---
title: "Mintlify vs ReadMe for agents: Agent Ready HTML"
description: "Mintlify against ReadMe on initial HTML, llms.txt, markdown, JSON-LD and OpenAPI, with a sourced difference and verdicts for three readers. Read 2026-11-04."
canonical: https://agentreadyhtml.com/compare/mintlify-vs-readme/
site: "Agent Ready HTML"
last_updated: 2026-11-04
section: "Compare"
---

# Mintlify vs ReadMe for agents: Agent Ready HTML

> Mintlify against ReadMe on initial HTML, llms.txt, markdown, JSON-LD and OpenAPI, with a sourced difference and verdicts for three readers. Read 2026-11-04.

Source: https://agentreadyhtml.com/compare/mintlify-vs-readme/
Site: Agent Ready HTML
Last reviewed: 2026-11-04

# Mintlify against ReadMe on what an agent reads

In short

Mintlify also serves the file at /.well-known/llms.txt and advertises llms.txt, llms-full.txt, the API catalog, MCP server card and agent card in an HTTP Link header, plus an X-Llms-Txt header. Mintlify leads on markdown on request, 2 to 1; ReadMe: Markdown for Agents is a documented setting under AI Discoverability; defaults vary by setting.

## The sourced difference

ReadMe returns markdown 404s with agentTools front matter and redirects guessed URLs such as /docs.md to the matching llms.txt; Mintlify returns a markdown 404 with links to llms.txt, llms-full.txt and up to three related pages, and splits llms.txt above 100,000 characters. [Source](https://docs.readme.com/main/changelog/upgraded-llms-txt), read 4 November 2026.

## The rubric side by side

| Key | Mintlify | ReadMe |
| --- | --- | --- |
| Content in the initial HTML | 2, on by default | 2, on by default |
| Real status codes | 2, on by default | 2, on by default |
| llms.txt generation | 2, on by default | 2, on by default |
| llms.txt linking | 2, on by default | 2, on by default |
| Markdown on request | 2, on by default | 1, with setup |
| JSON-LD output | 1, with setup | 0, not offered |
| OpenAPI exposure | 2, on by default | 2, on by default |
| Fenced, tagged code | 2, on by default | 2, on by default |
| Total | 15 of 16 | 13 of 16 |

The two differ on 2 of the numeric keys: markdown on request, JSON-LD output. Evidence for each score is on the profiles of [Mintlify](https://agentreadyhtml.com/platforms/mintlify/) and [ReadMe](https://agentreadyhtml.com/platforms/readme/).

## Verdicts by reader

Technical SEO

Both return real 404s to agents; ReadMe also catches guessed paths with redirects.

Docs owner

For large API references, Mintlify splitting and ReadMe Summarize Index solve the same size problem differently.

Front-end developer

Neither needs custom routing; both keep llms.txt current from navigation.

## What each leaves undone

### Mintlify

-   Does not publish the llms.txt behind a fully authenticated site to tools that cannot sign in.
-   Does not cap llms-full.txt size; the 100,000 character split applies to llms.txt only.

### ReadMe

-   Does not promise that an agent will request llms.txt.
-   Does not keep a custom llms.txt in sync with content changes.

Work left to the developer: Mintlify, Low: write a description in each page frontmatter so llms.txt entries carry one. ReadMe, Low: review the AI Discoverability toggles; a custom llms.txt stops automatic updates.

-   [Alternatives to Mintlify](https://agentreadyhtml.com/platforms/mintlify/alternatives/)
-   [Alternatives to ReadMe](https://agentreadyhtml.com/platforms/readme/alternatives/)

## Sources

1.  [docs.readme.com: the difference](https://docs.readme.com/main/changelog/upgraded-llms-txt) https://docs.readme.com/main/changelog/upgraded-llms-txt, read 4 November 2026
2.  [Mintlify: documentation](https://www.mintlify.com/docs/ai/markdown-export) https://www.mintlify.com/docs/ai/markdown-export, read 4 November 2026
3.  [ReadMe: documentation](https://docs.readme.com/main/docs/ai-discoverability) https://docs.readme.com/main/docs/ai-discoverability, read 4 November 2026

Last reviewed 4 November 2026

Edition

Crawl

2026-11-04

Page updated

2026-11-04

Method

How the viewer reads a page, how a file is graded and how a platform is scored: [the method page](https://agentreadyhtml.com/method/).