# llms.txt Generator: Website to LLM & RAG Pack (`blond_terrarium/site-to-llm-pack`) Actor

Turn any website or docs site into a ready-to-use LLM pack: llms.txt (llmstxt.org format), llms-full.txt, clean Markdown pages and RAG-ready chunks.jsonl with URL and title metadata. Crawls sitemaps and links. For ChatGPT, Claude, custom GPTs, vector databases and AI SEO.

- **URL**: https://apify.com/blond_terrarium/site-to-llm-pack.md
- **Developed by:** [LiveFree Analytics](https://apify.com/blond_terrarium) (community)
- **Categories:** AI, Developer tools, SEO tools
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $70.00 / 1,000 llm packs

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## llms.txt Generator: Turn Any Website into an LLM & RAG Pack (llms.txt, Markdown, Chunks)

Turn any website or docs site into a **ready-to-use LLM pack** in one run:

- **`llms.txt`** in the [llmstxt.org](https://llmstxt.org) format (site name, summary, and sections of linked pages with descriptions)
- **`llms-full.txt`** with every page as clean Markdown
- **`chunks.jsonl`**: RAG-ready chunks with URL, title and chunk metadata
- **`pages.jsonl`**: one clean Markdown page per line

**One pack per site.** It crawls sitemaps and links, extracts the main content (no menus, footers or cookie banners) and gives you the files.

- ✅ **llms.txt generator:** publish it at `yoursite.com/llms.txt` for AI search and AI assistants
- ✅ **Website to Markdown** for ChatGPT, Claude, custom GPTs, Gemini Gems and NotebookLM
- ✅ **Vector DB ready:** chunks split on headings and paragraphs, with overlap, for Pinecone, Qdrant, Chroma, pgvector and similar
- ✅ **Whole site or one section:** give a docs URL like `/docs/` and it packs only that section
- ✅ **Free error rows:** offline, blocked or empty sites are never charged

### Who it's for

- **Site owners and SEOs:** add an llms.txt for AI search (GEO/AEO) in minutes
- **AI builders:** feed docs into a RAG chatbot, a custom GPT or an agent
- **Agencies:** "make my client's site AI-ready" as a deliverable
- **Researchers:** a clean offline copy of a site's text

### What you get (real output, shortened)

```
{ "host": "docs.python.org", "crawlScope": "samePath", "siteName": "Python documentation", "pagesIncluded": 18,
  "tokensEstimate": 81596, "chunkCount": 206, "sections": [ { "name": "Pages", "pages": 18 } ],
  "llmsTxtUrl": "https://api.apify.com/v2/key-value-stores/…/records/docs.python.org-3-tutorial-llms-txt",
  "llmsFullTxtUrl": "…", "chunksJsonlUrl": "…", "pagesJsonlUrl": "…", "chargedPacks": 1, "charged": true }
```

llms.txt preview:

```
# Python documentation
> Python is an easy to learn, powerful programming language. …
## Pages
- [The Python Tutorial](https://docs.python.org/3/tutorial/): Python is an easy to learn, powerful programming language…
- [1. Whetting Your Appetite](https://docs.python.org/3/tutorial/appetite.html): If you do much work on computers, eventually…
```

### Try it in 1 minute

1. Add a homepage (whole site) or a section URL (`https://docs.example.com/guide/`).
2. Optional: max pages (default 50), chunk size, include/exclude URL patterns.
3. Run, then open the `llms.txt`, `llms-full.txt` and `chunks.jsonl` links in the output.

   { "websites": \["https://docs.python.org/3/tutorial/"], "maxPagesPerSite": 50, "chunkSize": 2000 }

### Price

One `llm-pack` event per site **per started 50 pages** (1-50 pages = 1 pack, 51-100 = 2).

| Apify plan | Per pack (up to 50 pages) |
|---|---|
| Free | $0.10 |
| Bronze | $0.09 |
| Silver | $0.08 |
| Gold | $0.07 |

- **No start fee** from us. Only Apify's standard minimum start event.
- **If no pack can be built** (every site offline, blocked or empty), the run fails with a clear message and **costs nothing**.

