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.

17k5.5kJupyter Notebook✓ Reviewed

microsoft/

agent-framework

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

12k2.1kPython✓ Reviewed

microsoft/

magentic-ui

MagenticLite is an experimental agent that works across the browser and local file system

In catalog: Microsoft Phi-4

10.0k999Python✓ Reviewed

microsoft/

aici

AICI: Prompts as (Wasm) Programs

2.1k84Rustquiet✓ Reviewed

microsoft/

flint-chart

🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.

2.0k104TypeScriptnew✓ Reviewed

microsoft/

intelligent-terminal

A fork of Windows Terminal with native agent integration, right in your command line.

1.6k110C++new✓ Reviewed

microsoft/

sarathi-serve

A low-latency & high-throughput serving engine for LLMs

51264Pythonquiet✓ Reviewed

microsoft/

Build-CLI

Experience Microsoft Build, directly from your terminal, with GitHub Copilot CLI and the Microsoft Build CLI.

28983TypeScriptnew✓ Reviewed