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

muffinscorp

v1.0.2

Published

Node.js client library for Muffins Corp AI API

Readme

Muffins Corp. JavaScript Client Library

Uma biblioteca cliente Node.js para interagir com a API de Inteligência Artificial da Muffins Corp (Muffins AI).

Instalação

npm install muffinscorp

Uso Básico

const { MuffinsCorp } = require("muffinscorp");

// Inicialização com API key
// A API key é opcional: pode ser fornecida manualmente ou deixada em branco para que a biblioteca busque automaticamente pela variável de ambiente MUFFINS_AI_API_KEY.
const muffinsai = new MuffinsCorp({
  apiKey: "sua-api-key", // Opcional
  // Opcional: URL base customizada
  // baseURL: 'https://custom-api-endpoint.com'
});

// Exemplo: Listar modelos
async function getModels() {
  const models = await muffinsai.models.list();
  console.log(models);
}

// Exemplo: Completar chat
async function createChatCompletion() {
  const completion = await muffinsai.chat.create({
    messages: [
      { role: "system", content: "Você é um assistente útil." },
      { role: "user", content: "Olá, mundo!" },
    ],
    model: "chat-model-small",
    stream: false, // Definir como true para respostas em stream
  });

  console.log(completion);
}

// Exemplo: Ver saldo de créditos
async function getCredits() {
  const balance = await muffinsai.credits.getBalance();
  console.log(balance);
}

Referência da API

Configuração

Opções ao inicializar MuffinsCorp:

  • apiKey (opcional): Sua chave da API MuffinsCorp ou Muffins AI. Caso não seja fornecida, a biblioteca buscará automaticamente pela variável de ambiente MUFFINS_AI_API_KEY.
  • baseURL (opcional): Endpoint customizado.

Principais Métodos

Chat:

  • muffinsai.chat.create(options) - Cria completação de chat.

    • messages: Array de mensagens com role e content.
    • model: Modelo a usar (default: "chat-model-small").
    • stream: Habilitar streaming (default: true).

Models:

  • muffinsai.models.list() - Lista modelos disponíveis.

Credits:

  • muffinsai.credits.getBalance() - Retorna saldo de créditos.

Tratamento de Erros

try {
  await muffinsai.chat.create({
    messages: [{ role: "user", content: "Hello" }],
  });
} catch (error) {
  console.error("Erro na API:", error.message);
}

Streaming

Para respostas em streaming:

const stream = await muffinsai.chat.create({
  messages: [{ role: "user", content: "Conte uma história" }],
  stream: true,
});

// Processar o stream conforme necessário