npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

agent-builder-chat

v1.0.5

Published

A customizable chat widget for Agent Builder - easily embed AI chat functionality into your React/Next.js applications

Readme

Agent Builder Chat Widget

A customizable chat widget for Agent Builder - easily embed AI chat functionality into your React/Next.js applications.

Installation

npm install agent-builder-chat
# or
yarn add agent-builder-chat
# or
pnpm add agent-builder-chat

Quick Start

Next.js / React

'use client'; // Required for Next.js App Router

import { ChatWidget } from 'agent-builder-chat';

export default function App() {
  return (
    <div>
      <h1>My Application</h1>

      <ChatWidget
        agentId="your-agent-id"
        apiKey="your-api-key"
        baseUrl="http://localhost:3000"
      />
    </div>
  );
}

Props

| Prop | Type | Required | Default | Description | |------|------|----------|---------|-------------| | agentId | string | Yes | - | The ID of your Agent Builder agent | | apiKey | string | Yes | - | Your Agent Builder public API key | | baseUrl | string | No | http://localhost:3000 | The base URL of your Agent Builder backend | | position | 'bottom-right' \| 'bottom-left' | No | 'bottom-right' | Position of the chat button | | primaryColor | string | No | '#6366f1' | Primary color for the widget (hex) | | title | string | No | 'Chat with us' | Title shown in the chat header | | placeholder | string | No | 'Type a message...' | Input placeholder text | | welcomeMessage | string | No | - | Initial message from the assistant |

Advanced Usage

Using the Hook Directly

If you want more control over the chat functionality, you can use the useChatWidget hook:

'use client';

import { useChatWidget } from 'agent-builder-chat';

export default function CustomChat() {
  const {
    messages,
    isLoading,
    error,
    isOpen,
    sendMessage,
    toggleOpen,
    clearChat,
  } = useChatWidget({
    agentId: 'your-agent-id',
    apiKey: 'your-api-key',
    baseUrl: 'http://localhost:3000',
    welcomeMessage: 'Hello! How can I help you today?',
  });

  return (
    <div>
      {/* Build your custom UI */}
    </div>
  );
}

Using the API Directly

For even more control, you can use the sendMessage function directly:

import { sendMessage } from 'agent-builder-chat';

async function chat() {
  const response = await sendMessage(
    {
      agentId: 'your-agent-id',
      apiKey: 'your-api-key',
      message: 'Hello!',
      conversationId: undefined, // First message
    },
    'http://localhost:3000'
  );

  console.log(response.reply);
  console.log(response.conversationId); // Use this for subsequent messages
}

Customization

Custom Colors

<ChatWidget
  agentId="your-agent-id"
  apiKey="your-api-key"
  primaryColor="#10b981" // Emerald green
/>

Custom Position

<ChatWidget
  agentId="your-agent-id"
  apiKey="your-api-key"
  position="bottom-left"
/>

Welcome Message

<ChatWidget
  agentId="your-agent-id"
  apiKey="your-api-key"
  welcomeMessage="Hi there! I'm here to help you with any questions."
/>

API Response

The chat API returns:

interface ChatResponse {
  reply: string;        // The assistant's response
  conversationId: string; // ID to continue the conversation
  leadId: string;       // ID of the lead record
  isComplete: boolean;  // True when all required data fields are captured
}

TypeScript Support

This package is written in TypeScript and includes full type definitions:

import type {
  ChatWidgetConfig,
  ChatWidgetProps,
  Message,
  ChatResponse,
  ChatRequest,
  ChatState,
} from 'agent-builder-chat';

License

MIT