Add a team of AI agents to your SvelteKit app — a support agent grounded in your content that answers with cited sources and can reach your tools via MCP, asking before it changes anything. SvelteKit's app template makes embedding a one-line change.
What your visitors get
A visitor with a question gets an instant, cited answer pulled from your own 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 to the exact source page, so trust stays high. It also captures a lead when it can't fully answer, so you never lose a visitor, and the analytics surface the questions your content doesn't yet cover.
Add it in three steps
- 1Create a website in AIML.chat and point the crawler at your app's URL (or connect its GitHub repo). It indexes and embeds your public pages automatically.
- 2Add the widget embed snippet to the
<head>insrc/app.html, so it loads on every route, or inject it from a root+layout.svelte. - 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 SvelteKit's hydration without hurting performance. As your content changes, a re-crawl — manual, scheduled, or via the GitHub Action on every push — keeps answers accurate. For other JS stacks, see the Remix and Next.js guides.
How do I embed it in SvelteKit?+
Add the widget embed snippet to the <head> in src/app.html, or inject it from a root +layout.svelte.
Does it work with SvelteKit SSR?+
Yes. The widget loads on the client and hydrates cleanly, so server rendering is unaffected.
Is there a free plan?+
Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.