into-md

Fetch any URL. Get clean markdown. Feed it to your LLM.

v0.5.0

Install

Global install with your package manager of choice:

bun add -g into-md
npm install -g into-md
yarn global add into-md

Or use bunx into-md to run without installing.

How it works

Pass any URL and get back clean, structured markdown ready for LLM consumption. into-md auto-detects whether a page needs a headless browser and falls back to Playwright if needed.

URL

into-md

clean markdown

What you get

Smart extraction

Uses readability heuristics to pull out the main content and strip away navigation, ads, and clutter.

Auto JS detection

Automatically detects SPAs and JS-rendered pages and falls back to a headless browser when needed.

LLM ready

Clean output with YAML frontmatter and semantic markdown, optimized for feeding into AI context windows.

Well structured

Tables converted to JSON, images preserved with context, and code blocks auto-tagged for syntax highlighting.

Example

$ into-md https://example.com/article

---
title: "Example Article"
description: "A sample web page"
strategy: "auto>static"
source: "https://example.com/article"
---

# Example Article

The main content of the page, cleaned up
and ready for your LLM...

Built by Nico Baier

GitHub