Add a team of AI agents to your GitBook docs — a support agent grounded in your content that answers with cited sources and can reach your tools via MCP, asking before it changes anything. AIML.chat indexes your published GitBook and answers visitors 24/7.
What your readers get
A reader who can't find an answer gets an instant, cited response pulled from your own GitBook pages rather than a generic guess. Behind the widget, AIML.chat runs a Support agent grounded in your content and tool-calling agents that act through the Model Context Protocol (MCP), with human write-confirm on anything that changes data. Every answer links back to the source page, and the analytics show which questions go unanswered so you know what to write next.
Add it in three steps
- 1Create a website in AIML.chat and point the crawler at your published GitBook URL. It indexes every page automatically.
- 2Add the embed snippet via GitBook's site customization (custom script injection, available on plans that allow it) — or run the widget on a wrapper page or portal you control.
- 3Publish. The assistant answers from your GitBook content, themed to match, and stays current as you re-crawl.
Because the widget is vanilla JS under 30KB gzipped, it's light wherever it loads. If your plan restricts script injection, you can still index your GitBook and surface the assistant on your main site or docs landing page. As content changes, a re-crawl keeps answers accurate. For similar platforms, see the ReadMe and Mintlify guides.
Can I embed the widget inside GitBook?+
On plans that allow custom script injection, yes. Otherwise, index your GitBook and run the assistant on a site or portal page you control.
Does it use my GitBook content?+
Yes. AIML.chat crawls your published GitBook and answers from it with cited sources.
Is there a free plan?+
Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.