Microsoft Agent Framework vs Semantic Kernel
Side-by-side comparison built from DeepYard's structured catalog. Content updated Aug 21, 2026.
Direct Answer
Microsoft Agent Framework suits teams needing open-source access, orchestration focus, and 60,568 GitHub stars in current listing data. Semantic Kernel suits teams needing open-source access, java focus, and 28,477 GitHub stars in current listing data. This summary reflects catalog metadata only for decision support, not independent testing.
What this comparison weighs
- Pricing and free-tier availability
- License model and deployment fit
- GitHub adoption and contributor depth
- Catalog tags, integrations, and supported workflows
| Metric | Microsoft Agent Framework | Semantic Kernel |
|---|---|---|
| GitHub Stars | 60.6K | 28.5K |
| Contributors | 444 | 400 |
| Last Commit | Apr 15, 2026 | Aug 21, 2026 |
| Open Issues | 997 | 250 |
| License | open-source | open-source |
| Pricing | open-source | open-source |
| Free Tier | Yes | Yes |
| Category | frameworks | frameworks |
| Trending | No | No |
Choose Microsoft Agent Framework if you need
- • Microsoft Agent Framework is the stronger pick when Orchestration matters because that capability is listed only on its profile.
- • Microsoft Agent Framework shows broader GitHub adoption with 60,568 stars versus 28,477 for Semantic Kernel.
- • Microsoft Agent Framework has a larger visible contributor base (444 vs 400).
Choose Semantic Kernel if you need
- • Semantic Kernel stands out for Java workflows that are not listed for Microsoft Agent Framework.
- • Semantic Kernel is the stronger pick when Plugins matters because that capability is listed only on its profile.
- • Semantic Kernel is the cleaner fit if you specifically need Csharp workflows from the catalog tags.
Meaningful differences
- • Workflow emphasis: Microsoft Agent Framework highlights Python, while Semantic Kernel highlights Java.
- • GitHub adoption: Microsoft Agent Framework shows 60,568 stars versus 28,477 for Semantic Kernel.
- • Contributor count: Microsoft Agent Framework lists 444 contributors and Semantic Kernel lists 400.
Shared capabilities
- • Microsoft
- • Multi Agent
- • Enterprise
- • Python
- • Open Source
Shared Tags
Only in Microsoft Agent Framework
Only in Semantic Kernel
Limitations and evidence
- • DeepYard compares structured public metadata; this is not an independent benchmark unless a test record is shown.
- • Signals such as stars, contributors, and last commit indicate public activity, not purchase fit or runtime quality.
- • Pricing and feature coverage reflect the stored listing snapshot and may lag vendor changes between refreshes.
Source links
About Microsoft Agent Framework
Microsoft's Agent Framework is the convergence of AutoGen and Semantic Kernel into a unified multi-agent platform. It provides a consistent API for building, orchestrating, and deploying agent teams across Python and .NET, with enterprise features like managed identity, Azure integration, and production-grade observability.
View full listingAbout Semantic Kernel
Semantic Kernel is Microsoft's open-source SDK for building AI agents and integrating LLMs into enterprise applications. It supports C#, Python, and Java with a plugin architecture for extending agent capabilities. Semantic Kernel provides planning, memory, and function-calling abstractions that work with OpenAI, Azure OpenAI, and Hugging Face models.
View full listing