Add a team of AI agents to your ReadMe.io developer hub — a support agent grounded in your API docs that answers with cited sources and can reach your tools via MCP, asking before it changes anything. Developers get answers without leaving your docs.
What your readers get
A developer stuck on an endpoint or auth flow gets an instant, cited answer pulled from your own ReadMe content 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 reference page, and the analytics show which questions go unanswered — invaluable for an API docs team. It also captures a lead when it can't fully answer, so you never lose a developer evaluating your API, and you can adopt its generated FAQ suggestions as starter prompts.
Add it in three steps
- 1Create a website in AIML.chat and point the crawler at your ReadMe hub URL. It indexes your guides and API reference automatically.
- 2Add the embed snippet in ReadMe's Configuration → Appearance → Custom JS (or the custom HTML/JS area your plan provides).
- 3Save. The assistant appears across your hub, themed to match, and stays current as you re-crawl.
Because the widget is vanilla JS under 30KB gzipped, it loads cleanly inside ReadMe without slowing the page. As your reference changes, a re-crawl keeps answers accurate, and the analytics tell you which endpoints confuse developers most. For similar platforms, see the GitBook and Mintlify guides.
How do I embed the widget in ReadMe?+
Add the snippet via ReadMe's Custom JS area under Configuration → Appearance, and it loads across your hub.
Does it answer API questions accurately?+
Yes. It grounds answers in your indexed reference and guides, with citations to the exact page.
Is there a free plan?+
Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.