JhunkooBot

JhunkooBot fetches web pages so Jhunkoo.ai customers can train an AI agent on their own website content.

Why it visited your site

Someone using Jhunkoo.ai added a URL from your domain as a knowledge source for their agent. We fetch that page once so its text can be indexed, and again only when the agent is retrained. JhunkooBot does not crawl links, follow your sitemap, or discover pages on its own — it requests only the exact URLs a customer entered.

How to identify it

Requests carry this user-agent string:

JhunkooBot/1.0 (+https://www.jhunkoo.ai/bot)

How to block it

Add this to your robots.txt:

User-agent: JhunkooBot
Disallow: /

To block only part of your site, list those paths instead of /. You can also block the user-agent at your CDN or firewall.

What we do with the content

Page text is converted to plain text and stored as embeddings so the customer's agent can answer questions about it. Scripts, styles, and images are discarded. Content is used only for the agent belonging to the customer who added the URL — it is never shared between customers or used to train foundation models.

Contact

Questions, or think JhunkooBot is behaving incorrectly? Email [email protected].