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 🙏

© 2025 – Pkg Stats / Ryan Hefner

llmint

v1.0.1

Published

typescript library to use LLMs for common non-AI website content quality evaluations using LLMs understanding of semantics

Downloads

8

Readme

LLMint - Web Quality Eval library

Note: This is WIP with limited functionality implemented

LLMint is an open-source TypeScript toolkit that brings quality assurance to modern websites using large language models. Validate content structure, tone of voice, SEO integrity, internal linking, and accessibility — all powered by prompt-based inspections and test container automation. LLMint helps you ensure your web experience is clear, consistent, inclusive, and aligned with user intent.

Based on the POC outlined in this blogpost

  • Tests are instantly readable as it uses prompts rather than html parsing
  • Library comes with standard uses cases to aid discovery over generic prompting
  • Focus is on providing developers and non-developers simple ways to perform subjective judgement on editorial content, structure, user journeys and persona intent and expectations

How to use

Library is test framework agnostic, it simply needs raw html string to perform the evals, using either local or hosted LLM

Examples

Setting up with with Docker Model Runner or Vercel AI SDK provider


// DMR:
cons llmint = new LLMint("ai/qwen3");

// openai:
import { createOpenAI } from "@ai-sdk/openai";
const openai = createOpenAI({
    apiKey: "...",
  });
const model = openai("gpt-4-turbo");
cons llmint = new LLMint(model);

llmint.editorial
        .toneOfVoice
        .evaluate({...})

Tone of voice:

    const ev = await llmint.editorial.toneOfVoice.evaluate({
      styleguide: "Write short and concisely",
      content: "<body>...</body>,
      expectation: `I expect this article to follow the styleguide provided and
                    be about how this body tag is completely empty`,
    });

Validate content for a given persona, intent and expectation

import LLMint from "llmint";
const llmint = new LLMint("ai/qwen3");

it("Blog posts should be listed with punchy headlines and sorted by date", async () => {
  const content = await fetchHelper({
    url: `site.com/blog`,
    selector: "article",
  });

  const ev = await llmint.persona.validateIntent.evaluate({
    persona: {
      name: "Community member",
      description: `You are an umbraco community member, with a developer
                      background, highly interested in community events
                      and eager to find out more about umbraco`,
    },

    intent: `I am browsing this page to find news about umbraco and its community
        I am only interested in click-baity and exciting news, if I see anything
        boring I will rage and quit the site`,

    expectation: `I expect blog posts to have interesting
        headlines and be sorted by date with the latest posts first`,

    content: content,
  });

  console.log(ev);
  expect(ev.result, ev.reason).toBe("good");
});

Test result data returned

Each evaluation returns a json object with the following structure:

  {
    result: good|medium|bad
    rating: 1-100
    reason: string (reason for the result)
    suggestions: Array<string> (suggestions for improvement)
    prompt: string (the full prompt sent to the model)
  }