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

@mograblog/web-agent-loop

v0.1.1

Published

Fully functional frontend-only AI agent loop with zero backend. Supports MCP tools, local WebGPU, and Bring-Your-Own-Key.

Readme

@mograblog/web-agent-loop

A fully functional, frontend-only AI agent loop with zero backend. Run autonomous AI agents entirely in the browser with local WebGPU models, Bring-Your-Own-Key cloud LLMs, and Model Context Protocol (MCP) tools.

npm version License: MIT


Features

  • 🌐 Frontend-Only: Runs 100% in the user's browser. Zero backend servers or proxy relays required.
  • ⚡ WebGPU & Cloud LLMs: Run local open-weight models (Llama 3, Qwen, DeepSeek, Phi) on-device via WebLLM / WebGPU, or connect directly to OpenAI / Ollama.
  • 🔌 Model Context Protocol (MCP): Discover and execute tools over HTTP/SSE, including Arcade.dev connectors, built-in sample tools, or custom endpoints.
  • 💻 Localhost Coding Bridge: Optional local companion CLI (npx web-agent-bridge) that securely exposes file editing and terminal command execution to the browser agent.
  • 📦 Dual Artifacts:
    • . Core headless TypeScript SDK
    • ./demo Drop-in Custom Element <web-agent-demo>
    • ./react React component wrapper with full JSX typings

Installation

npm install @mograblog/web-agent-loop

Quickstart

1. Headless TypeScript SDK

import { WebAgentLoop, createWebSearchTool } from '@mograblog/web-agent-loop';

const agent = new WebAgentLoop({
  provider: {
    type: 'openai',
    apiKey: 'YOUR_API_KEY',
    model: 'gpt-4o-mini'
  },
  systemPrompt: 'You are a helpful research assistant with access to web search.',
  tools: [createWebSearchTool()]
});

const result = await agent.run('What are the latest developments in WebGPU?');
console.log(result.response);

2. Drop-in Web Component Demo

Embed the full interactive playground anywhere with zero build configuration:

<script type="module">
  import '@mograblog/web-agent-loop/demo';
</script>

<web-agent-demo 
  title="AI Agent Playground" 
  theme="dark" 
  default-tab="sample">
</web-agent-demo>

3. React Component

import React from 'react';
import { WebAgentDemo } from '@mograblog/web-agent-loop/react';

export function AgentPlayground() {
  return (
    <div className="h-screen w-full">
      <WebAgentDemo theme="dark" defaultTab="bridge" />
    </div>
  );
}

4. Localhost Coding Bridge

Let the browser agent edit files and run terminal commands on your computer:

npx web-agent-bridge --dir ./my-project --port 3001

License

MIT © Guy Mograbi