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

ez-reads

v1.0.0

Published

Turn any research paper into a beautiful static website

Downloads

85

Readme

ez-reads

Turn any research paper into a beautiful, interactive static website.

Paste an ArXiv URL or DOI, and ez-reads will fetch the paper, distill it into structured sections using an LLM, and generate a polished React site — complete with an AI chat assistant that can answer questions about the paper.

Features

  • Automatic distillation — Extracts key contributions, methodology, results, stats, significance, limitations, glossary, and more
  • Beautiful sites — React + Tailwind sites with scroll animations, color themes, and responsive design
  • AI chat assistant — Each generated site includes a chat widget powered by Groq so visitors can ask questions about the paper
  • Paper library — An auto-generated index page lists all your papers with search
  • ArXiv + DOI support — Works with ArXiv URLs and DOIs from any publisher
  • Figure extraction — Automatically downloads and displays paper figures

Requirements

Install

npm install -g ez-reads

Or run it directly without installing:

npx ez-reads

Usage

ez-reads

On first run, you'll be prompted for your Groq API key. The key powers both:

  1. Paper distillation — extracting structured data from the paper via LLM
  2. Chat assistant — the interactive Q&A widget on each generated site

Model used: qwen/qwen3-32b (available on Groq's free tier)

Skip the prompt

Set your key in the environment to skip the interactive prompt:

export GROQ_API_KEY=gsk_your_key_here
ez-reads

Or create a .env file in the directory where you save the key:

GROQ_API_KEY=gsk_your_key_here

How it works

📄 paper → 🔬 distill → ✨ generate → 🌐 site
  1. Fetch — Scrapes the paper content from ArXiv or resolves a DOI
  2. Distill — Sends the paper through 5-6 LLM calls to extract structured JSON (title, abstract, methodology, results, stats, glossary, etc.)
  3. Generate — Builds a React + Tailwind static site and serves it locally

Output goes to ./ez-reads-output/ in your current directory.

Commands

| Command | Description | |---|---| | ez-reads or paper-site | Start the interactive CLI | | npm run rebuild | Rebuild all existing sites (after template changes) |

Generated site structure

ez-reads-output/
├── index.html          # Library page (lists all papers)
└── <paper-slug>/
    ├── index.html      # Paper site
    ├── assets/         # JS/CSS bundles
    ├── figures/        # Downloaded figures
    ├── meta.json       # Metadata for library index
    └── data.json       # Full distilled data (for rebuilds)

Chat assistant

Every generated site includes a floating chat button in the bottom-right corner. Visitors can ask questions about the paper and get answers powered by the same Groq API key used during generation.

Note: Your Groq API key is embedded in the generated site's JavaScript bundle to power the chat assistant. This is fine for local use or private hosting. If you plan to host generated sites publicly, be aware that the key is visible in the page source.

License

MIT