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

@rmdylabs/rmdy

v0.6.1

Published

Verified runtime fixes for AI agents

Readme

RMDY CLI

RMDY turns real AI-agent failures into privacy-safe regression cases and verified runtime fixes. It remains compatible with the apatch/v0.1 package format and existing AP identifiers.

Alpha guarantees

  • scan performs redaction locally and never uploads the original trace.
  • Patch packages are declarative YAML plus JSON fixtures; the alpha runner does not execute arbitrary patch code.
  • AP-0042 and the AP-0051 tool-loop circuit breaker are bundled behavior patches.
  • install --runtime openai-agents generates a real OpenAI Agents SDK function-tool guardrail.
  • attest signs passing regression results with a local ECDSA P-256 validator key. The public registry independently replays supported declarative fixtures before marking a submission verified.
  • Everything runs on Node.js 22.13 or newer.

Install

Install the public CLI:

npm install --global @rmdylabs/rmdy
rmdy --version

Requires Node.js 22.13 or newer.

Try it

rmdy scan packages/apatch-cli/examples/failing-trace.json
rmdy test AP-0042
rmdy test AP-0051
rmdy attest AP-0051 --failure AP-F-XXXXXXXX
rmdy install AP-0042 --runtime openai-agents
rmdy install AP-0051 --runtime openai-agents
rmdy init my-first-patch --id AP-LOCAL-0001

scan writes a sanitized artifact to .apatch/cases. install writes verified patch packages to .apatch/patches and records versions in .apatch/installed.json. With --runtime openai-agents, it also generates .apatch/runtime/openai-agents.mjs; import applyAgentPatches() from that file and wrap the custom function tools passed to your Agent. Re-running install is safe and regenerates the adapter from all installed patches. attest writes a portable signed bundle while keeping the private validator key local. The older faultmesh and apatch executables remain compatibility aliases during the alpha.

Patch package

AP-0042/
├── patch.yaml
└── cases/
    └── regression.json

The v0.1 runtime supports declarative required-argument gates and repeated-tool-call circuit breakers. The registry never executes arbitrary submitted code: it validates the signature and safely replays these two declarative intervention types against the submitted JSON fixtures.

The legacy apatch executable remains an alias during the alpha compatibility window.