jatinkrmalik/LLMFeeder

Brower extension to convert web pages to clean Markdown and copy to clipboard so you can feed it to your favorite LLM model as context with just 1 click!

What it solves

LLMFeeder is a browser extension designed to simplify the process of feeding web content into Large Language Models (LLMs). It solves the problem of messy HTML, irrelevant page elements (like ads or navigation bars), and token limits by converting web pages into clean, structured Markdown format that is optimized for AI consumption.

How it works

The extension operates entirely on the client side. It uses Mozilla's Readability.js to identify and extract the main content of a page, and Turndown.js to convert that HTML into Markdown. Users can trigger the conversion via a popup UI, right-click context menus, or keyboard shortcuts. The resulting Markdown can be copied to the clipboard or downloaded as a .md file.

Who it’s for

Anyone who uses LLMs (such as ChatGPT, Claude, or Gemini) and frequently needs to provide web-based information as context for their prompts.

Highlights

  • Multi-Tab Support: Convert multiple selected tabs simultaneously and merge them into a single file or a ZIP archive.
  • Token Counter: Provides real-time token estimation based on GPT-4/Claude tokenizers to help users stay within context limits.
  • Lazy-Loading Auto-Scroll: Automatically scrolls through chat or AI pages to ensure long conversations are not truncated during extraction.
  • Privacy-First: Operates fully locally with zero remote data transmission, telemetry, or backend dependencies.
  • Customizable Metadata: Allows users to define their own citation styles using a template-based system for titles, URLs, and authors.
  • Smart Content Extraction: Offers options to extract only the main article content, the full page, or specific selected text.

Related

  • Project
    paulpierre/markdown-crawler

    A multithreaded web crawler that converts website pages into markdown files to simplify document parsing and chunking for RAG and LLM fine-tuning.

  • Project
    unclecode/crawl4ai

    An open-source web crawler and scraper that converts web pages into clean, LLM-ready Markdown for RAG, AI agents, and data pipelines.

  • Project
    AeternaLabsHQ/pullmd

    PullMD is a self‑hosted service that turns URLs, PDFs, Office files, images, audio, and YouTube videos into clean Markdown. It offers a PWA front‑end, a REST API, and an MCP endpoint for AI agents, with optional OCR, captioning, and transcription via OpenAI‑compatible models. Deploy with Docker Compose; configure authentication, SSRF protection, and front‑matter output to suit LLM pipelines.

  • Project
    drmingler/smart-llm-loader

    A Python package that converts documents and scanned images into clean, structured markdown chunks using OCR and LLM-powered semantic chunking for RAG systems.

  • Project
    0xMassi/webclaw

    A web extraction tool that converts websites into clean Markdown, JSON, and LLM-optimized context for AI agents and RAG pipelines.