Microsoft
Organization@microsoft
Open source projects and samples from Microsoft
67
Published Tools
55,486
Total Stars
19,189,277
Weekly Downloads
114,473
GitHub Followers
7,654
Public Repos
100/100
Avg Security
Published Tools
11 MCP Servers47 Skills9 Agentsacross 9 categoriesOfficial Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
All Azure MCP tools to create a seamless connection between AI agents and Azure services.
Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
The Power BI Modeling MCP Server, brings Power BI semantic modeling capabilities to your AI agents.
Official agent plugin providing skills and MCP server configurations for Azure scenarios.
Lab for creating an MCP Server and using it in Microsoft Copilot Studio.
[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?
Gift your VS Code agent a real debugger: breakpoints, stepping, inspection.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Agent Framework Samples - showcasing ways in which agent framework can be utilized.
A comprehensive set of samples of creating and using MCP servers and clients with .NET
A multi-agent event planning workflow built with Microsoft Agent Framework - combining Semantic Kernel's enterprise orchestration with AutoGen's multi-agent patterns.
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
A professional prompt engineer who helps you optimize your GPT-prompts with state-of-the-art techniques
Microsoft Cognitive Services Speech SDK for Python
Azure Entra ID authentication extension for Python database drivers
Core package for scanning cloud resources across providers
Generic utilities for scanning cloud resources
The azdata NPM module provides Azure Data Studio extension authors tools to write extensions. It provides the azdata.d.ts node module (all accessible API for extensions) as well as commands for compiling and testing extensions.
Configuration and scripts for the baseline Azure IoT Create React App.
Redis support for the [refreshing-config](https://github.com/Microsoft/refreshing-config) configuration library.
The Power BI Modeling MCP Server, brings Power BI semantic modeling capabilities to your agents.
Provides Model Context Protocol (MCP) integration and tooling for Fabric in Visual Studio Code.
AI-powered Azure DevOps GitHub Copilot chat extension
VS Code extension: Learn Training AI Assistant
Build, deploy, and manage Azure applications with support from Copilot all without leaving VS Code.
A VS Code extension to bring speech-to-text and other voice capabilities to VS Code.
GitHub Copilot for Azure is the @azure extension. It's designed to help streamline the process of developing for Azure. You can ask @azure questions about Azure services or get help with tasks related to Azure and developing for Azure, all from within Visual Studio Code.
Enhanced development tools for C++ in VS Code
Upgrade Java project with GitHub Copilot
Upgrade and migrate your applications to Azure
Tooling to create Power Platform solutions & packages, manage Power Platform environments and edit Power Apps Portals
GitHub Copilot modernization for .NET is a public preview AI-powered experience that helps you bring your .NET applications to the latest version quicker and more confidently than ever before. Powered by GitHub Copilot and Agent Mode, it serves as an intelligent upgrade companion that understands yo
Gives access to search engines from within Copilot
Chinese (Simplified, China) language support for speech-to-text and other voice capabilities in VS Code.
AI Toolkit for VS Code streamlines generative AI app development by integrating tools and models. Browse and download public and custom models; author, test and evaluate prompts; fine-tune; and use them in your applications.
VS Code extension: Prompt flow for VS Code
This tool extends the LLM's capabilities by allowing it to run Python code in a sandboxed Python environment (Pyodide) for a wide range of computational tasks and data manipulations that it cannot perform directly.
A chat extension providing vision capabilities in VS Code, with a focus on accessibility.
Visual Studio Code extension for Azure Machine Learning
Visual Studio Code extension for Microsoft Foundry
IntelliCode Completions: AI-driven code auto-completion
This extension is used by the Azure Machine Learning Extension
Microsoft Fabric VS Code experience for Data engineering and Data science of Microsoft Fabric (Previously Synapse VS Code)
An extension pack for Python data scientists.
This extension is used by the Azure Machine Learning extension to enable debugging of local endpoints.
This extension enables remote connection to Azure Machine Learning compute instances in vscode.dev
Create and manage Microsoft Fabric notebooks inside Visual Studio Code for the Web (Previously Synapse VS Code - Remote)
Data viewing, cleaning and preparation for tabular datasets
This extension is now a part of Azure IoT Tools extension pack. We highly recommend installing Azure IoT Tools to get full capabilities for Azure IoT development. Interact with Azure IoT Hub, IoT Device Management, IoT Edge Management, IoT Hub Device Simulation, IoT Hub Code Generation and IoT Hub D
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more info
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is an instruct finetune of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). To read more about the model release, [click here](https://wizardlm.github.io/WizardLM2/). #moe