Comparisons / Pydantic AI vs Semantic Kernel
Pydantic AI vs Semantic Kernel: Which Agent Framework to Use?
Pydantic AI is a type-safe agent framework built by the Pydantic team. 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
Pydantic AI
16.1k
1.9k
Python
MIT
2024-06-21
Pydantic (Samuel Colvin)
Semantic Kernel
27.6k
4.5k
C#
MIT
2023-02-27
Microsoft
GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.
| Concept | Pydantic AI | Semantic Kernel |
|---|---|---|
| Agent | `Agent()` class with typed `result_type`, system prompt, and `model` parameter | `ChatCompletionAgent` with `Kernel`, instructions, and service config |
| Tools | `@agent.tool` decorator with typed parameters and Pydantic validation | — |
| Agent Loop | `agent.run()` handles the tool-call loop internally with typed dispatch | — |
| Structured Output | `result_type=MyModel` enforces Pydantic model on final LLM response | — |
| Model Switching | Swap `model='openai:gpt-4o'` to `model='anthropic:claude-sonnet'` in one line | — |
| Dependencies | `RunContext[DepsType]` injects typed dependencies into tools at runtime | — |
| 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-Language | — | C#, Python, Java SDKs with shared abstractions |
Pydantic AI vs Semantic Kernel, head to head
Pydantic AI Pydantic AI is a type-safe agent framework built by the Pydantic team.
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 Pydantic AI if
Pick Pydantic AI if pydantic AI adds genuine value if you want compile-time type checking across your agent's tools, outputs, and dependencies. If you already use Pydantic in your stack, it fits naturally. But the core agent logic — loop, dispatch, validate — is still ~60 lines of Python you can own entirely. Pydantic AI 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.
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; Pydantic AI would force you to translate.
What both add
Both Pydantic AI 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 Pydantic AI 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 →