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 🙏

© 2025 – Pkg Stats / Ryan Hefner

@kognitiv-ai/kog-chat

v1.0.19

Published

Kog Chat widget - embeddable AI chat for your website

Downloads

1,957

Readme

@kognitiv-ai/kog-chat

Embeddable AI chat widget for your website.

Installation

npm:

npm install @kognitiv-ai/kog-chat

CDN:

<script src="https://unpkg.com/@kognitiv-ai/kog-chat"></script>

Usage

Minimal:

import KogChat from '@kognitiv-ai/kog-chat';

new KogChat().mount(document.body);

With client-side tools:

import KogChat from '@kognitiv-ai/kog-chat';

const kog = new KogChat();

// Register tools the AI can invoke
kog.registerTool('read_page_content', () => document.body.innerText);
kog.registerTool('get_current_url', () => window.location.href);
kog.registerTool('get_selected_text', () => window.getSelection().toString());

kog.mount(document.body);

CDN (no build step):

<script src="https://unpkg.com/@kognitiv-ai/kog-chat"></script>
<script>
  const kog = new KogChat();
  kog.registerTool('read_page_content', () => document.body.innerText);
  kog.mount(document.body);
</script>

Configuration

const kog = new KogChat({
  // All options are optional
  bearerToken: 'jwt-token',        // Pre-authenticate (skip login screen)
  apiBaseUrl: 'https://your-api',   // Backend API base
  theme: 'light',                  // 'dark' | 'light'
  corner: 'bottom-right',          // Widget position
  paneSide: 'right',               // Pane slide direction
  paneWidth: '550px',              // Pane width
  paneHeight: '100%',              // Pane height
  primaryColor: '#2563eb',         // Brand colors
  secondaryColor: '#00c389',
  tertiaryColor: '#d3d9e4',
  surfaceColor: '#f7f9fc',         // Surface background
  panelColor: '#ffffff',           // Panel background
  textColor: '#0f172a',
  triggerIconUrl: 'https://cdn.example.com/brand/chat-icon.svg', // or triggerIconSvg (inline)
  fullscreen: false,               // If true, iframe fills the provided container and stays open
});

// For an inline, always-open embed:
// const kog = new KogChat({ fullscreen: true }).mount(document.getElementById('chat-container'));

All options can also be provided later via kog.updateConfig({ ... }).

Events

kog.on('ready', () => console.log('Widget ready'));
kog.on('opened', () => console.log('Chat opened'));
kog.on('closed', () => console.log('Chat closed'));
kog.on('toolCall', ({ toolName, args }) => console.log('Tool called:', toolName));

API

| Method | Description | |--------|-------------| | mount(element) | Mount widget to a DOM element | | unmount() | Remove widget | | registerTool(name, callback) | Register a client-side tool | | unregisterTool(name) | Remove a tool | | open() | Open chat pane | | close() | Close chat pane | | on(event, callback) | Add event listener | | off(event, callback) | Remove event listener | | whenReady() | Returns Promise that resolves when ready |

License

MIT