Semantic Kernel vs Pydantic AI
Semantic Kernel is a framework from microsoft (MIT licence, 29k GitHub stars, last push 2026-11-20); Pydantic AI is a framework from pydantic (MIT licence, 21k GitHub stars, last push 2026-11-21). They share 1 of 4 capabilities and integrations identified for either (overlap 0.60); only Semantic Kernel covers Tool Use & Function Calling; only Pydantic AI covers Agent SDKs, Python Agent Frameworks. Figures as of 2026-11-21. DER
Semantic Kernel profilePydantic AI profileOpen in the compare tool
Side-by-side facts
6 of 16 rows differ (marked). Unknown means no source we track states it.
| Field | Semantic Kernel | Pydantic AI |
|---|---|---|
| Type | Framework · library CUR | Framework · library SRC |
| Publisher · differs | microsoft CUR | pydantic SRC |
| Licence | MIT CUR | MIT CUR |
| Open source | Yes CUR | Yes CUR |
| Pricing model | open-source CUR | open-source CUR |
| Hosting | Unknown | Unknown |
| Latest version | Unknown | Unknown |
| Languages · differs | csharp, python, java CUR | python CUR |
| GitHub stars · differs | 29k (28,791) SRC | 21k (21,325) SRC |
| Forks · differs | 4.9k SRC | 3.2k SRC |
| Last push · differs | 2026-11-20 SRC | 2026-11-21 SRC |
| Archived | No SRC | No SRC |
| First published · differs | Unknown | 2024-06-21 SRC |
| Versions recorded | Unknown | Unknown |
| Verification | Checked by AgentSidekick against official sources CUR | Checked by AgentSidekick against official sources CUR |
| Last verified | 2026-11-21 CUR | 2026-11-21 CUR |
Shared and unique capabilitiesDER
Capabilities are assigned by keyword rules from each description unless a researcher set them; integrations are services named in the description or package metadata.
Both (1)
Only Semantic Kernel (1)
Only Pydantic AI (2)
Platform compatibility
Status per platform from the evidence we hold. No pairing has been tested by AgentSidekick.
No compatibility evidence
For all 47 platforms on record the status is Unknown or Platform discontinued for both: neither product type implements a standard we can check (MCP, Agent Skills, Claude plugins) and neither publisher names a platform.
Maintenance
Repository activity read from the GitHub API. Activity is not quality.
| Measure | Semantic Kernel | Pydantic AI |
|---|---|---|
| Status | Active DER | Active DER |
| Days since last push | 1 DER | 0 DER |
| Open issues | 101 SRC | 1.4k SRC |
| Latest GitHub release | dotnet-1.82.0 · 2026-11-07 SRC | v2.71.0 · 2026-11-19 SRC |
| Newest registry version | Unknown | Unknown |
Evaluation dimensions
Separate signals with their evidence; there is no overall score. Hover or focus a status for its evidence.
| Dimension | Semantic Kernel | Pydantic AI |
|---|---|---|
| Source authority | Checked against official sources | Checked against official sources |
| Publisher verification | Organisation account | Organisation account |
| Maintenance activity | Active | Active |
| Licence clarity | MIT | MIT |
| Installation clarity | Linked | Linked |
| Documentation | Docs linked | Docs linked |
| Compatibility evidence | Unknown | Unknown |
| Security review | Not reviewed | Not reviewed |
Which fits which requirementDER
Derived from the differences above, one rule per line. Nothing here says either product is better; check the requirement against your own needs.
Choose Semantic Kernel if…
- you need Tool Use & Function Calling (classified for Semantic Kernel only)
Choose Pydantic AI if…
- you need Agent SDKs, Python Agent Frameworks (classified for Pydantic AI only)
Sources
- Semantic Kernel · Curated research: learn.microsoft.com (external)checked
- Semantic Kernel · Researcher checked: learn.microsoft.com (external)checked
- Semantic Kernel · Researcher checked: github.com (external)checked
- Pydantic AI · GitHub topic search: github.com (external)checked
- Pydantic AI · Curated research: ai.pydantic.dev (external)checked
- Pydantic AI · Researcher checked: ai.pydantic.dev (external)checked
- Pydantic AI · Researcher checked: github.com (external)checked
Page data last updated .