News for hackers. Stuff that matters.

Show HN: Llms.txt Generator – Turn websites into a text file to feed to any LLM

https://llmstxt.firecrawl.dev/

Hey HN! It’s Eric from Firecrawl (https://firecrawl.dev).

I just launched llms.txt Generator, a tool that transforms any website into a clean, structured text file optimized for feeding to LLMs. You can learn more about the standard at https://llmstxt.org.

Here’s how it works under the hood:

1. We use Firecrawl, our open-source scraper, to fetch the full site, handling JavaScript-heavy pages and complex structures. 2. The markdown content is parsed and then the title and description are extracted using GPT-4o-mini. 3. The everything is combined and the result is a lightweight llms.txt file that you can paste into any LLM.

Let me know what you think!

( 6 comments | on HN )
Re:Show HN: Llms.txt Generator – Turn websites into a text f... by jondwillis on Friday November 22, 2024 @10:25AM (#42214547)
Plain HTTP and passing an API key as a URL query parameter? Yikes!
Re:Show HN: Llms.txt Generator – Turn websites into a text f... by DrillShopper on Friday November 22, 2024 @10:59AM (#42214869)
Thanks for facilitating even more widespread and frictionless copyright violations
Re:Show HN: Llms.txt Generator – Turn websites into a text f... by e-clinton on Saturday November 23, 2024 @05:45AM (#42220258)
Wait till you hear about copy/paste
Re:Show HN: Llms.txt Generator – Turn websites into a text f... by DrillShopper on Sunday November 24, 2024 @01:28PM (#42229447)
Not the same thing and not at the same scale
Re:Show HN: Llms.txt Generator – Turn websites into a text f... by IndieCoder on Friday November 22, 2024 @11:16AM (#42215031)
I like the idea but Firecrawl and GPT4o is quite heavy. I use https://github.com/unclecode/crawl4ai in some projects, it works very well without these dependencies and is modular so you can use LLMs but do not have to :)
Re:Show HN: Llms.txt Generator – Turn websites into a text f... by throwaway314155 on Friday November 22, 2024 @04:13PM (#42217413)
For a simple solution, you can just right click->Save Page As.. and upload the resulting `.html` file into Claude/ChatGPT as an attachment. They're both more than capable of parsing the article content from the HTML without needing any pre-processing.