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

@littleee/devpilot

v0.2.0

Published

A page-native annotation toolbar for collecting UI feedback and exporting it for AI-assisted code changes.

Downloads

22

Readme

DevPilot

@littleee/devpilot is the published package for the DevPilot browser workflow.

Today, the package exposes DevPilot: a page-native toolbar for collecting UI feedback in the browser and exporting it as structured context for AI-assisted code changes.

Over time, DevPilot is intended to grow beyond annotation into MCP-powered code navigation, stability observation, and AI-assisted repair loops.

Install

npm install @littleee/devpilot

react and react-dom are required peer dependencies.

What You Get Today

  • floating in-page toolbar
  • element, text, and area annotations
  • structured task-packet export for AI coding workflows
  • optional Stability Copilot for runtime errors and failed requests
  • explicit repair request flow instead of automatic code modification
  • optional MCP sync when an endpoint is provided

Main Flow

The current local-first flow is intentionally simple:

Annotate -> Copy to AI -> Diagnose / Fix

You do not need MCP to get value from the package. In local mode, DevPilot can already:

  • record issues directly on the page
  • package page context into an AI-friendly task packet
  • support copy-and-paste handoff into Claude, Codex, Cursor, and similar tools

Zero-config Mount

import { mountDevPilot } from "@littleee/devpilot";

mountDevPilot();

Optional Mount Options

mountDevPilot({
  defaultOpen: false,
});

Feature Flags

DevPilot is designed as a composable product surface:

  • core annotation: enabled by default
  • stability copilot: opt-in
  • MCP sync: opt-in, or enabled when endpoint is provided
mountDevPilot({
  features: {
    stability: true,
    mcp: true,
  },
  endpoint: "http://127.0.0.1:4748",
});

If you want the stability module without remote sync:

mountDevPilot({
  features: {
    stability: true,
  },
});

When stability and mcp are both enabled, clicking the 修复 action in the stability panel creates an explicit repair request for AI agents. DevPilot does not automatically modify code after annotation.

Product Modes

@littleee/devpilot supports two practical modes:

  • Local mode
    • annotation and AI handoff only
    • no remote sync required
  • Connected mode
    • MCP-backed sync for collaborative or agent-driven workflows
    • optional runtime issue capture and repair-request flow

React

import { DevPilot } from "@littleee/devpilot";

export function App() {
  return (
    <>
      <YourApp />
      <DevPilot />
    </>
  );
}

Vue

import { createApp } from "vue";
import { mountDevPilot } from "@littleee/devpilot";
import App from "./App.vue";

createApp(App).mount("#app");
mountDevPilot();

Current Scope

@littleee/devpilot is meant to stay useful even before the full connected workflow is enabled:

  • Core: page annotation and AI handoff
  • Core + Stability: issue capture, observation, and explicit repair requests
  • Core + MCP: remote session sync for connected workflows
  • Core + Stability + MCP: collaborative repair loops with Claude / Cursor

DevPilot does not automatically modify code after annotation or observation. Repairs are created only when the user explicitly clicks 修复.