Microsoft Agent Framework: Multi-agent orchestration for Python and .NET

Repositorymicrosoft/agent-frameworkTool

Microsoft Agent Framework (MAF) is an open-source framework designed for building, orchestrating, and operating production-grade AI agents and multi-agent workflows in Python, .NET, and Go.

Key points

  1. Provides consistent APIs across Python, C#/.NET, and Go (hosted in a dedicated repository).
  2. Supports graph-based patterns including sequential execution, concurrency, handoffs, and group collaboration.
  3. Built for production requirements with durability, restartability, observability, governance, and human-in-the-loop control.
  4. Integrates with Microsoft Foundry, Azure OpenAI, OpenAI, and the GitHub Copilot SDK.
  5. Released under the MIT licence with patterns for both local execution and cloud deployment.

Why it matters

Agentic prototypes often struggle when moving to production because stateful multi-agent workflows require strict reliability, human oversight, and observability. MAF provides an enterprise-ready foundation for these operational requirements.

Analysis

The project targets engineering teams moving beyond basic prompt loops into structured multi-agent coordination. With over 13,000 GitHub stars, packaged distribution via PyPI and NuGet, and deep integration into Azure and OpenAI ecosystems, MAF establishes a standardized bridge between Python AI development and enterprise .NET environments.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:LangChain Inc.

    LangGraph: Low-Level Orchestration for Stateful AI Agents

    LangGraph by LangChain Inc. is an orchestration runtime designed for building and managing long-running, stateful AI agents. It enables developers to combine deterministic, hand-coded logic with LLM-driven steps within a single graph. Operating independently of the core LangChain library, LangGraph emphasises durable execution, state persistence, and human-in-the-loop controls.

    AI & LLMs· Resource

  • Link:Microsoft

    Microsoft AutoGen Framework

    AutoGen ist ein Open-Source-Framework von Microsoft, das die Entwicklung von LLM-basierten Anwendungen durch den Einsatz von Multi-Agenten-Systemen ermöglicht. Es erlaubt Entwicklern, komplexe Aufgaben durch die Orchestrierung mehrerer spezialisierter KI-Agenten effizient zu lösen.

    AI & LLMs

  • Repository:langgenius/dify

    Dify: Collaborative Development Platform for Agentic Workflows and RAG

    Dify is an open-source development workspace designed to build agentic workflows, RAG pipelines, and LLM integrations. It enables teams to move projects from initial prototype to production without rebuilding the application stack, offering deployment options across cloud, VPC, and self-hosted environments.

    154.5kstarsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.