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

prometey-ai-sdk

v0.1.0

Published

Prometey provider for the Vercel AI SDK: run generateText, streamText and friends on your users' own AI (free tiers and their keys) through Prometey's auto router.

Readme

prometey-ai-sdk

Prometey for the Vercel AI SDK. Your app's generateText (structured output included), streamText and embed calls run on your users' own AI (their free tiers and API keys), picked per request by Prometey's auto router.

npm install prometey-ai-sdk ai
import { createPrometey } from 'prometey-ai-sdk';
import { generateText, streamText } from 'ai';

const prometey = createPrometey({ baseURL: 'https://YOUR-PROMETEY-HOST', apiKey: userToken });

const { text } = await generateText({ model: prometey('auto'), prompt: 'Write a haiku about Mondays' });

const result = streamText({ model: prometey('auto:fast'), prompt: 'Tell me a joke' });
for await (const piece of result.textStream) process.stdout.write(piece);

The user's token

apiKey accepts:

  • a string: a user's token from "Connect Prometey", or an API key from your Prometey dashboard for your own scripts;
  • a function (sync or async), called before each request: handy when tokens live in a session store;
  • a connected Prometey client from prometey-sdk in the browser:
import { Prometey } from 'prometey-sdk';
const client = new Prometey({ baseUrl: 'https://YOUR-PROMETEY-HOST' });
await client.ready(); // after the user connected
const prometey = createPrometey({ baseURL: client.baseUrl, apiKey: client });

Without a token, calls fail with PrometeyNotConnectedError before reaching the network.

Models

| Model | Picks | |---|---| | auto | The best model for each request among the user's providers | | auto:fast / auto:best | Leaning towards speed / quality | | auto:cascade | A fast model first, a stronger one if the answer looks weak | | auto:<task> (e.g. auto:code:generation) | The best model for that task | | provider/model | That exact model |

prometey.embeddingModel('nemotron-3-embed-1b') and prometey.imageModel('auto') work too.

What your features need

const prometey = createPrometey({ baseURL, apiKey, requires: { vision: true, json: true, quality: 'best' } });

Prometey then only routes to models that can do it (vision, tools, json, min_context, quality).

Who answered

const r = await generateText({ model: prometey('auto'), prompt: 'Hi' });
r.providerMetadata?.prometey; // { provider: 'groq', model: 'openai/gpt-oss-120b', requestId: '…' }

MIT licensed.