DeepSpeed, ONNX, Phi, Semantic Kernel, Guidance
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.
A programming framework for agentic AI
A modular graph-based Retrieval-Augmented Generation (RAG) system
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
Official inference framework for 1-bit LLMs
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
End-to-end Generative Optimization for AI Agents
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Secure AI conversations with documents, video, audio, and more. Personal workspaces for focused context, group spaces for shared insight. Classify docs, reuse prompts, and extend with modular features.
A large-scale simulation framework for LLM inference
Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents
Curated lessons on getting started building agents with Copilot Studio
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report
Five lessons, learn how to really apply AI to your .NET Applications
MCP Gateway is a reverse proxy and management layer for MCP servers, enabling scalable, session-aware stateful routing and lifecycle management of MCP servers in Kubernetes environments.
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.
This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimization, and the development of intelligent Edge AI agents.
The Power BI Modeling MCP Server, brings Power BI semantic modeling capabilities to your AI agents.
12 Lessons to Get Started Building AI Agents
The Microsoft 365 Agent SDK simplifies building full stack, multichannel, trusted agents for platforms including M365, Teams, Copilot Studio, and Webchat.
Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
A library for helping developers craft prompts for Large Language Models
12 Weeks, 24 Lessons, AI for All!
Azure MLOps (v2) solution accelerators. Enterprise ready templates to deploy your machine learning models on the Azure Platform.
FarmVibes.AI: Multi-Modal GeoSpatial ML Models for Agriculture and Sustainability
The absolute trainer to light up AI agents.
General technology for enabling AI capabilities w/ LLMs and MLLMs
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Debugging, monitoring and visualization for Python Machine Learning and Data Science
Hummingbird compiles trained ML models into tensor computation for faster inference.
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
Automatable GenAI Scripting
Integrate cutting-edge LLM technology quickly and easily into your apps
This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.
An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.
21 Lessons, Get Started Building with Generative AI
Learn Generative AI fundamentals through Java programming.
UFO³: Weaving the Digital Agent Galaxy
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
workshop materials to build intelligent solutions on Open AI
The first "code-first" agent framework for seamlessly planning and executing data analytics tasks.
[ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Simple and Distributed Machine Learning
Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.
Low-bit LLM inference on CPU/NPU with lookup table
A library of workshops written by and for Microsoft Learn Student Ambassadors and Cloud Advocates and their local communities
Join a time-traveling adventure where you meet history’s legends while learning Generative AI technologies! ✨
TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
PyTorch Wildlife: a Collaborative Deep Learning Framework for Conservation.
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
Automatic Generation of Visualizations and Infographics using Large Language Models
MCP Python Tutorial
Graphormer is a general-purpose deep learning backbone for molecular modeling.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Official community-driven Azure Machine Learning examples, tested with GitHub Actions.
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"
Official code for TimeCraft: A Time Series Generation Framework for Real-World Applications
Multi-modality pre-training
MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model
Community for applying LLMs to robotics and a robot simulator with ChatGPT integration
[CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation
For releasing code related to compression methods for transformers, accompanying our publications
Examples for using ONNX Runtime for machine learning inferencing.
Best Practices, code samples, and documentation for Computer Vision.
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
A tutorial demonstrating how to implement deep learning models for time series forecasting
Microsoft Security Copilot is a generative AI-powered security solution that helps increase the efficiency and capabilities of defenders to improve security outcomes at machine speed and scale, while remaining compliant to responsible AI principles
maximal update parametrization (µP)
Spectral Temporal Graph Neural Network (StemGNN in short) for Multivariate Time-series Forecasting
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
Samples for getting started with deep learning across TensorFlow, CNTK, Theano and more.
A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.
Foundation Architecture for (M)LLMs
Sample Code for Gated Graph Neural Networks
[NeurIPS 2021 Spotlight] Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"
multilspy is a lsp client library in Python intended to be used to build applications around language servers.
Diffusion models of protein structure; trigonometry and attention are all you need!
AICI: Prompts as (Wasm) Programs
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Automated benchmarking of Retrieval-Augmented Generation (RAG) systems
Samples and Tools for Windows ML.
Generating native code interfaces from TypeScript
Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.
The IQ Series is a hands-on learning experience for Microsoft IQ: Microsoft's unified intelligence layer for the enterprise, spanning Foundry IQ, Work IQ, and Fabric IQ. The series includes video episodes, Jupyter notebooks, and Azure deployment templates.
