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

articlemind

v1.0.6

Published

AI-powered academic paper learning agent — analyze papers with Feynman, Simon, and First Principles methods

Readme


English · 中文 · 日本語 · Français · Deutsch


English

ArticleMind turns dense academic papers into deep understanding. It uses three proven learning methodologies, each embodied by an AI tutor persona:

| Method | Philosophy | Tutor Style | |--------|-----------|-------------| | Feynman | If you can't explain it simply, you don't understand it | Like Carl Sagan teaching the cosmos | | Simon | Break knowledge into chunks. Master each. Assemble. | Like a cartographer drawing your knowledge map | | First Principles | Question every assumption. Rebuild from axioms. | Like Socrates cross-examining an argument |

Highlights

  • Natural Language Interface — No rigid commands. Say 加载 paper.pdf 用费曼分析 and it just works. Supports Chinese + English mixed input.
  • Three Depth Levels — Basic (overview), Intermediate (method-level), Advanced (axiomatic reconstruction)
  • PDF & TXT — Drag in a file path, it auto-detects and loads. No clicking, no uploading.
  • Persistent Memory — Every analysis saved to ~/.articlemind/memory/ as structured Markdown. Your knowledge compound grows.
  • Multi-Provider — Works with Anthropic, DeepSeek, or any Anthropic-compatible API. Bring your own key.
  • Conversational — After analysis, chat with the tutor. Ask follow-ups. Challenge arguments. Go deeper.

Install

npm install -g articlemind

npm downloads

Quick Start

# 1. Configure your API key
cp .env.example .env
# Edit .env → set ARTICLEMIND_API_KEY=sk-your-key

# 2. Launch
articlemind

# 3. Talk naturally
加载 attention-is-all-you-need.pdf 用费曼分析

中文

ArticleMind 把晦涩的学术论文转化为真正的理解。内置三种经典学习框架,AI 导师实时引导。

| 方法 | 核心哲学 | 导师风格 | |------|---------|---------| | 费曼学习法 | 不能用大白话讲清楚就是没懂 | 像卡尔·萨根讲宇宙 | | 西蒙学习法 | 知识拆成块,逐块攻克,再组装 | 像画知识地图的制图师 | | 第一性原理 | 质疑所有假设,从公理重建 | 像苏格拉底式拷问 |

亮点

  • 自然语言交互 — 不记命令,说「加载 paper.pdf 用费曼分析」直接执行。中英混合输入无压力。
  • 三档深度 — 基础(概览)、中等(方法级)、进阶(公理化重建)
  • PDF/TXT 秒读 — 给个路径自动识别加载,无需点击上传
  • 持久记忆 — 每次分析存为 Markdown 到 ~/.articlemind/memory/,知识复利增长
  • 多提供商 — 支持 Anthropic、DeepSeek 及任意兼容 API,自带密钥
  • 对话模式 — 分析完继续追问、挑战论证、深挖细节

安装

npm install -g articlemind

快速开始

cp .env.example .env
# 编辑 .env → 填入 ARTICLEMIND_API_KEY=sk-你的密钥
articlemind
# 然后随便说:加载论文.pdf 费曼 进阶 分析

日本語

ArticleMindは難解な学術論文を深い理解へと変えます。実績ある3つの学習フレームワークをAIチューターがガイドします。

| メソッド | 哲学 | スタイル | |----------|------|----------| | ファインマン | 簡単に説明できなければ理解していない | カール・セーガンのように | | サイモン | 知識を塊に分解し、一つずつ習得 | 知識マップを描く地図製作者のように | | 第一原理 | 全ての仮定を疑い、公理から再構築 | ソクラテスのように |

特徴

  • 自然言語インターフェース — コマンド不要。中国語+英語の混在入力に対応
  • 3段階の深さ — 基礎・中級・上級(公理的分析)
  • PDF/TXT対応 — ファイルパスを入力するだけで自動読み込み
  • 永続メモリ — 分析結果をMarkdownで保存、知識が複利的に成長
  • マルチプロバイダー — Anthropic、DeepSeek、互換APIに対応
  • 対話モード — 分析後に質問、議論の挑戦、詳細な掘り下げが可能
npm install -g articlemind
cp .env.example .env
articlemind

Français

ArticleMind transforme des articles académiques denses en compréhension profonde. Trois méthodologies d'apprentissage éprouvées, guidées par un tuteur IA.

| Méthode | Philosophie | Style | |---------|-------------|-------| | Feynman | Si vous ne pouvez pas l'expliquer simplement, vous ne l'avez pas compris | Comme Carl Sagan expliquant le cosmos | | Simon | Décomposer le savoir en blocs, maîtriser chacun, assembler | Comme un cartographe dessinant votre carte de connaissances | | Premiers Principes | Questionner chaque hypothèse, reconstruire depuis les axiomes | Comme Socrate interrogeant un argument |

Points Forts

  • Interface en langage naturel — Pas de commandes rigides. Dites ce que vous voulez, il comprend.
  • Trois niveaux de profondeur — Vue d'ensemble, niveau méthode, reconstruction axiomatique
  • Lecture PDF/TXT — Donnez un chemin de fichier, il charge automatiquement
  • Mémoire persistante — Chaque analyse sauvegardée en Markdown
  • Multi-fournisseurs — Anthropic, DeepSeek, toute API compatible
  • Mode conversation — Continuez à questionner après l'analyse
npm install -g articlemind
cp .env.example .env
articlemind

Deutsch

ArticleMind verwandelt dichte akademische Arbeiten in tiefes Verständnis. Drei bewährte Lernmethoden, verkörpert durch KI-Tutoren.

| Methode | Philosophie | Stil | |---------|-------------|------| | Feynman | Wer es nicht einfach erklären kann, hat es nicht verstanden | Wie Carl Sagan den Kosmos erklärt | | Simon | Wissen in Blöcke zerlegen, jeden meistern, zusammensetzen | Wie ein Kartograf Ihrer Wissenslandkarte | | Erste Prinzipien | Jede Annahme hinterfragen, von Axiomen aus neu aufbauen | Wie Sokrates ein Argument prüft |

Highlights

  • Natürlichsprachliche Schnittstelle — Keine starren Befehle. Einfach sagen, was Sie wollen.
  • Drei Tiefenstufen — Überblick, Methodenebene, axiomatische Rekonstruktion
  • PDF/TXT-Unterstützung — Dateipfad eingeben, automatisch laden
  • Permanenter Speicher — Jede Analyse als Markdown gespeichert
  • Multi-Provider — Anthropic, DeepSeek, beliebige kompatible API
  • Dialogmodus — Nach der Analyse weiter fragen, Argumente hinterfragen
npm install -g articlemind
cp .env.example .env
articlemind

Configuration

Create .env from the template:

ARTICLEMIND_API_BASE_URL=https://api.deepseek.com/anthropic
ARTICLEMIND_API_KEY=sk-your-key-here
ARTICLEMIND_MODEL=DeepSeek-V4-pro
ARTICLEMIND_MEMORY_PATH=~/.articlemind/memory

Supported providers: Anthropic (native), DeepSeek (via Anthropic compatibility), or any endpoint that speaks the Anthropic Messages API.


License

MIT © ArticleMind Contributors