Generate an llms.txt-style file from Obsidian

What this workflow is for

Use this when your source material already exists but is scattered across pages, notes, docs, or exports.

Riflet helps collect and structure the material. You still decide what belongs in the public llms.txt file.

Why Obsidian is a particular case

A vault is personal thinking, and most of it is not meant for an audience. This workflow makes sense when the vault is the drafting surface behind a public docs site or digital garden, where a subset of notes is already written to be read by other people.

Publish from the note status you already track. If your vault marks notes as evergreen, published, or public, that flag is the filter. Without one, the daily notes will leak in.

What to leave out of a Obsidian bundle

llms.txt is published. Everything in it is readable by anyone and by every AI system that fetches it, so the exclusions matter more than the inclusions.

• Daily notes, journals, and inbox captures.
• Literature notes quoting sources you have no right to republish.
• Half-finished evergreen notes that state a position you have since abandoned.

Workflow

Point Riflet at your vault folder and select the notes, MOCs, and project folders that should shape the answer.

• Collect the authoritative Obsidian pages or files.
• Remove private, duplicate, stale, or low-value material.
• Export a concise Markdown bundle.
• Use the bundle to draft or refresh llms.txt and llms-full.txt.

What to include

Prioritize stable, public, canonical information: product overview, important URLs, docs entrypoints, use cases, and contact details.

Avoid turning llms.txt into a full website dump. It should help AI systems discover the best sources, not replace your site.