MarkItDown is a Microsoft/AutoGen Python utility for converting PDF, Office, HTML, images, audio, and archives into Markdown for LLM pipelines.
Open Source: #microsoft
Catalog projects marked with #microsoft. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 12 projects with a combined 891,593 GitHub stars. Main languages: Python, Jupyter Notebook, C#.
Repositories
PowerToys is Microsoft’s collection of utilities for customizing Windows and speeding up everyday tasks.
Windows Terminal is Microsoft’s open terminal app for Windows command-line work, tabs, panes, profiles, settings, and the modern console host.
Web Dev For Beginners is Microsoft’s 24-lesson, 12-week curriculum for starting web development with HTML, CSS, and JavaScript.
ML For Beginners is Microsoft’s classic machine learning curriculum: 12 weeks, 26 lessons, quizzes, and practical assignments.
AI Agents for Beginners is a Microsoft course of 12 lessons for learning agents, RAG, tools, and multi-agent systems.
AutoGen is Microsoft’s Python framework for multi-agent AI applications; the project is now in maintenance mode.
PowerShell is a cross-platform shell, scripting language, and automation framework for structured data, APIs, and system objects.
Monaco Editor is the fully featured browser code editor from VS Code, with a playground, models, URIs, and multiple editor instances.
Data Science for Beginners is Microsoft’s beginner course for data science.
dotnet/core is the repository for .NET release notes, news, and lifecycle information.