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

@iblai/agent-ai

v2.6.2

Published

IBL AI Agent web component

Readme

AgentAI Web Component

The AgentAI web component is a customizable chat widget that can be embedded in any web application. This component is distributed via npm and can also be accessed directly via a bundled JavaScript file hosted on an S3 bucket.

Note: The component is registered as both <agent-ai> and <mentor-ai> for backwards compatibility. <mentor-ai> will be removed in a future version — prefer using <agent-ai>.


Features

  • Embeddable chat widget.
  • Configurable via attributes.
  • Supports authenticated and anonymous modes.
  • Context-aware functionality for dynamic page data exchange.

Installation

Using npm

npm install @iblai/agent-ai

Direct Usage via S3

Include the bundled script in your HTML file:

<script src="https://assets.ibl.ai/web/mentorai.js?versionId=LaZKI7VC02L5buFhcIcaKiBKf4SyjTkD"></script>

Usage

Vanilla Javascript

Include the component directly in your HTML:

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <script src="https://assets.ibl.ai/web/mentorai.js"></script>
    <title>AgentAI Widget</title>
  </head>
  <body>
    <agent-ai
      mentorurl="https://mentor.iblai.app"
      authurl="https://auth.iblai.app"
      lmsurl="https://learn.iblai.app"
      tenant="your-tenant"
      mentor="mentor-id"
      isanonymous
      iscontextaware
      isadvanced
      theme="light"
    ></agent-ai>
  </body>
</html>

Attributes

| Attribute | Description | Type | Default Value | | ----------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | ------- | ------------------------ | | mentorurl | URL of the MentorAI platform. | String | https://mentor.iblai.app | | tenant | Tenant name for authentication. | String | undefined | | mentor | Mentor name for the chat widget. | String | undefined | | isanonymous | Enables anonymous mode. If set, the component will not require user authentication. (Ensure this matches the anonymity of the mentor) | Boolean | false | | iscontextaware | Enables context-aware functionality to send page information to the iframe. | Boolean | false | | isadvanced | Enables advanced chat features. | Boolean | false | | authUrl | URL for authentication. | String | https://auth.iblai.app | | contextOrigins | Comma separated values indicating the origins whitelisted for sending context. Defaults to an empty string. | String | "" | | lmsUrl | URL for edX LMS. | String | learn.iblai.app | | authRelyOnHost | Used to determine if to solely depend on the host for authentication and prevent mentor iframe from redirecting to the auth SPA. | Boolean | false | | edxUserId | Indicates the user id on edX. Optional. | String | undefined | | theme | Sets the theme of the component. Can be either light or dark. | String | light | | component | Specifies the component to display in the mentor application. Can be one of analytics-overview, analytics-users, analytics-topics, or chat. | String | chat | | redirectToken | A token used by the auth layer to redirect back to the equivalent set URL. | String | undefined | | enablechatactionpopup | Enables chat action popups for voice calls and screen sharing. When enabled, sends MENTOR:ENABLE_CHAT_ACTION_POPUPS message to the iframe. | Boolean | false | | contextsettings | Enables the LMS context settings view. When present, renders a settings form instead of the chat iframe. | Boolean | false | | contextid | The LMS context/course identifier. Displayed in the heading and sent with the settings API request. Used with contextsettings. | String | undefined | | contextenabled | Sets the initial state of the Enabled checkbox in the context settings view. Present = checked, absent = unchecked. Used with contextsettings. | Boolean | false |


LMS Context Settings View

When the contextsettings attribute is present, the component renders a settings form instead of the chat iframe. This view is designed for instructors in external LMS systems (e.g. Canvas, Open edX) who need to configure whether the mentor AI widget should be enabled or disabled for a specific course or context.

What the Settings Form Displays

  • A heading showing the Context ID (e.g. "Editing LMS Context Id: 110")
  • An Enabled checkbox to toggle whether the mentor widget is active for this context
  • A Mentor ID text input to specify which mentor to use
  • A Save button that submits the configuration via a POST request

How It Works

  1. The instructor sees a form pre-populated with the provided attribute values (enabled state, mentor ID).
  2. They can toggle the Enabled checkbox and/or change the Mentor ID.
  3. Clicking Save sends a POST request to:
    {lmsurl}/api/mentor-xblock/orgs/{tenant}/context/?context_id={contextid}
    with a JSON body:
    {
      "enabled": true,
      "mentor_id": "744a3672-0a59-4cc9-ad5a-03ada402a658"
    }
  4. On success (HTTP 200), a green "Settings saved successfully" message is displayed.
  5. On error, the component displays the error message from the response payload (e.g. {"error": "Mentor ID must be a valid UUID"}), or a generic "An unknown error occurred" message if no specific error is returned.

