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

laserbrain

v2.1.0

Published

A goal-alignment harness for AI agents — holds the goal your agent stated first, frozen where it cannot revise it, and checks every later step against it. No model, no network, no key.

Readme

laserbrain

A goal-alignment harness for AI agents. Your agent states its goal on the first step; that statement is frozen where the agent cannot revise it, and every later step is checked against it.

No model, no network, no key. A fixed algebraic structure computed locally in single-digit milliseconds — the same grammar the Python package and the hosted API read.

npm install laserbrain
import { Harness } from 'laserbrain'

const h = new Harness()
h.check('add a CSV importer to the admin panel', 'advancing', 8)   // grounded

const v = h.check('refactor the ORM base class', 'advancing', 5)
v.drifting   // true
v.reason     // 'goal-drift'
v.ground     // 'add a CSV importer to the admin panel'  ← the frozen goal, handed back

Sub-tasks

A legitimate sub-task reads as drift unless you declare its parent. This is the most common false positive:

h.check('validate CSV columns', 'advancing', 6)                    // goal-drift  (wrong)
h.check('validate CSV columns', 'advancing', 6, { parentGoal: G }) // excursion   (right)

The nine verdicts

grounded advancing reground excursion — carry on · stalled self-report — warn, then interrupt · goal-drift ungrammatical — stop · oscillating — reads the sequence rather than the step

Parity

This is not a re-implementation that behaves similarly. It is checked step-for-step against vectors generated from the Python package, which is the reference:

npm test    # 16 sequences, 276 field comparisons

If a field disagrees with Python, the test fails. Regenerate the vendored source with node vendor.mjs after any grammar change.

Where it does nothing

It measures execution, where the goal is fixed before the run starts. On exploration — figuring out what to build while building it — it will report drift continuously, correctly, and to no purpose.

Also available

  • Python: pip install laserbrain — adds the enforcement hooks and a stdio MCP server (laserbrain install), plus a tamper-evident audit chain.
  • Hosted MCP: https://laserbrain-mcp.degibug.workers.dev/mcp
  • Docs: https://phronesis.world/laserbrain

MIT.