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

@kmlckj/licos-dev-sdk

v0.2.14

Published

LICOS Dev SDK for server-side model capability calls

Readme

LICOS Dev SDK for Node.js

Server-side model capability clients for LICOS coding projects.

Do not import this package from browser/client code. It resolves the project owner's user token through the LICOS runtime identity and sends authenticated requests to platform APIs.

Install

npm install @kmlckj/licos-dev-sdk

The LICOS runtime provides platform identity and project owner context. Project code should not hard-code tokens, model base URLs, or provider keys.

For model selection, omit model or pass auto to use the first matching model from the platform model capability catalog. Pass a concrete model ID only when the user explicitly chooses one.

Chat

import { LLMClient } from '@kmlckj/licos-dev-sdk';

const client = new LLMClient();
const result = await client.invoke('Write a short product summary.');

console.log(result.text);

Image Generation

import { ImageGenerationClient } from '@kmlckj/licos-dev-sdk';

const result = await new ImageGenerationClient().generate('A clean blue sky over a modern city', {
  count: 1,
  size: '1024x1024',
});

console.log(result.urls);

Use imageUrl, image, or filePath when the task needs image-to-image generation from a reference image. Local files are encoded by the SDK before the request is sent.

const result = await new ImageGenerationClient().generate('Keep the object shape and change the background to a clean blue sky', {
  imageUrl: 'https://example.com/source.png',
  filePath: './assets/reference.png',
  count: 1,
});

console.log(result.urls);

Video Generation

import { VideoGenerationClient } from '@kmlckj/licos-dev-sdk';

const result = await new VideoGenerationClient().generate('A slow aerial shot over a futuristic harbor', {
  parameters: { duration: 5, ratio: '16:9' },
});

console.log(result.url);

Vision Understanding

import { VisionClient } from '@kmlckj/licos-dev-sdk';

const result = await new VisionClient().understand({
  imageUrl: 'https://example.com/image.png',
  prompt: 'Describe the image in one paragraph.',
});

console.log(result.text);

imageUrl can also be a data:image/...;base64,... URI, plain Base64 image data, or use filePath for a local image file.

Speech Recognition

import { SpeechRecognitionClient } from '@kmlckj/licos-dev-sdk';

const result = await new SpeechRecognitionClient().recognize({
  audioUrl: 'https://example.com/audio.mp3',
});

console.log(result.text);

audioUrl can also be a data:audio/...;base64,... URI, plain Base64 audio data, or use filePath for a local audio file.

Observability

import { logInfo, recordMetric, recordTrace } from '@kmlckj/licos-dev-sdk';

await logInfo('Application started');

await recordMetric({
  route: '/stream_run',
  method: 'POST',
  latencyMs: 320,
  statusCode: 200,
});

await recordTrace({
  traceId: 'trace-001',
  input: { query: 'hello' },
  output: { answer: 'hi' },
  latencySeconds: 1.2,
});