BETA · privacy LLMs & voice servers operational · GPU upgrade underway for faster responses · packages may still change Status & Roadmap →

Website Crawler: automatically scan your website for knowledge base content

The built-in web crawler scans your existing website and automatically converts it into searchable knowledge base content. No more manually copying text.

← ← Back to knowledge base

What does the Website Crawler do?

The Website Crawler visits your website pages, extracts text content and stores it in your bot's knowledge base — all within minutes, without any manual uploads.

How it works

  1. Enter the start URL and optional URL include/exclude patterns.
  2. Set the crawl depth.
  3. Start the crawl — navigation and footer elements are removed, main content is retained.
  4. Text is automatically chunked and indexed in the vector database.
  5. Schedule automatic re-crawls (weekly, monthly) to keep the knowledge base current.

Limitations and ethical use

Robots.txt is respected; noindex/disallow pages are skipped. Images, videos and JS-rendered content are not extracted. The crawler may only be used on websites you own or are authorised to crawl.