What is Semantic Kernel?
Latest launch MIT
Summary
Semantic Kernel is Microsoft's MIT-licensed SDK for AI agents and plugins in Python, .NET and Java, now succeeded by Microsoft Agent Framework.
- Category
- Frameworks
- Open source
- Yes
- License
- MIT
- Pricing
- Semantic Kernel is MIT-licensed and free to install from PyPI or NuGet (Java builds live in microsoft/semantic-kernel-java). You pay your model provider for tokens.
Semantic Kernel is Microsoft's SDK for adding LLM calls, plugins and agents to Python, .NET and Java apps. Code: microsoft/semantic-kernel, MIT.
The top of its README now reads "Semantic Kernel is now Microsoft Agent Framework" and links a migration guide. So treat it as the maintained predecessor of Microsoft Agent Framework: it still ships fixes and connectors, but new agent features land in MAF.
Its strengths are the plugin model (native functions, prompt templates, OpenAPI specs and MCP), a broad set of vector store connectors, and local models through Ollama, LM Studio or ONNX. Requirements per the README: Python 3.11 through 3.14 (1.47.0 dropped 3.10), .NET 10+, JDK 17+.
Python releases: 1.45.0 on October 6, 1.46.0 on October 28 and 1.47.0 on November 5, 2026, per GitHub; 1.47.0 requires Python 3.11 or later. Deciding whether to migrate? Read Microsoft Agent Framework vs Semantic Kernel. This hub was created with the dated launch Semantic Kernel 1.46.0 for Python.
For other options see the frameworks category, including LangChain and AG2.
Semantic Kernel alternatives
| Tool | License | Pricing note |
|---|---|---|
Semantic KernelThis pageSemantic Kernel is Microsoft's MIT-licensed SDK for AI agents and plugins in Python, .NET and Java, now succeeded by Microsoft Agent Framework. | MIT | Semantic Kernel is MIT-licensed and free to install from PyPI or NuGet (Java builds live in microsoft/semantic-kernel-java). You pay your model provider for tokens. |
Microsoft Agent FrameworkMicrosoft Agent Framework is an MIT-licensed Python and .NET framework for AI agents and multi-agent workflows, and the successor to Semantic Kernel. | MIT | Microsoft Agent Framework is MIT-licensed and free to install from PyPI or NuGet. You pay your model provider, or Azure if you host agents on Microsoft Foundry. |
LangChainLangChain is an open-source agent engineering platform and Python framework for building agents. | MIT | Not stated |
AG2AG2 (formerly AutoGen) is an Apache-2.0 Python framework for AI agents and multi-agent networks, installed from PyPI as ag2 and imported as ag2. | Apache-2.0 | AG2 is Apache-2.0 and free to install from PyPI. You pay your model provider for tokens. |
Launches and updates
Semantic Kernel 1.46.0 hardens plugins and connectors
Semantic KernelSemantic Kernel 1.46.0 for Python (Oct 28, 2026) blocks ../ upload paths, pins HttpPlugin DNS, stops logging argument values and fixes connectors.
Category: Frameworks
Pricing: Open source
Guides covering Semantic Kernel
Questions
What is Semantic Kernel?
A model-agnostic SDK from Microsoft for building AI agents and multi-agent systems, with plugins from native functions, prompt templates, OpenAPI specs or MCP, plus vector store connectors. It supports Python 3.11 through 3.14, .NET 10+ and JDK 17+.
Is Semantic Kernel being replaced?
Its README says Semantic Kernel is now Microsoft Agent Framework and calls MAF the enterprise-ready successor, with a migration guide on Microsoft Learn. Semantic Kernel still gets releases: Python 1.47.0 shipped on November 5 and .NET 1.82.0 on November 7, 2026.
How do I install Semantic Kernel?
pip install semantic-kernel for Python, or dotnet add package Microsoft.SemanticKernel for .NET. Set OPENAI_API_KEY or your Azure OpenAI key first.
Should I start a new project on Semantic Kernel?
Microsoft's own pointer is to Microsoft Agent Framework for new work. Semantic Kernel makes sense if you already run it in production and want fixes while you plan a migration.