Microsoft Open Source Projects
Microsoft-related open source software spans tools, libraries, and frameworks for building, debugging, and operating applications across Microsoft technologies and platforms. These projects can help developers work with .NET and C#, automate workflows, connect software to cloud services, and add capabilities such as AI or data processing. Open development also makes source code available for inspection, adaptation, and community contributions.
This area includes developer tools, language libraries, cloud integrations, AI frameworks, and utilities for Windows and cross-platform environments. When choosing a tool, check its license, maintenance activity, documentation, supported runtimes, security practices, and compatibility with your existing stack. These resources are useful to individual developers, teams, and organizations maintaining Microsoft-based systems or exploring open source options for their software workflows.
5 repositories · updated September 11, 2026
Skill Recorder: Turn Screen Recordings into AI Agent Skills
Skill Recorder is a desktop application that captures your on-screen work sessions, including clicks and app switches. It leverages the GitHub Copilot CLI to analyze these recordings, reconstructing them into an intent and ordered steps. This process allows users to generate reusable AI agent skills or automations for platforms like Microsoft Scout, Copilot Cowork, or Copilot Studio.
AutoGen: A Programming Framework for Agentic AI
AutoGen is a versatile programming framework from Microsoft designed for building multi-agent AI applications. It empowers AI agents to operate autonomously or collaborate seamlessly with human users, streamlining the execution of complex tasks. The framework offers a layered, extensible design, providing both high-level APIs for rapid prototyping and low-level components for fine-grained control.
KBLaM: Knowledge Base Augmented Language Models for Enhanced LLMs
KBLaM, developed by Microsoft, is the official implementation of "Knowledge Base Augmented Language Models" presented at ICLR 2025. This innovative method enhances Large Language Models by directly integrating external knowledge bases, offering an efficient alternative to traditional Retrieval-Augmented Generation (RAG) and in-context learning. It eliminates external retrieval modules and scales computationally linearly with knowledge base size, rather than quadratically.
OmniParser: A Vision-Based Tool for GUI Agent Screen Parsing
OmniParser is a comprehensive tool developed by Microsoft for parsing user interface screenshots into structured, understandable elements. It significantly enhances the ability of vision-based models, such as GPT-4V, to generate accurate actions grounded in specific regions of a GUI. This project aims to advance pure vision-based GUI agents by providing robust screen parsing capabilities.
debugpy: An Advanced Debugger for Python Development
debugpy is Microsoft's robust implementation of the Debug Adapter Protocol (DAP) for Python 3. It provides powerful debugging capabilities, allowing developers to efficiently inspect and troubleshoot their Python applications. This tool supports both command-line and API-based usage, offering flexibility for various development workflows.