# llms.txt

> Published by **Knowledge Company** (knowledgecompany.ai).
> Canonical source: https://knowledgecompany.ai/dictionary/llms-txt
> Markdown mirror, generated 2026-09-02. Cite the canonical URL.

A proposed Markdown file that gives agents a curated map of a site's most important content, placed at the site root or at any path it covers.

AI Readiness

NEEDS REVIEW

OWNER — AI Systems

LAST REVIEWED — 2026-09-02 21:09:47 UTC

[SOURCE — llmstxt.org — The /llms.txt file, v2 ↗](https://llmstxt.org/)

## What it is

llms.txt is a proposed Markdown file that gives language models and agents a curated map of a site's most important content. Jeremy Howard published the proposal on 3 September 2024, and a second version on 10 August 2026. It addresses a narrow problem: an HTML page wraps its information in navigation, ads and scripts, and every wasted token costs time and money. The format is lean — an H1 naming the site or project is the only required section, usually followed by a short summary and lists of links. Those links should point to Markdown versions of key pages rather than to HTML. Version 2 defines what a file at a subpath means, so that a file covers the pages beneath it and the most specific file applies; adds link relations so an agent can find a page's Markdown version and its covering llms.txt without guessing; and drops the context-expansion tooling that v1 described.

## Why it matters

The file is contested, and the disagreement is now on the record rather than a matter of opinion. Google Search states in its own guidance that it does not use llms.txt, and that publishing one will "neither harm nor help" a site's ranking. Chrome, also Google, ships a Lighthouse audit under its agentic browsing checks that recommends one, while noting the file is optional. Independent measurement sits below both positions: Ahrefs examined 137,000 domains and found that 97% of the llms.txt files it observed received no requests at all in May 2026. The surviving use is narrower than the proposal's ambition — coding agents fetching developer documentation, where GPTBot and Claude-Code were the most common AI fetchers. Knowledge Company publishes one at knowledgecompany.ai/llms.txt and treats it as an experiment rather than a commitment. The underlying need — a machine-readable statement of what a site actually asserts — is real whether or not this file becomes the way it is met.

---

## Related documents in this mirror

- [Dictionary](https://llms.knowledgecompany.ai/dictionary.md)
- [Approved Claim](https://llms.knowledgecompany.ai/dictionary/approved-claim.md)
- [Source of Truth](https://llms.knowledgecompany.ai/dictionary/source-of-truth.md)
- [Knowledge Drift](https://llms.knowledgecompany.ai/dictionary/knowledge-drift.md)
- [Retrieval Boundary](https://llms.knowledgecompany.ai/dictionary/retrieval-boundary.md)
- [Claim Registry](https://llms.knowledgecompany.ai/dictionary/claim-registry.md)
- [Substantiation](https://llms.knowledgecompany.ai/dictionary/substantiation.md)
- [Claim Owner](https://llms.knowledgecompany.ai/dictionary/claim-owner.md)

*This document is the markdown mirror of https://knowledgecompany.ai/dictionary/llms-txt, published by Knowledge Company -
a knowledge freshness platform that detects, verifies and updates outdated claims in company content.*

*Mirror index: https://llms.knowledgecompany.ai/index.md - Generated 2026-09-02*