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 vs Semantic Kernel

Agent Development comparison

Microsoft Agent Framework vs Semantic Kernel

Pricing, pros, cons, and ideal use cases — side by side.

Microsoft Agent Framework logo
Microsoft Agent FrameworkFree

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.

Visit Microsoft Agent Framework
Semantic Kernel logo
Semantic KernelFree

Microsoft's open-source SDK for integrating LLMs into C#, Python and Java applications, now succeeded by Microsoft Agent Framework (1.0, April 2026).

Visit Semantic Kernel

At a glance

Microsoft Agent FrameworkSemantic Kernel
PricingFreeThe 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.FreeSemantic Kernel is MIT-licensed and free, and Microsoft now describes Microsoft Agent Framework as its "enterprise-ready successor" (version 1.0 released 3 April 2026, also MIT). Its successor, Microsoft Agent Framework, can be hosted on Foundry Agent Service: no added charge for Foundry-native prompt and workflow agents; hosted agents bill $0.0994 per vCPU-hour and $0.0118 per GiB-hour in East US, plus model tokens and tool fees (for example Web Search at $14 per 1,000 transactions). As read on the vendor's pricing page on 10 November 2026.
CategoryAgent DevelopmentAgent Development
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
.NET and Java enterprise development teamsOrgs embedding AI into existing applicationsMicrosoft-ecosystem shops

Pros & cons

Microsoft Agent Framework

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

Semantic Kernel

Pros
  • First-class C#, Python, and Java support
  • Designed to fit into existing enterprise apps
  • Backed and maintained by Microsoft
  • Clean plugin and function abstractions
Cons
  • Smaller ecosystem than Python-first frameworks
  • Succeeded by Microsoft Agent Framework; new projects should evaluate that first
  • Less suited to rapid Python prototyping

Which should you choose?

Microsoft Agent Framework is built around .net and python teams building agents on azure; Semantic Kernel leans more toward .net and java enterprise development teams. Shortlist the one whose strengths line up with your biggest constraint.

Still deciding between Microsoft Agent Framework and Semantic Kernel?

Get one AI workflow a week showing Agent Development in a real stack — what they cost, and where each one breaks.

See all Microsoft Agent Framework alternatives →See all Semantic Kernel alternatives →Browse all Agent Development tools →