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

dr-debug

v0.1.17

Published

Autonomous In-Browser AI Debugging & Observability Agent

Readme

🩺 Dr. Debug (dr-debug)

Autonomous In-Browser AI Debugging & Observability Agent
Diagnoses client substrate crashes, network failures, memory leaks, and DOM anomalies directly within the browser runtime using Re-Act diagnostic loops.

npm version License: MIT TypeScript

Created by Saswat Mohanty (@SazWhatician)


⚡ Installation

Install via npm, pnpm, or yarn:

npm install dr-debug

Or run via CDN / HTML script tag:

<script type="module" src="https://unpkg.com/dr-debug/dist/standalone.js"></script>

🚀 Quick Start

1. In Any Modern JavaScript / TypeScript Project

import { DrDebug } from 'dr-debug'

// Initialize the autonomous debugging copilot
const doctor = new DrDebug({
  apiKey: process.env.GROQ_API_KEY || 'your-llm-api-key',
  model: 'openai/gpt-oss-120b', // or 'openai:gpt-4o', 'claude-3-5-sonnet', or local 'litert'
  enableUI: true,      // Renders the sleek Shadow DOM HUD & floating widget
  enableDocker: true,  // Connects with local Docker bridge for backend logs
  enableMCP: true      // Enables IDE live synchronization
})

// Trigger diagnostic investigations programmatically
await doctor.investigate('Investigate recent API failures on checkout')

2. Standalone In-Browser Drop-In (Zero Bundler Required)

Add this script to your index.html or entry template:

<script 
  type="module" 
  src="https://unpkg.com/dr-debug/dist/standalone.js"
  data-api-key="your-api-key"
  data-model="openai/gpt-oss-120b">
</script>

🔬 Core Capabilities

  • Deep Substrate Telemetry Interception: Monkeypatches and observes fetch, XMLHttpRequest, console.error, window.onerror, unhandled promise rejections, and Performance API metrics without leaking into application state.
  • Shadow DOM Diagnostic HUD: Complete glassmorphic DevTools panel rendered into a sealed Shadow Root to ensure zero CSS collisions with host websites.
  • Re-Act Autonomous Loop: Multi-turn reasoning agent that queries DOM trees, searches console logs, verifies network payloads, and generates concrete code diff solutions.
  • Docker Log Correlation: Streams backend container logs and correlates them with frontend network timeouts to pinpoint full-stack root causes.
  • MCP Protocol Bridge: Syncs tab telemetry with Cursor, VS Code, and Claude Code via Model Context Protocol.

🛠️ Configuration Options

| Option | Type | Default | Description | |:---|:---|:---|:---| | apiKey | string | undefined | LLM API key (Groq, OpenAI, Anthropic, or Gemini) | | model | string | 'openai/gpt-oss-120b' | Target model name or provider format | | enableUI | boolean | true | Show floating button and diagnostic modal | | enableDocker | boolean | false | Enable Docker container telemetry sync | | enableMCP | boolean | false | Enable Model Context Protocol websocket bridge | | mcpPort | number | 9999 | Port for local MCP daemon bridge |


📄 License

MIT © Saswat Mohanty