Comparisons / LangGraph vs Semantic Kernel

LangGraph vs Semantic Kernel: Which Agent Framework to Use?

LangGraph is LangChain's stateful workflow framework — a graph of nodes (functions) connected by edges with shared state. Semantic Kernel is Microsoft's enterprise SDK for building AI agents. Here is how they compare — paradigm, ecosystem, and the use cases each one is actually built for.

By the numbers

LangGraph

GitHub Stars

18.9k

Forks

3.4k

Language

Python

License

MIT

Created

2024-01-17

Created by

LangChain Inc (Harrison Chase)

Backed by

Sequoia Capital, Benchmark

Funding

Part of LangChain Inc — $50M raised across A and B

Weekly downloads

8.2M

Cloud/SaaS

LangGraph Platform (hosted), LangSmith (observability)

Production ready

Yes

Used by: Replit, Klarna, Elastic

github.com/langchain-ai/langgraph

Semantic Kernel

GitHub Stars

27.6k

Forks

4.5k

Language

C#

License

MIT

Created

2023-02-27

Created by

Microsoft

github.com/microsoft/semantic-kernel

GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.

ConceptLangGraphSemantic Kernel
AgentA `StateGraph` with nodes, edges, and a typed `State` channel`ChatCompletionAgent` with `Kernel`, instructions, and service config
Tools`ToolNode(tools)` paired with a conditional edge for routing
Loop`add_conditional_edges` from a node back to itself until a `END` condition
StateTyped `State` channels with reducers (`Annotated[list, add_messages]`)
Checkpointing`MemorySaver` / `PostgresSaver` persists state per `thread_id`
Human-in-loop`interrupt_before` / `interrupt_after` pauses execution for review
Parallel fanoutMultiple edges from one node + reducers merge results
Tools / Plugins`KernelPlugin` with `@kernel_function` decorators, typed parameters
Planning`StepwisePlanner`, `HandlebarsPlanner` for multi-step decomposition
Memory`SemanticTextMemory` with embeddings and vector stores
Orchestration`Kernel.invoke()` with plugin resolution and filter pipeline
Multi-LanguageC#, Python, Java SDKs with shared abstractions

LangGraph vs Semantic Kernel, head to head

LangGraph LangGraph is LangChain's stateful workflow framework — a graph of nodes (functions) connected by edges with shared state.

Semantic Kernel Semantic Kernel is Microsoft's enterprise SDK for building AI agents.

Both wrap the same underlying agent pattern — an LLM call, a tool dispatch, a loop — in different abstractions. The choice between them is mostly about which mental model and ecosystem fits the team you have, not which one is technically more capable.

Pick LangGraph if

Pick LangGraph if langGraph earns its weight when your agent is a workflow — explicit branches, checkpoints, parallel branches, or a human approval gate. For a single-agent loop, the graph machinery is overkill and a plain while loop is faster to write, debug, and ship. LangGraph is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; Semantic Kernel would force you to translate.

Full LangGraphcomparison →

Pick Semantic Kernel if

Pick Semantic Kernel if semantic Kernel earns its complexity in enterprise environments with Azure OpenAI, .NET backends, and existing Microsoft infrastructure. But the core agent pattern — LLM call, tool dispatch, loop — is identical to what you can build in 60 lines of Python. Semantic Kernel is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; LangGraph would force you to translate.

Full Semantic Kernelcomparison →

What both add

Both LangGraph and Semantic Kernel pull in a class hierarchy and a dependency tree to wrap what is, at the core, an HTTP POST in a while loop. If your use case is straightforward — one provider, a handful of tools, a single agent — the framework cost may exceed the framework benefit. The lesson below shows the same pattern in ~60 lines without either dependency.

Or build your own in 60 lines

Both LangGraph and Semantic Kernel implement the same 8 patterns. An agent is a function. Tools are a dict. The loop is a while loop. The whole thing composes in ~60 lines of Python.

No framework. No dependencies. No opinions. Just the code.

Build it from scratch →