🚀 @mnexium/chat — Drop-In AI Chat for Any Web App

We just shipped @mnexium/chat: a single npm package that adds a polished, production-ready AI chat widget to any website. React, Next.js, Express, or plain HTML — it just works, and most importantly it remembers.

The Problem

Adding AI chat to a product usually means:

• Designing and building a custom UI

• Handling streaming responses

• Managing conversation state

• Securing API keys

• ... and it still wont remember anything about your users

That’s a lot of engineering just to let users ask questions.

Demo

Visit mnexium.com or mnexium.com/docs and try it out on the @Mnexium AI website.

The Solution

NPM Package - https://www.npmjs.com/package/@mnexium/chat

npm install @mnexium/chat

One package. Three ways to use it:

⚛️ React / Next.js

import { MnexiumChat } from '@mnexium/chat';

export default function App() {
  return (
    <>
      <YourApp />
      <MnexiumChat endpoint="/api/mnx" />
    </>
  );
}

A floating chat button appears. Click. Chat. Done.

🌐 Plain HTML / Express

<script 
  src="/mnexium-chat.js"
  data-endpoint="/api/mnx"
  data-theme="dark"
></script>

Same UI. No React. No build step.

🧩 Headless (Bring Your Own UI)

import { MnexiumClient } from '@mnexium/chat/core';

const chat = new MnexiumClient({ endpoint: '/api/mnx' });
chat.onMessage((messages) => renderYourOwnUI(messages));
await chat.send('Hello!');

We handle streaming + state. You control the interface.

What You Get

• Floating widget with modern glass design

• Real-time streaming responses

• Markdown rendering

• Dark/light themes + custom colors + logo

• Multi-provider support (OpenAI, Anthropic, Gemini)

• Persistent memory across sessions

Why Mnexium?

The widget is powered by Mnexium, which gives your AI:

• 🧠 Memory across conversations

• 📚 Automatic learning from users

• 🎯 Personalization over time

You get a smarter assistant without building memory infrastructure.

@mnexium/chat v2.0.0 is live on npm.
One package. Any framework. Instant AI chat.