Required Attributes for Context Settings

| Attribute | Required | Description | | ----------------- | -------- | --------------------------------------------------------------------------- | | contextsettings | Yes | Boolean flag that enables the context settings view. | | contextid | Yes | The LMS context/course identifier displayed in the heading. | | lmsurl | Yes | Base URL of the LMS, used to construct the API endpoint. | | tenant | Yes | Platform/organization key, used in the API endpoint path. | | mentor | Yes | The initial Mentor UUID pre-filled in the Mentor ID input field. | | contextenabled | No | If present, the Enabled checkbox is initially checked. Otherwise unchecked. |

Context Settings Examples

Enabled context with a pre-filled mentor

<agent-ai
  contextsettings
  contextid="110"
  contextenabled
  lmsurl="https://learn.iblai.app"
  tenant="my-org"
  mentor="744a3672-0a59-4cc9-ad5a-03ada402a658"
></agent-ai>

This renders the form with the Enabled checkbox checked and the Mentor ID field pre-filled with the provided UUID.

Disabled context with no mentor

<agent-ai
  contextsettings
  contextid="205"
  lmsurl="https://learn.iblai.app"
  tenant="my-org"
  mentor=""
></agent-ai>

This renders the form with the Enabled checkbox unchecked and an empty Mentor ID field.

React usage

import React from "react";
import "@iblai/agent-ai";

const CourseSettings = ({ contextId, mentorId, isEnabled }) => {
  return (
    <agent-ai
      contextsettings
      contextid={contextId}
      {...(isEnabled ? { contextenabled: "" } : {})}
      lmsurl="https://learn.iblai.app"
      tenant="my-org"
      mentor={mentorId}
    ></agent-ai>
  );
};

Javascript Frameworks

React

Install the package:

npm install @iblai/agent-ai

Use the component

import React from "react";
import "@iblai/agent-ai";

const App = () => {
  return (
    <div>
      <agent-ai
        mentorurl="https://mentor.iblai.app"
        authurl="https://auth.iblai.app"
        lmsurl="https://learn.iblai.app"
        tenant="your-tenant"
        mentor="mentor-id"
        isanonymous
        iscontextaware
        isadvanced
        theme="light"
      ></agent-ai>
    </div>
  );
};

export default App;

Angular

Install the package:

npm install @iblai/agent-ai

Use the component in your template:

<agent-ai
  mentorurl="https://mentor.iblai.app"
  authurl="https://auth.iblai.app"
  lmsurl="https://learn.iblai.app"
  tenant="your-tenant"
  mentor="mentor-id"
  isanonymous
  iscontextaware
  isadvanced
  theme="light"
></agent-ai>

Add CUSTOM_ELEMENTS_SCHEMA in your module:

import { NgModule, CUSTOM_ELEMENTS_SCHEMA } from "@angular/core";

@NgModule({
  declarations: [AppComponent],
  imports: [BrowserModule],
  schemas: [CUSTOM_ELEMENTS_SCHEMA],
  bootstrap: [AppComponent],
})
export class AppModule {}

Vue

Install the package:

npm install @iblai/agent-ai

Use the component:

<template>
  <agent-ai
    mentorurl="https://mentor.iblai.app"
    authurl="https://auth.iblai.app"
    lmsurl="https://learn.iblai.app"
    tenant="your-tenant"
    mentor="mentor-id"
    isanonymous
    iscontextaware
    isadvanced
    theme="light"
  ></agent-ai>
</template>

<script>
export default {
  name: "App",
};
</script>

Context Sharing

This section describes the context sharing functionality implemented in the application, which allows for sharing HTML content between iframes and their parent windows.

Functions

  1. AgentAI.sendHTMLContentToHost(host: string, interval: number = 5000)

    This function is used when the application is running inside an iframe and needs to share the page content with the host. It creates a Web Worker to clean the HTML content before sending it to the host.

    • Parameters:

      • host: The target host to which the cleaned content will be sent.
      • interval: The time interval (in milliseconds) for checking and sending content (default is 5000 ms).
    • Usage:

      AgentAI.sendHTMLContentToHost("https://example.com", 5000);
  2. AgentAI.sendHTMLContentToIframe(iframeId: string, iframeHost: string, interval = 5000)

    This function allows the application to send HTML content to a specified iframe. It also utilizes a Web Worker for cleaning the content before sending it.

    • Parameters:

      • iframeId: The ID of the iframe element to which the content will be sent.
      • iframeHost: The host of the iframe.
      • interval: The time interval (in milliseconds) for checking and sending content (default is 5000 ms).
    • Usage:

      AgentAI.sendHTMLContentToIframe(
        "myIframe",
        "https://iframe-host.com",
        5000
      );
  3. AgentAI.proxyContextPostMessage(targetIdOrHost: string, host?: string)

    This function proxies post messages of type context either to an iframe or to the parent window, depending on the context in which it is called. It listens for incoming messages and forwards them accordingly.

    • Parameters:

      • targetIdOrHost: The ID of the target iframe or the host to which the message should be sent.
      • host: An optional parameter specifying the host to which the message will be sent.
    • Usage:

      AgentAI.proxyContextPostMessage("myIframe", "https://iframe-host.com");