### All settings

| Field | Default | What it does |
|---|---|---|
| websites | – | Homepages or section URLs, one pack each |
| maxPagesPerSite | 50 | Pages per pack (up to 5,000) |
| crawlScope | auto | Section URL = that section; homepage = whole site |
| useSitemaps | true | Also find pages via sitemap.xml |
| maxCrawlDepth | 5 | Clicks from the start URL |
| contentMode | article | Main content only, or the whole page minus nav |
| chunkSize / chunkOverlap | 2000 / 200 | RAG chunking (characters) |
| include/excludeUrlPatterns | – | Filter pages |
| maxChargedPacks | 0 | Hard stop (0 = none) |

### FAQ

**What is llms.txt?** It's a proposed standard: a Markdown file at `/llms.txt` that tells AI tools what a site is about and where its key pages are.
**JavaScript-only sites?** Pages that render only in the browser may come back empty. Those are free error rows, never charged.
**Need just Markdown per page at scale?** Use our [Website to Markdown for LLM](https://apify.com/blond_terrarium/website-to-markdown-llm) actor (charged per page).

### Use it from code, no-code tools or AI agents

- **API:** `POST https://api.apify.com/v2/acts/blond_terrarium~site-to-llm-pack/run-sync-get-dataset-items?token=YOUR_TOKEN`
- **Make, Zapier, n8n, webhooks** through Apify integrations
- **AI agents (MCP):** `https://mcp.apify.com?tools=blond_terrarium/site-to-llm-pack`

# Actor input Schema

## `websites` (type: `array`):

One pack per URL. A homepage packs the whole site; a section URL (https://docs.example.com/guide/) packs just that section.

## `maxPagesPerSite` (type: `integer`):

One pack is charged per started 50 pages (1-50 pages = 1 pack, 51-100 = 2).

## `crawlScope` (type: `string`):

Which pages to include.

## `useSitemaps` (type: `boolean`):

Also discover pages from sitemap.xml (finds pages that are not linked).

## `maxCrawlDepth` (type: `integer`):

How many clicks away from the start URL to follow links.

## `contentMode` (type: `string`):

How to pick the text of each page.

## `chunkSize` (type: `integer`):

Chunks split on headings and paragraphs for vector databases. 0 = one chunk per page.

## `chunkOverlap` (type: `integer`):

Characters repeated between consecutive chunks.

## `includeUrlPatterns` (type: `array`):

Regex or text patterns; only matching URLs are packed.

## `excludeUrlPatterns` (type: `array`):

Regex or text patterns to leave out (for example /tag/, /login).

## `respectRobotsTxt` (type: `boolean`):

Skip pages the site asks crawlers not to visit.

## `maxConcurrency` (type: `integer`):

How many websites to pack at once.

## `maxChargedPacks` (type: `integer`):

Stop after this many charged packs. The run also stops at your "Max cost per run".

## Actor input object example

```json
{
  "websites": [
    "https://docs.python.org/3/tutorial/"
  ],
  "maxPagesPerSite": 50,
  "crawlScope": "auto",
  "useSitemaps": true,
  "maxCrawlDepth": 5,
  "contentMode": "article",
  "chunkSize": 2000,
  "chunkOverlap": 200,
  "respectRobotsTxt": true,
  "maxConcurrency": 2,
  "maxChargedPacks": 0
}
```

# Actor output Schema

## `overview` (type: `string`):

No description

## `files` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "websites": [
        "https://docs.python.org/3/tutorial/"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("blond_terrarium/site-to-llm-pack").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "websites": ["https://docs.python.org/3/tutorial/"] }

# Run the Actor and wait for it to finish
run = client.actor("blond_terrarium/site-to-llm-pack").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "websites": [
    "https://docs.python.org/3/tutorial/"
  ]
}' |
apify call blond_terrarium/site-to-llm-pack --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,blond_terrarium/site-to-llm-pack"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/RVV3cxvFfmPZ2ebgK/builds/hnLhxQZ1bSBrt8Qy0/openapi.json