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

@hoshinorin/rin

v0.5.0

Published

[English](README.md) · [简体中文](readme/README.zh-CN.md) · [日本語](readme/README.ja.md) · [Español](readme/README.es.md) · [Français](readme/README.fr.md) · [More languages](readme/README.md)

Readme

English · 简体中文 · 日本語 · Español · Français · More languages

Rin

Your personal AI assistant, living on your computer. Rin remembers what matters, helps with real tasks, and gets better as you use it.

Rin is a local, general-purpose AI assistant with memory, tools, scheduling, UI entry points, and chat bridges built in. It can help with documents, web research, files, reminders, code, connected services, and repeated workflows — while sharing one assistant state across terminal, desktop, automation, and chat.

| What matters | What Rin provides | | ------------------------ | ------------------------------------------------------------------------------------- | | Global memory | Useful facts, preferences, and lessons can survive beyond a single chat session. | | Learns from repeated use | Corrections and successful workflows can become compact instructions and skills. | | Local background runtime | Different interfaces connect to one assistant instead of isolated chat windows. | | Ready-to-use product | Memory, scheduling, tools, chat bridges, and UI paths are provided out of the box. | | Self-bootstrapped | Rin is used to build Rin, making this repository a live test of the assistant itself. |

[!WARNING] Rin is still young. Treat everyday use as experimental: you may meet rough edges, missing documentation, unstable behavior, token/API cost, or occasional breaking changes.

Support Rin

If Rin saves you time, you can support its maintenance on Ko-fi. Sponsorship is voluntary and supports ongoing maintenance costs; it does not buy feature priority or private support commitments.

Installation

[!TIP] Most users should start with the stable install command below. Use the install commands directly; the installer sets up the rin command. Pre-release and git channels are available in the folded sections.

Rin requires Node.js 22.19.0 or newer and npm on every platform.

Linux and macOS

curl -fsSL https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.sh | sh
curl -fsSL https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.sh | sh -s -- --beta
curl -fsSL https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.sh | sh -s -- --nightly
curl -fsSL https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.sh | sh -s -- --git
curl -fsSL https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.sh | sh -s -- --git main
curl -fsSL https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.sh | sh -s -- --git deadbeef

Windows

Install from PowerShell or Windows Terminal.

& ([scriptblock]::Create((irm https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.ps1)))
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.ps1))) --beta
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.ps1))) --nightly
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.ps1))) --git
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.ps1))) --git main
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/rinchan-hoshino/rin/bootstrap/install.ps1))) --git deadbeef

After installation, use the same command on every platform:

rin

The Windows installer writes the rin command launcher and adds Rin's user launcher directory to the user PATH when possible. Open a new terminal if the current shell does not see rin immediately. The GUI entry points are temporarily disabled while the desktop UI is being redesigned.

Safety and cost

Rin can keep context, write memory, run scheduled work, browse the web, and call models repeatedly. This may consume more model tokens, API quota, or subscription capacity than a one-off chat.

Use supervision for important actions. Do not let Rin perform irreversible or sensitive work unless you understand the risk and can review or roll back the result.

Technical direction

Rin is built on Pi and keeps Pi's KISS-first spirit:

  • keep the core small and understandable
  • show the model the real tools and context
  • let the model decide when that is the simplest reliable design
  • avoid model-specific tricks and over-tuned prompts
  • prefer transparent local state over remote platform lock-in

Rin is not trying to be a heavy agent framework. It is trying to be a practical everyday assistant that can remember, act, and improve while staying inspectable.

Documentation

This README is the public user overview. Translations live in readme/README.*.md and should stay aligned with this English version.

If you are changing Rin itself, start with docs/developer/README.md. Agent-facing runtime guidance and installed docs are kept separately from this public README.