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

@zero-ar/sdk

v0.5.0

Published

Author agents and attach durable Zero-AR runs to applications.

Readme

@zero-ar/sdk

Attach durable Zero-AR work to an application and author the immutable resources that define an agent. The SDK gives an application one configured runtime handle, run handles that can be recreated by id, and builders for agents, tools, validators, postures, domain packs and orchestrations.

The SDK is a client surface. It needs an already-running Zero-AR endpoint and does not contain the kernel, database or model provider.

A recorded Zero-AR run showing the durable work that an SDK run handle addresses.

Install

Node.js 24.11.0 through the Node 24 LTS line is required.

npm install @zero-ar/sdk

First working example

Start one run, read its durable records and wait for its typed result.

import { createZeroAR } from '@zero-ar/sdk';

const zeroar = createZeroAR({
  endpoint: process.env.ZERO_AR_URL,
  apiKey: process.env.ZERO_AR_API_KEY,
});

const run = await zeroar.run({
  objective: 'Reconcile the supplier records and report what remains unverified.',
  items: ['supplier-001', 'supplier-002'],
});

console.log('run', run.id);

for await (const record of run.events()) {
  console.log(record.seq, record.type);
}

const result = await run.result();
console.log(result.verdict, result.not_established);

Another process can recreate the handle with zeroar.attach(run.id). The runtime owns the run and its history; the handle is a convenience over the public API.

Public surface

  • createZeroAR, ZeroAR and RunHandle for application integration.
  • Run control through steer, redirect, answer and cancel.
  • Durable result, event and verification-plan reads.
  • defineAgent, defineTool, defineValidator and definePosture builders.
  • Project loading, locking, scaffolding and publication helpers.
  • Domain-pack, orchestration and research-orchestration compilers.
  • Publication-bound memory handles.

Use the generated client directly when the application needs a route that the facade does not wrap.

What this does not establish

The SDK does not decide what correct means. A verified result requires the task contract's admitted validators or named people to pass. Creating a run does not grant model, tool or effect authority, and the SDK never places a provider credential in a manifest or model context.

Where to go next