llms.txt

Holocron generates a /llms.txt file that serves as an index of all documentation pages. This is the primary discovery endpoint for AI agents.

What it contains

The file lists:

The site name and description
A link to /docs.zip for bulk download
Every page with its title and .md URL

Agents can read this file to understand the site structure and then fetch individual pages as Markdown.

Example output

1234567891011121314151617181920212223# My Docs

> Documentation and usage guide for My Docs.

## Best way to inspect these docs

Download all docs as markdown files and grep them locally:

```bash
curl -L https://example.com/docs.zip -o docs.zip
unzip docs.zip -d docs
grep -R "search term" docs/
```

Use this when you need to search across the whole documentation set. The zip contains every page as a .md file.

## Page index

You can also fetch individual markdown pages directly:

- [Getting Started](https://example.com/getting-started.md)
- [Authentication](https://example.com/guides/auth.md)
- [Deployment](https://example.com/deploy.md)

Usage

1curl https://your-docs-site.com/llms.txt

The route is available at both /llms.txt and under your base path if configured.