llms.txt Tools

llms.txt Insights

Data from 523 real-world llms.txt files, analyzed for structure, size, compliance, and patterns. Last updated March 30, 2026

Projects
523
Total Links
151,268
Median Size
15.6 KB
Unique Sections
5,256

File Size Distribution

How large are llms.txt files across the ecosystem? The smallest is 213 B (/llms.txt directory), the largest 1.8 MB (What is Datadog?).

< 1 KB
18
1–5 KB
98
5–20 KB
187
20–50 KB
92
50–100 KB
52
100–500 KB
64
500 KB+
12
Min
213 B
Median
15.6 KB
Max
1.8 MB

Best Practices Adoption

How well do real-world llms.txt files follow the spec and best practices?

Under 100K tokens
97%
Has H2 sections
96%
No code blocks
92%
Has H1 title
90%
No H3+ headings
78%
Uses absolute URLs
77%
Under 50 KB
76%
Has blockquote description
50%
All links described
35%
Has Optional section
23%

Link Description Coverage

Across 151,268 links, only 54% include descriptions. Descriptions give LLMs context about each page without fetching it.

54%described
With descriptions: 81,194
Without descriptions: 70,074
Median: 83 links per file

Most Common Section Names

5,256 unique H2 section names across all files. These are the most popular.

"Docs"
177x
"Installation"
136x
"API Reference"
130x
"Optional"
121x
"Usage"
94x
"OpenAPI Specs"
87x
"Getting started"
83x
"Next steps"
76x
"Example"
47x
"Troubleshooting"
46x
"Install"
45x
"How it works"
44x

URL Patterns

URL Style
85% absolute15% relative
File Placement
/llms.txt (root)87%
/docs/llms.txt13%
Other paths1%
Link Target Extensions
.md101,691.none57,235.txt9,719.mdx6,614.html1,688.png222.com188.json187

By Category

How do different categories of projects approach llms.txt?

llms.txt usage statistics by project category
Category Count Avg Size Avg Links Size Distribution
Libraries23271.6 KB307
AI5467.9 KB170
Documentation Tools5136.3 KB208
UI Libraries3719.5 KB100
Frameworks3464.7 KB245
Databases3050.5 KB294
Platforms28143.5 KB354
Developer Tools1837.8 KB160
Vue Ecosystem1016.4 KB117
CMS924.4 KB180
Build Tools & Runtimes834.6 KB318
Monitoring5431.7 KB3161
Authentication3214.6 KB1470
E-commerce354.0 KB300
React Ecosystem114.0 KB177

Structural Patterns

Has blockquote description50%
References llms-full.txt10%
Has "Optional" section23%
Uses H3+ headings (non-spec)22%
19 projects use a flat structure (no H2 sections): Next.js, Ark UI, Supabase, Ri Xu Online, Appwrite, Kotlin Documentation, Strapi Documentation, http://docs.copilotkit.ai llms.txt, https://docs.litellm.ai/ llms.txt, Documentation, Memvid, https://www.sardine.ai llms.txt, Alpaca Main Page, sitespeak.ai llms.txt, https://tolgee.io llms.txt, https://latte.nette.org/ llms.txt, WordLift, https://nette.org/en/ llms.txt, ScreenshotOne.com Documentation
45 projects have multiple H1 headings: Svelte, SvelteKit, Ark UI, SWR, Remotion, Turso...
44 projects include code blocks: Svelte, SvelteKit, Waku, daisyUI, Zustand, SWR...

Token Estimates

How much LLM context do these files consume?

Min
54
Median
3,992
Mean
17,090
Max
471,765
18 files exceed 100K tokens
What is Datadog?: 471,765 tokens
Documentation: 447,604 tokens
Add a New Provider: 371,002 tokens
LLMs.txt - Sitemap for AI content discovery: 307,831 tokens
Tamagui Complete Documentation: 267,532 tokens
Kilo Code Documentation: 254,109 tokens
Snowflake Documentation: 231,479 tokens
Gemini CLI Documentation: 219,925 tokens
PraisonAI: 209,780 tokens
SvelteKit: 137,599 tokens
Vultr Documentation: 135,514 tokens
Mailchimp - Complete Web Content Analysis: 131,208 tokens
Modular: 125,191 tokens
Svelte: 117,430 tokens
LaunchDarkly | Documentation: 115,318 tokens
Agno: 114,069 tokens
Documentation: 111,033 tokens
Auth0 blog: 100,823 tokens

Compliance Leaderboard

Size Extremes

Recommendations from the Data

Describe every link

53% of links across the ecosystem lack descriptions. Adding a short description after each link (e.g. - [Page](url): What this page covers) dramatically improves LLM comprehension and saves token budget.

Target 5 to 50 KB

The median file is 16 KB. Files under 50 KB fit easily in any LLM context. Larger files should consider an "Optional" section or splitting into llms.txt (index) and llms-full.txt (full content). Only 12% of files use the Optional pattern.

Use standard section names

"Docs", "Guides", "Reference", "Examples", and "Getting Started" are the most recognized patterns. Using familiar names helps LLMs navigate your file structure predictably. Avoid deeply nested H3+ headings (27% of files violate this).

Always use absolute URLs

21% of projects use relative URLs. Relative URLs break when the file is consumed outside its original domain (AI agents, documentation aggregators, IDE integrations). Always use full https:// URLs.

Consider llms-full.txt

28% of projects reference an llms-full.txt companion file. This pattern is growing because it enables RAG pipelines and deep context loading without requiring the LLM to fetch each page individually.

Frequently Asked Questions

We track and analyze llms.txt files from 523+ projects across frameworks, libraries, platforms, databases, and developer tools. The standard has seen rapid adoption since its introduction, particularly among developer documentation sites.

The median llms.txt file is around 16 KB with about 3,992 tokens. This fits comfortably in any LLM context window. Files over 100 KB start to consume significant context, and files over 500 KB may exceed smaller model limits. Aim for 5 to 50 KB with well-described links.

The most common section names are "Docs", "Guides", "Reference", "Examples", and "Getting Started". Most effective files use 3 to 8 sections. An "Optional" section is a useful pattern that lets LLMs skip less critical content when context is limited.

Yes. Only 54% of links across all analyzed files include descriptions, but descriptions dramatically improve AI comprehension. A link description tells the LLM what the page covers without needing to fetch it, saving tokens and improving accuracy.

About 10% of analyzed projects reference an llms-full.txt companion file. This file embeds the full content of linked pages inline, so AI systems can consume everything in one request. It is especially valuable for RAG pipelines and deep context loading.

We fetch and parse every llms.txt file from our registry of 523+ projects, validate structure against the spec, extract statistics on size, sections, links, and URL patterns, then compute compliance scores. The data is regenerated periodically to track changes.

Related Tools