llms.txt Generator — Make Any Website AI-Readable
Pricing
Pay per usage
llms.txt Generator — Make Any Website AI-Readable
Crawl a website and generate llms.txt + llms-full.txt for AI/LLM discoverability and RAG pipelines. Batch, API-callable, pay-per-page.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Cenk KURTOĞLU
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 hours ago
Last modified
Categories
Share
llms.txt Generator — Make Any Website AI-Readable (llms.txt + llms-full.txt)
Generate llms.txt and llms-full.txt for any website — the emerging standard that tells AI models (ChatGPT, Claude, Perplexity, Gemini) what your site is about and how to reference it. Think robots.txt, but for LLMs.
Point this Actor at a URL. It crawls the site, extracts titles, descriptions, and clean main content, and produces two downloadable files ready to drop at your domain root.
Why llms.txt matters in 2026
- RAG is the default architecture for AI apps —
llms.txtfiles are pre-structured, information-dense input made for retrieval pipelines. - Google added
llms.txtto Chrome Lighthouse's "Agentic Browsing" audit (May 2026) as an AI-readiness check. - AI search visibility (GEO/AEO) increasingly depends on giving models a clean, structured map of your content.
What this Actor does
- Crawls a website (same-domain links, up to your
maxPageslimit). - Extracts
title, metadescription, and clean main content (<article>/<main>aware, strips nav/footer/scripts). - Builds
llms.txt— a concise, linked index of your pages. - Builds
llms-full.txt— the full text of every page for complete LLM/RAG ingestion. - Pushes a per-page dataset (URL, title, description) you can export as JSON/CSV.
Built for developers & scale (not just one page)
Unlike one-off web UI tools, this Actor is API-callable, batch-friendly, and pipeline-ready:
- Generate
llms.txtfor hundreds of client sites programmatically. - Wire it into a content/RAG pipeline (n8n, cron, CI) via the Apify API.
- Pay only for pages processed.
Input
| Field | Type | Default | Description |
|---|---|---|---|
websiteUrl | string | — | Site to crawl (required). |
maxPages | integer | 50 | Max pages processed (controls cost/runtime). |
includeFullText | boolean | true | Also generate llms-full.txt. |
maxContentCharsPerPage | integer | 12000 | Truncate very long pages in the full file. |
Output
- Key-value store:
llms.txtandllms-full.txt(download from the run's Storage tab). - Dataset: one record per page (
url,title,description,contentChars).
Example
{"websiteUrl": "https://example.com","maxPages": 100,"includeFullText": true}
Then place the resulting llms.txt at https://example.com/llms.txt (root, like robots.txt).
Use cases
- AI SEO / GEO: make your site discoverable and quotable by AI assistants.
- RAG ingestion: turn any docs/marketing site into clean, chunk-ready text.
- Agencies: batch-generate
llms.txtfor every client site. - AI agents: give agents a structured, low-noise view of a domain.
Tip: run on your documentation or marketing site first, review llms.txt, then publish it at your domain root.