Semantic Kernel
learn.microsoft.comframeworkself-hosted
Semantic Kernel is a self-hosted framework in the Agent Frameworks layer of the AI stack. Microsoft SDK for embedding AI steps into .NET and Python apps.
By Lattice editorial · Facts verified · method
- licence
- MIT
- language
- C#
- cost
- free
- owned by
- Applied Engineering
Verified 2026-09build refuses it from 2027-04
Use Semantic Kernel when
Embedding AI steps into an existing .NET estate.
Skip Semantic Kernel when
Your stack is not .NET.
Turns a model call into a multi-step program. — that is what this layer of the stack is answerable for. See the full Agent Frameworks section for the rest of the options.
Visit learn.microsoft.comCompare with another toolBadge this entry
[](https://lattice.kunjshah.in/agent-frameworks/semantic-kernel)Quick answers
- Is Semantic Kernel open source?
- Yes. Semantic Kernel is open source under the MIT licence. It is free to use.
- What are the alternatives to Semantic Kernel?
- The closest alternatives to Semantic Kernel are LangChain and Pydantic AI.
Reading on agents
Alternatives to Semantic Kernel
Also in agents
- LangChainLangChainComposable abstractions for model calls, tools and state.Use when Tool use and state, in an ecosystem where the answers already exist.Skip when You want a thin, legible core — this is a large surface.MIT · self-hosted · free
- LlamaIndexLlamaIndexData-centric framework for retrieval and agent workflows.Use when Data-centric work where retrieval is the centre of the problem.Skip when You need agent orchestration more than data access.MIT · self-hosted · free
- Pydantic AIPydantic AIType-safe agent framework that leans on Pydantic models.Use when Type-safe agents where schema correctness is the priority.Skip when You want a batteries-included ecosystem.MIT · self-hosted · free
- AutoGenAutoGenMicrosoft research project for conversable multi-agent systems.Use when Research into conversable multi-agent systems.Skip when You need something stable and documented for production.MIT · self-hosted · free
- CrewAICrewAIRole-based orchestration where agents collaborate as a crew.Use when Role-based orchestration where agents are framed as a team.Skip when You want direct control over the loop itself.MIT · self-hosted · free
- MastraMastraTypeScript agent framework with typed workflows and evals.Use when TypeScript agents with typed workflows and evals built in.Skip when You are working in Python.Apache-2.0 · self-hosted · free
- OpenAI Agents SDKOpenAI Agents SDKLightweight primitives for handoffs, guardrails and tracing.Use when A small, legible set of primitives for handoffs and guardrails.Skip when You need multi-provider abstraction at every layer.Apache-2.0 · self-hosted · free
- AgnoAgnoMinimal agent runtime centered on model-agnostic tool interfaces.Use when A minimal agent runtime with model-agnostic tool interfaces.Skip when You need the wider ecosystem around it.MPL-2.0 · self-hosted · free
- Claude Agent SDKClaude Agent SDKAnthropic's toolkit for building agents with tool use and hooks.Use when Building agents against Anthropic models, with tool use and hooks.Skip when You need provider independence at the framework layer.proprietary · self-hosted · free
- LettaLettaAgent runtime with persistent, editable memory as a first-class primitive.Use when Agents whose memory is a first-class, inspectable and editable state.Skip when You want memory to be a detail the framework handles for you.Apache-2.0 · self-hosted · free
- smolagentssmolagentsMinimal code-first agent loop from the Hugging Face team.Use when Reading the whole agent loop in a page — it is deliberately tiny.Skip when You need a rich tool ecosystem around it.Apache-2.0 · self-hosted · free
- Vercel AI SDKVercel AI SDKProvider-agnostic building blocks for streaming apps and agents.Use when Streaming model calls in a TypeScript app, provider-agnostically.Skip when You need agent orchestration rather than model calls.Apache-2.0 · self-hosted · free