Add a team of AI agents to your Nextra site — a support agent grounded in your docs that answers with cited sources and can reach your tools via MCP, asking before it changes anything. Since Nextra runs on Next.js, embedding uses the framework you already have.
What your readers get
A reader who's stuck gets an instant, cited answer from your own documentation 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 to the exact page, and the analytics surface the questions your docs don't yet answer.
Add it in three steps
- 1Create a website in AIML.chat and point the crawler at your docs URL (or connect the GitHub repo your MDX lives in). It indexes and embeds every page automatically.
- 2Add the embed with Next.js's
Scriptcomponent in your app — for the Pages Router use a custom_app, for the App Router add it to the root layout — or drop it into Nextra'stheme.confighead element. - 3Deploy. The widget appears site-wide, themed to match, and stays current as you re-crawl.
Because the widget is vanilla JS under 30KB gzipped, it loads cleanly alongside Next.js without hurting your build. As your docs change, a re-crawl — manual, scheduled, or via the GitHub Action on every push — keeps answers accurate. If your whole app is Next.js, see the Next.js guide; for other doc tools, see Docusaurus.
How do I embed it in Nextra?+
Use Next.js's Script component in your _app or root layout, or add the snippet to Nextra's theme.config head element.
Will it stay in sync as my docs change?+
Yes. Re-crawl on demand, on a schedule, or automatically on every push with the GitHub Action.
Is there a free plan?+
Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.