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

@purecore/one-llm-4-all

v2.1.0

Published

Unified Fluent Interface for OpenAI, Groq, OpenRouter, Claude, Gemini, DeepSeek and Mistral. Native implementation, zero bloating.

Readme

one-llm-4-all

Interface unificada e Fluent para OpenAI, Groq, OpenRouter, Claude (Anthropic) e Gemini.

Uso

import { sendPrompt } from 'one-llm-4-all';

// Texto
const txt = await sendPrompt('Explique LLMs em uma frase.', {
  model: 'llama-3.1-8b-instant',
  provider: 'groq',
  apiKey: process.env.GROQ_API_KEY,
}).getText();

// JSON (response_format json_object no provider)
const obj = await sendPrompt('Retorne apenas um JSON: { "ok": true }', {
  model: 'llama-3.1-8b-instant',
  provider: 'groq',
  apiKey: process.env.GROQ_API_KEY,
}).getJSONResponse();

Interface unificada

UnifiedLLMParams: propriedades que valem para qualquer LLM.

| Obrigatórias | Opcionais (com default) | |--------------|-------------------------| | messages (string ou LLMMessage[]) | max_tokens = 1024 | | model | temperature = 0.7 | | | top_p = 1 | | | stream = false | | | stop, system, response_format, seed | | | provider, apiKey |

Padrão encadeável

sendPrompt(...).getText() e .getJSONResponse() usam:

  • Fluent Interface (API fluente): métodos que retornam o “próximo passo” para encadear.
  • Builder Pattern: montagem em etapas; .getText() e .getJSONResponse() são os métodos que executam a requisição.

Provedores

  • openai (OpenAI)
  • groq (Groq)
  • openrouter (OpenRouter)
  • anthropic (Claude)
  • gemini (Google Gemini)

API keys: GROQ_API_KEY, OPENROUTER_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY (ou apiKey nas opções).

Testes de Rotação Real

Recentemente adicionamos um sistema de testes de integração real que rotaciona modelos a cada 1 minuto. Isso é ideal para validar a estabilidade de múltiplos endpoints.

Como foi feito

O script scripts/real_rotation_test.ts utiliza a interface fluente da biblioteca para percorrer o free_models.json, enviando um prompt de teste para cada modelo com um intervalo de 60 segundos.

Como funciona

  1. Carrega os modelos suportados.
  2. Itera sequencialmente.
  3. Registra logs detalhados em rotation_results.log.

Como testar

bun run test:real-rotation

Para saber mais sobre as mudanças recentes, veja o CHANGELOG.md.