file

llms.txt is becoming the new standard for making web content accessible to AI. It's simple to adopt, but powerful in impact, especially for developer tools and product-led companies.

With Mintlify, you don't even have to think about it. We automatically generate and host /llms.txt, /llms-full.txt, and .md versions of all your pages for LLM optimization.

If you want to skip the manual setup, you can get started with Mintlify today and make your documentation LLM-ready by default.