Updated

Semantic Kernel

Microsoft's open-source SDK for building AI agents and multi-agent workflows in C#, Python and Java, with plugins, memory and vector-store connectors; Microsoft now points new work to its successor, Microsoft Agent Framework.

9 open-source projects declare Semantic Kernel in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostableFree tier

Users being moved · Oct 2025: Microsoft calls Microsoft Agent Framework the successor to Semantic Kernel and publishes a migration guide; Semantic Kernel 1.x keeps getting critical bug and security fixes, but most new features go to Agent Framework. Source ↗

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Semantic Kernel

What Semantic Kernel is used for

AI SDK & Agent Framework · Broad framework →Building agents in C#/.NET, Python or Java with Microsoft's SDK and its Azure integrations.Trade-off: Microsoft directs new projects to Microsoft Agent Framework; Semantic Kernel gets critical fixes but few new features.
LangChain66Mastra24LlamaIndex16AI SDK5CrewAI3Semantic Kernel0Makers' products on each, for AI SDK & agent framework

Semantic Kernel vs the alternatives makers chose

OptionMakers' productsOpen source
LangChain66 57%Yes
Mastra24 21%Yes
LlamaIndex16 14%Yes
AI SDK5 4%Yes
CrewAI3 3%Yes
LangGraph1 1%Yes
Semantic Kernel0 0%Yes

For AI SDK & agent framework: how many of the 115 makers' products we know the AI SDK & agent framework of chose each option.

When to use Semantic Kernel, and when not

Something else fits better if

  • Your app is TypeScript and you want agents without adding a Python service: AI SDK or Mastra.
  • You want a small typed agent loop in Python, close to the raw API: Pydantic AI or OpenAI Agents SDK.
  • Your agent works on files and runs commands, like a coding or research agent: Claude Agent SDK.
  • You need many prebuilt connectors for models, tools and data sources: LangChain.
  • Your agent is a long-running workflow with branches, saved state and human approval steps: LangGraph.
From each decision's guide, written from what makers' products chose and why.

Who uses it

No maker's live product on record yet, and 9 open-source projects that declare it in their code.

We haven't found a maker's live product that uses Semantic Kernel yet — only the open-source projects below, which declare it in their code.

Open source: a project that declares Semantic Kernel as a dependency in its public code — verifiable, but not necessarily a live product.

Alternatives to Semantic Kernel

All alternatives by situation →

Further reading

Questions makers ask about Semantic Kernel

What are the alternatives to Semantic Kernel?

For AI SDK & agent framework, the other options makers' products we track chose most are LangChain (66), Mastra (24), LlamaIndex (16), AI SDK (5), CrewAI (3), LangGraph (1). Open source or self-hostable among them: LangChain, Mastra, LlamaIndex, AI SDK, CrewAI, LangGraph. Each alternative, with the situation it fits, is on the Semantic Kernel alternatives page.

Is Semantic Kernel free?

Yes — it is free, open-source software.

Is Semantic Kernel open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Semantic Kernel?

No llms.txt, official MCP server or CLI found yet.

Who uses Semantic Kernel?

No maker's live product we track yet; 9 open-source projects declare it in their code. source ↗