microsoft

A Python utility that converts various file formats (PDFs, Office documents, images, audio, HTML, etc.) into clean Markdown text optimized for AI and text analysis pipelines. Preserves document structure while making content easily consumable by LLMs.

Microsoft PowerToys is a collection of 30+ utilities that help power users customize Windows and streamline everyday tasks, including FancyZones, PowerToys Run, Color Picker, and Command Palette.

Microsoft's typed superset of JavaScript that compiles to plain JavaScript, adding static types and modern language features.

Modern terminal for Windows with tabs, Unicode/UTF-8, GPU-accelerated rendering, and support for PowerShell, WSL, and cmd.

Cross-browser end-to-end testing framework from Microsoft, with a single API for Chromium, Firefox, and WebKit and built-in auto-wait.

Open-source voice AI framework that includes advanced speech recognition (ASR) for 60-minute audio transcription with speaker diarization, text-to-speech (TTS) for 90-minute multi-speaker synthesis, and real-time streaming TTS. Operates at ultra-low 7.5Hz frame rate for efficient long-form audio processing.

Microsoft's MCP server for Playwright. Lets agents drive a browser via tool calls.

Microsoft's framework for building multi-agent AI applications, with support for code execution, function calling, and conversational orchestration.

Microsoft's native port of the TypeScript compiler to Go, targeting major build- and type-checking speedups.

A framework for training and optimizing AI agents using reinforcement learning and other algorithms. Supports any agent framework with minimal code changes and enables selective optimization of multi-agent systems.

A comprehensive multi-language framework for building, orchestrating, and deploying AI agents and multi-agent workflows. Supports both Python and .NET with features like graph-based workflows, observability, and multiple LLM providers.

Free, open-source code editor from Microsoft with a rich extension ecosystem, debugging, and integrated Git.

Microsoft's toolkit for governing AI agents — policy enforcement, zero-trust identity, and execution sandboxing.

Microsoft's official inference framework for 1-bit LLMs — runs large language models with extreme memory and energy efficiency.

Microsoft's modular graph-based retrieval-augmented generation system, building knowledge graphs from documents for richer LLM Q&A.

Microsoft's SDK for integrating LLMs into apps with planners, memory, plugins, and orchestration across C#, Python, and Java.

Microsoft's screen-parsing model that turns UI screenshots into structured element data — the perception layer for pure-vision GUI agents.

Microsoft's React and web component library implementing the Fluent Design System — used in Office, Teams, and Microsoft 365.

Python bindings for Playwright — Microsoft's cross-browser end-to-end testing framework with auto-wait and tracing.

CLI for common Playwright actions — record browser interactions and have it generate the Playwright code that reproduces them.

Microsoft Research's experimental agent that operates across the browser and local filesystem in tandem — a step toward general-purpose computer-use agents.

Microsoft's toolkit for building, testing, and deploying high-quality LLM applications — visual orchestration, tracing, and prompt evaluation.

Microsoft Research's LLM-powered multi-agent persona simulation — populate scenarios with synthetic users for product research and creative brainstorming.

Microsoft Research's structured 3D latent diffusion model for scalable 3D asset generation from text or images. CVPR 2025 Spotlight.

Microsoft's prompt and KV-cache compression for LLMs — up to 20x compression with minimal accuracy loss for cheaper, faster inference.

The browser-based code editor that powers VS Code, packaged for embedding in web apps with syntax highlighting and IntelliSense.

Microsoft's compatibility layer for running Linux binaries natively on Windows, with full kernel support, GUI app integration, and tight Windows interop.

Microsoft Research's AI-assisted visualization tool — describe the chart you want in plain English, drag fields in, and it generates the data transforms and renders the visualization.

Microsoft's fast static type checker for Python — also powers the Pylance language server in VS Code.

Microsoft's open-source framework for detecting, redacting, masking, and anonymizing PII in text and images.

Microsoft's IDE-style autocomplete for the terminal — ports Fig completion specs into a cross-shell command-line helper.

Microsoft's adaptive interface system — design tokens, components, and tooling for building modern web experiences with web components.

Microsoft Research's multi-agent Windows automation framework — UI-Focused agents (UFO3) that coordinate to operate Windows apps.

Microsoft's library for building natural language interfaces using TypeScript types — LLMs respond in JSON conforming to your schema.

Microsoft's code-first stack for building, observing, and deploying distributed .NET apps — orchestration, service discovery, and dashboards in one package.

Microsoft's official C/C++ extension for VS Code — IntelliSense, debugging, code navigation, and toolchain integration.

Microsoft's interactive data-visualization tool — explore datasets through animated unit charts that group, sort, and filter on the fly.

Microsoft's language for defining APIs — write API contracts once, generate OpenAPI / JSON Schema / Protobuf and server/client code.

Microsoft's reference implementation of Low-Rank Adaptation — efficient fine-tuning that trains a tiny number of parameters per task.

Microsoft's reference architecture for placing AI-powered phone calls — your bot dials out (or callers dial in) and an LLM drives the conversation.