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

@mdgate/ai

v0.6.26

Published

Optional AI helper for mdgate: ai({ baseURL, apiKey, model }).convertImage / convertAudio / convertVideo

Readme

@mdgate/ai

Optional multimodal callbacks for mdgate image, audio, and video conversion.

@mdgate/ai talks to an OpenAI-compatible chat/completions endpoint. There is no default provider. You pass baseURL, apiKey, and model.

Works in Node.js, Cloudflare Workers, Edge runtimes, and browsers.

npm install @mdgate/ai

Why @mdgate/ai

Raster images, audio, and video are not deterministic document formats. mdgate does not pick an OCR or speech vendor.

This package is a thin adapter so the model you already use can plug into @mdgate/image, @mdgate/audio, and @mdgate/video.

  • No default endpoint
  • No Python runtime
  • No native addons
  • No WASM runtime
  • The prompt is built in

SVG still converts locally in @mdgate/image. You do not need this package for SVG.


Usage

import { create } from '@mdgate/core';
import { ai } from '@mdgate/ai';
import { image } from '@mdgate/image';
import { audio } from '@mdgate/audio';
import { video } from '@mdgate/video';
import { pdf } from '@mdgate/pdf';

const media = ai({
  baseURL: 'https://api.example.com/v1',
  apiKey: process.env.API_KEY!,
  model: 'your-model',
});

const read = create([
  pdf(),
  image(media.convertImage),
  audio(media.convertAudio),
  video(media.convertVideo),
]);

baseURL is the OpenAI-compatible API root (the same value the OpenAI SDK uses). Requests go to {baseURL}/chat/completions.

Audio and video are sent as data URLs.

These callbacks are not registered by all(). Compose them yourself.


What it covers

Raster images: JPEG, PNG, WebP, GIF, TIFF, HEIC, BMP.

Audio: MP3, WAV, M4A, AAC, Ogg, FLAC, WebM audio.

Video: MP4, MOV, WebM, Matroska, AVI.

You can also call the helpers directly:

await media.convertImage({ bytes, mime: 'image/png' });
await media.convertAudio({ bytes, mime: 'audio/mpeg' });
await media.convertVideo({ bytes, mime: 'video/mp4' });

Need a complete reader?

npm install @mdgate/converters

Then add image(), audio(), and video() on top of all().

@mdgate/ai is part of the open-source mdgate/converters project.

For AI agents, the same converter architecture can be used to extend read_file from text files to real-world document formats.


License

MIT