Hack Together: RAG Hack | Register, Learn, Hack
This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.
Sample code and documentation for using the Microsoft HoloLens 2 for Computer Vision research.
Prompt Orchestration Markup Language
Build your first agent with Azure AI Agent Service Workshop
Muzic: Music Understanding and Generation with Artificial Intelligence
FastFormers - highly efficient transformer models for NLU
AI-in-a-Box leverages the expertise of Microsoft across the globe to develop and provide AI and ML solutions to the technical community. Our intent is to present a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction.
Microsoft Finance Time Series Forecasting Framework (FinnTS) is a forecasting package that utilizes cutting-edge time series forecasting and parallelization on the cloud to produce accurate forecasts for financial data.
[arXiv 2023] Set-of-Mark Prompting for GPT-4V and LMMs
Gift your VS Code agent a real debugger: breakpoints, stepping, inspection.
Implementation of the Aurora model for Earth system forecasting
Experience, Learn and Code the latest breakthrough innovations with Microsoft AI
Parameter server framework for distributed machine learning
End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service
Generation of protein sequences and evolutionary alignments via discrete diffusion models
Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
Windows SDK for the Microsoft Computer Vision API, part of Cognitive Services
Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
A research prototype of a human-centered web agent
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022
Python notebooks with ML and deep learning examples with Azure Machine Learning Python SDK | Microsoft
Official Implementation of "KBLaM: Knowledge Base augmented Language Model"
The Multi-Agent Custom Automation Engine Solution Accelerator is an AI-driven system that manages a group of AI agents to accomplish tasks based on user input. Powered by Microsoft Agent Framework, Azure Foundry, Azure Cosmos DB, and infrastructure services, it provides a reference application, allowing you to hit the ground running.
Large-scale pretrained models for goal-directed dialog
Research project. A Memory solution for users, teams, and applications.
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
Medical Imaging Deep Learning library to train and deploy 3D segmentation models on Azure Machine Learning
Microsoft Distributed Machine Learning Toolkit
a family of versatile and state-of-the-art video tokenizers.
This solution accelerator leverages Microsoft Foundry, Azure Content Understanding, Azure OpenAI Service, and Foundry IQ to enable organizations to derive insights from volumes of conversational data using generative AI. It offers key phrase extraction, topic modeling, and interactive chat experiences through an intuitive web interface.
Jupyter Notebook with Python samples for the Cognitive Services Computer Vision API
Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
⚠️DirectML is in maintenance mode ⚠️ DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm.
A Dataset of Python Challenges for AI Research
The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.
Platform for Situated Intelligence
Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV). Packages available at: https://www.nuget.org/profiles/Recognizers.Text, https://www.npmjs.com/~recognizers.text
A Unified Semi-Supervised Learning Codebase (NeurIPS'22)
GIT: A Generative Image-to-text Transformer for Vision and Language
RAG Time: A 5-week Learning Journey to Mastering RAG
Inference code for scalable emulation of protein equilibrium ensembles with generative deep learning
Generative AI extensions for onnxruntime
This is a collection of our NAS and Vision Transformer work.
Sample code and documentation for using the Microsoft HoloLens for Computer Vision research
Send a phone call from AI agent, in an API call. Or, directly call the bot from the configured phone number!
Sharing Updatable Models (SUM) on Blockchain
A pre-trained GPT model for Python code completion and generation
Cookiecutter API for creating Custom Skills for Azure Search using Python and Docker
TypeChat is a library that makes it easy to build natural language interfaces using types.
TensorFlow implementations of Graph Neural Networks
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
Agent Framework Samples - showcasing ways in which agent framework can be utilized.
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
A unified 3D Transformer Pipeline for visual synthesis
Resource scheduling and cluster management for AI
A developer CLI for working with Azure resources to build and deploy AI applications. Commands map to key workflow stages: code, build, deploy, and monitor.
Prompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.
This repo accelerates development of RAG applications with rich data sources including SQL Warehouses and documents analysed with Azure Document Intelligence
NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego
Natural Language Processing Best Practices & Examples
Android SDK for the Microsoft Computer Vision API, part of Cognitive Services.
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
A highly-customizable web-based client for Azure Bot Services.