WorkflowStack AI
WorkflowsIndustriesToolsGuidesAI QuizBlogEnterprise
Get Free Workflows
WorkflowStack AI

Practical AI workflows for SMB operators and enterprise teams. No fluff. No hype. Just what ships.

Library

  • All Workflows
  • Industries
  • Enterprise
  • Tools
  • Guides

Company

  • About
  • Blog
  • Newsletter
  • Contact

Stay Updated

Weekly workflow ideas for operators and enterprise teams.

Get Free Workflows

© 2026 Blueteem LLC. All rights reserved.

Privacy PolicyTerms of Service
HomeToolsMicrosoft Agent Framework
Microsoft Agent Framework logo

Microsoft Agent Framework

Agent Development
FreeVisit Site

Microsoft's open-source agent framework for Python and .NET, the 1.0 successor to both Semantic Kernel and AutoGen, with graph-based workflows and hosting on Foundry Agent Service.

Overview

Microsoft Agent Framework is where Microsoft's two earlier agent projects ended up. Its documentation calls it "the direct successor, created by the same teams" and "the next generation of both Semantic Kernel and AutoGen": it keeps AutoGen's simple single- and multi-agent abstractions, adds Semantic Kernel's enterprise features (session-based state, type safety, middleware, telemetry), and introduces graph-based workflows that give explicit control over multi-agent execution paths, with state management for long-running and human-in-the-loop work. Version 1.0 was announced for Python and .NET on 3 April 2026 and both SDKs release frequently (python-1.25.0 and dotnet-1.28.0 in the first week of November 2026). A Go SDK is in public preview in a separate repository and does not yet implement declarative agents or functional workflows. Model support covers Microsoft Foundry, Azure OpenAI, OpenAI, Anthropic and Ollama among others, and agents can call MCP servers. Microsoft publishes migration guides from both Semantic Kernel and AutoGen, which matters because Microsoft has declared AutoGen archived and no longer maintained. The framework is free; the cost question is where you run it. Microsoft's own advice applies before you start: "If you can write a function to handle the task, do that instead of using an AI agent."

Pros & Cons

Pros

  • One supported path that replaces both Semantic Kernel and AutoGen
  • First-class Python and .NET SDKs at 1.0, MIT-licensed
  • Graph-based workflows with state for long-running and human-in-the-loop work
  • Works with Foundry, Azure OpenAI, OpenAI, Anthropic and Ollama models
  • Official migration guides from Semantic Kernel and AutoGen

Cons

  • The managed hosting path is Microsoft Foundry on Azure; elsewhere you run it yourself
  • Go SDK is still in public preview and missing features
  • Fast release cadence means frequent upgrades
  • Younger ecosystem than LangGraph's
  • Existing AutoGen and Semantic Kernel code has to be migrated, not just upgraded

Workflows that use Microsoft Agent Framework

Get a new AI workflow each week — many feature Microsoft Agent Framework and other tools in this category.

Compare Microsoft Agent Framework

Microsoft Agent Framework vs LangGraphMicrosoft Agent Framework vs CrewAIMicrosoft Agent Framework vs LlamaIndexMicrosoft Agent Framework vs OpenAI AgentKitMicrosoft Agent Framework vs Semantic Kernel
See all Microsoft Agent Framework alternatives →

Pricing

The framework is MIT-licensed and free. Hosting is optional and separate: on Foundry Agent Service there is "no additional charge for creating or running Foundry-native agents using prompts and workflows", while hosted agents bill container compute at $0.0994 per vCPU-hour and $0.0118 per GiB-hour (West US 3), plus model tokens and tool fees such as Web Search at $14 per 1,000 transactions. As read on the vendor's pricing page on 11 November 2026.

Ideal For

.NET and Python teams building agents on AzureTeams migrating off AutoGen or Semantic KernelEnterprises that want explicit, graph-based multi-agent workflowsMicrosoft-ecosystem shops hosting agents on Foundry
Visit Microsoft Agent Framework