New Tool for Converting Web Pages to Markdown
New Tool for Converting Web Pages to Markdown
The `.MD this page` extension allows for easy conversion of web pages into clean Markdown, removing unnecessary elements.
Copying web pages into LLMs doesn't have to include all the HTML code, ads, and interface elements. The .MD this page extension converts any page into clean Markdown with a single click, ready for submission to a language model.
The extension uses Mozilla Readability to automatically extract the main content of the page while discarding navigation, ads, and other extraneous content. Before exporting, the result can be previewed and edited if necessary, and then copied to the clipboard, saved as a Markdown file, or used as a basis for a prompt.
During export, you can also customize what goes into the final document: whether to keep or remove images, links, metadata, the URL of the original page, and the document structure map.
The project is distributed with open source code under the MIT license.
Why it matters
AnalysisThis tool simplifies the process of preparing web content for language models, which can significantly enhance the efficiency of developers and researchers in the field of artificial intelligence.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Part II. AI Agent Architecture: From Model to Memory and Tools
A deep engineering dive: tokenization, KV-cache, sampling determinism, the training stack, quantization, context engineering, the safety stack, production RAG, ReAct, and multi-agent swarm systems.
Guide: Image-to-Prompt Tools Overview
Image-to-prompt generation tools are neural networks that analyze visual inputs and generate detailed text descriptions closely resembling human-crafted prompts.
Dynamic Tool Selection
An architectural approach for building scalable AI agents equipped with hundreds of tools. Instead of loading all function descriptions into the context simultaneously, the system employs semantic search or a Router model for dynamic selection of only 3-5 most relevant tools for a specific user query.
Function Calling / Tool Calling
A technical protocol and standard for LLM interaction with external software. Instead of free text, the model returns valid JSON containing the function name and typed arguments according to JSON Schema, enabling the backend to deterministically execute actions in real APIs.