GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — Build software better, together

#

defuddle

Star

Here are 24 public repositories matching this topic...

Language: All
Filter by language
All 24 TypeScript 10 JavaScript 5 Python 3 Go 2 PHP 1 Shell 1
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated
obsidian-skills

obsidianmd / obsidian-skills

Star 51.8k

Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.

markdown cli skills opencode hermes obsidian agents bases md codex claude knap jsoncanvas defuddle agentskills clawdbot openclaw
  • Updated Nov 11, 2026
  • Shell

kepano / defuddle

Sponsor
Star 10k

Get the main content of any page as Markdown.

html markdown cli readability obsidian md defuddle
  • Updated Oct 25, 2026
  • TypeScript

kepano / defuddle-cli

Sponsor
Star 506

Moved to the main defuddle repo. Command line utility to extract clean html, markdown and metadata from web pages.

html markdown extraction md defuddle
  • Updated Mar 2, 2026
  • JavaScript

joematthews / pi-smart-web-search

Star 24

Web search tool for the pi coding agent — batch queries, ranked readable markdown results ready to fetch. Pairs with pi-smart-fetch.

search typescript pi web-scraping content-extraction ai-agents web-search agentic llm-tools defuddle pi-coding-agent pi-extension pi-package wreq-js
  • Updated Oct 22, 2026
  • TypeScript

artemnistuley / docrawl

Star 7

Lightweight CLI for crawling documentation sites into Markdown with defuddle

html markdown cli crawler md defuddle
  • Updated Jun 27, 2026
  • TypeScript

dotcommander / defuddle

Star 6

Go library and CLI for extracting web page content — articles, metadata, and clean text from any URL

go markdown cli web-scraping html-parser content-extraction defuddle
  • Updated Oct 31, 2026
  • Go

wizzy15 / obsidian-skill

Star 5

📝 Manage and organize Obsidian vaults with CLI tools for notes, tasks, tags, templates, and knowledge graph analysis.

automation typescript ai note-taking pkm codex bun task-management zettelkasten obsidian-vault ai-agent defuddle claude-code-plugin claude-skills claude-agent clawdbot
  • Updated Oct 12, 2026

alexwkleung / web-search-skill

Sponsor
Star 3

Web search (Brave) and page reading (defuddle) skill for coding agents through Chrome CDP

nodejs shell skills opencode python3 cdp web-search chrome-devtools-protocol brave-search local-llm agent-skills claude-code defuddle coding-agent pi-coding-agent
  • Updated Oct 24, 2026
  • Python

MichaelvanLaar / n8n-nodes-defuddle

Star 2

n8n community node for extracting main content from webpages using Defuddle library

web-scraping readability content-extraction n8n n8n-community-node-package defuddle
  • Updated Oct 11, 2026
  • TypeScript

sonic0002 / defuddle-js

Star 1

A JS version of defuddle

nodejs javascript readability defuddle
  • Updated Mar 26, 2026
  • JavaScript

michalschroeder / page2md

Star 1

Render any URL with headless Chromium and extract clean Markdown.

docker markdown cli ai web-scraping playwright llm defuddle
  • Updated Nov 11, 2026
  • TypeScript

sonic0002 / defuddle-php

Star 1

PHP version of defuddle(https://github.com/kepano/defuddle)

php readability defuddle
  • Updated Mar 25, 2026
  • PHP

Jimytimyzimy / obsidian-headless

Star 1

Sync Obsidian vaults from the command line using a headless client, enabling automated and continuous sync without the desktop app.

react chrome-extension testing api chrome automation vue opencode codex claude neovim-lua headless-browser nvim-cmp aiagent defuddle
  • Updated Oct 13, 2026

suheilOS / readr

Star 0

A focused reading queue for articles, papers, books, podcasts, and videos.

typescript cloudflare defuddle
  • Updated Sep 19, 2026
  • TypeScript

harrywang / zotero-attachments-markdown

Star 0

Zotero plugin: convert web snapshots, EPUBs and Word documents into clean Markdown with front matter, images and footnotes

markdown epub docx zotero obsidian zotero-plugin defuddle
  • Updated Oct 10, 2026
  • JavaScript

caidewu / web-clip-cli

Star 0

一键将网页保存为 Obsidian 兼容的 Markdown 文件,支持 obsidian-clipper 模板。

nodejs markdown obsidian knowledge-management article-extractor web-clipper zettelkasten second-brain content-extractor defuddle obsidian-clipper
  • Updated Jun 8, 2026
  • TypeScript

3stelth / agentic-web-clipper

Star 0

Web clipper agentico per Obsidian: estrazione deterministica (Chrome headless + Defuddle) + recupero contenuti via agente LLM. Output Markdown pulito, pronto per vault e ingestione LLM.

markdown obsidian web-clipper puppeteer llm claude-code defuddle
  • Updated Jul 10, 2026
  • JavaScript

fbsfyl / cortico-world-web-pro

Star 0

联网 Pro:给 Coopanion / Cortico 桌宠的多源联网搜索与正文阅读扩展。AnySearch 主力,Bing/搜狗/360 兜底,Defuddle 提取正文。

desktop-pet web-search defuddle cortico coopanion
  • Updated Oct 23, 2026
  • TypeScript

jdmonaco / mdclip

Star 0

CLI tool to clip web pages and extract the content to Markdown with YAML frontmatter.

markdown cli obsidian frontmatter webclip obsidian-md mdformat defuddle
  • Updated Sep 19, 2026
  • Python

jimmieego / url2epub

Star 0

Python CLI for turning web articles into EPUBs with Defuddle extraction, Pandoc generation, embedded images, and WeChat support.

python cli pandoc epub defuddle
  • Updated Sep 20, 2026
  • Python

Add this topic to your repo

To associate your repository with the defuddle topic, visit your repo's landing page and select "manage topics."

Learn more

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.