Introducing Browser Sandbox - Give your agents a secure, fully managed browser environment Read more →
Eric Ciarla
Welcome to Launch Week III, Day 4! Today we’re excited to launch llmstxt.new — the fastest way to turn any website into a clean, consolidated text file for LLMs.
Meet llmstxt.new: Text Extraction Made Effortless
With llmstxt.new, you can instantly transform any webpage into a .txt file that’s optimized for large language models. No clutter, no boilerplate — just the content that matters.
Just add llmstxt.new/ in front of any URL and get back clean, structured text ready for use in training or inference.
Key Features
- Instant Usage: Add
llmstxt.new/before any URL.- Example:
llmstxt.new/https://firecrawl.dev
- Example:
- Two Outputs:
llms.txt– a concise, structured summary.llms-full.txt– the complete page content.
- API Friendly: Use it via
http://llmstxt.new/{YOUR_URL}or integrate with your Firecrawl API key for full control. - LLM-Ready Format: Built for modern LLM pipelines, both training and inference.
Built on Firecrawl
llmstxt.new is powered by Firecrawl’s extraction engine, ensuring reliable parsing, smart content filtering, and high-quality text generation from any web source.
Whether you’re prepping datasets, building LLM apps, or feeding prompts — this tool gets you to usable text faster than ever.
Try it Now
- Get started: llmstxt.new
- Need help? Join the Discord or reach out via help@firecrawl.com
Eric Ciarla @ericciarla
Cofounder and CMO of Firecrawl
About the Author
Eric Ciarla is a co-founder of Firecrawl. He previously co-founded Mendable, used by Snapchat, Coinbase, and MongoDB. He's been building products in the AI and data space since 2022.
More articles by Eric Ciarla
Browser Sandbox: Secure Environments for Agents to Interact with the WebBranding Format v2: Improved Logo ExtractionExtract Web Data at Scale With Parallel AgentsIntroducing the Firecrawl Skill and CLI - Give Agents Real-Time Web DataHow Credal Extracts 6M+ URLs Monthly to Power Production AI AgentsIntroducing Spark 1 Pro and Spark 1 MiniIntroducing /agent: Gather Data Wherever It Lives on the WebRetell’s AI phone agents get LLM-ready content from FirecrawlIntroducing Firecrawl v2.5 - The World's Best Web Data APIWhy Firecrawl Beats Octoparse for AI Web ScrapingFOOTER
The easiest way to extract
data from the web
data from the web
. .
.. ..+
.:.
.. .. .::
+.. ..: :.
.:..::. .. ..
.--:::. .. ... .:. ..
.. .:+=-::.:. . ...-.::. ..
::.... .:--+::..: ......:+....:. :.. ..
....... ::-=:::: ..:-:-...: .--..:: .........
.. . . . ..::-:-.. .-+-:::.. ...::::. .: ...::.:..
. -... ....: . . .--=+-::. :-=-:.... . .:..:: .:---:::::-::....
..::........::=..... ...:-.. .:-=--+=-:. ..--:..=::.... . .:.. ..:---::::---=:::..:...
..........::::.:::::::-::.-.. ...::--==:. ..-::-+==-:... .-::....... ..--:. ..:=+==.---=-+-:::::::-..
. .....::......:: ::::-::.---=+-:..::-+==++X=-:. ..:-::-=-== ---.. .:.--::.. .:-==::=--X==-----====--::+:::+...
..-....-:..::-::=-=-:-::--===++=-==-----== X+=-:.::-==----+==+XX+=-::.:+--==--::. .:-+X=----+X=-=------===--::-:...:. ....
....::::...:-:-==+++=++==+++XX++==++--+-+==++++=-===+=---:-==+X:XXX+=-:-=-==++=-:. .:-=+=- -=X+X+===+---==--==--:..::...+....+
..:::---.::.---=+==XXXXXXXX+XX++==++===--+===:+X+====+=--::--=+XXXXXXX+==++==+XX+=: ::::--=+++X++X+XXXX+=----==++.+=--::+::::+. ::.=...
.:::-==-------=X+++XXXXXXXXXXX++==++.==-==-:-==+X++==+=-=--=++++X++:X:X+++X+-+X X+=---=-==+=+++XXXXX+XX=+=--=X++XXX==---::-+-::::.:..-..