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

@manya-hael/cortex

v1.0.0

Published

A reasoning fabric that routes tasks to the tools that already own them, gates dispatch through access control, and chains every decision into an auditable trail — composed from memory, unify, shield, and stamp.

Downloads

142

Readme

@manya/cortex

A reasoning fabric, not another agent.

Cortex doesn't answer questions itself. It decides who should — by asking @manya/unify's mesh which already-registered tool owns the capability a task needs, gating dispatch through @manya/shield, remembering every decision through @manya/memory, and chaining every decision into its own tamper-evident trail with @manya/stamp.

Usage

import { memory } from '@manya/memory';
import { unify } from '@manya/unify';
import { cortex } from '@manya/cortex';

// Tools register themselves with the mesh as they come online.
unify.registerTool({
  manifest: { id: 'forge', owns: ['keyDerivation'] },
  api: { deriveKey: (passphrase) => derive(passphrase) },
});

const store = memory.createMemoryStore('ara');
const brain = cortex.createCortex(store);

// Let atlas provision devices.
cortex.authorize(brain, 'atlas', 'operator', [
  { resource: 'device:*', actions: ['provision'] },
]);

const result = cortex.plan(brain, 'derive a key for the new device', {
  capability: 'keyDerivation',
  requesterId: 'atlas',
  resource: 'device:phone-1',
  action: 'provision',
});
// { intent: 'execution', owner: 'forge', authorized: true, confidence: 0.8, ... }

if (result.authorized) {
  cortex.dispatchPlan(brain, result, 'keyDerivation', 'deriveKey', ['a passphrase']);
}

Why this composition

  • "Who should solve this?" is answered by unify.route/unify.dispatch against the mesh's existing capability registry — Cortex doesn't keep a second list of who-does-what.
  • "What confidence do we have?" blends whether a capability is actually registered right now, whether the requester is authorized, and whether memory already has relevant episodes — not a guess.
  • Every decision is remembered twice, for different reasons: once in the bound memory store's episodic log (so other reasoning can recall why a plan was made), and once in Cortex's own stamp-chained decision trail (so the planning process itself can be audited independent of memory).
  • Dispatch never bypasses authorization, even if a caller forgets to check plan.authorizeddispatchPlan refuses on its own.