Compare frameworks
CrewAI vs Pydantic AI vs Semantic Kernel
Every figure below carries the source that reported it and the moment it was observed. Values that failed validation are withheld rather than shown, and a dash means no source we track carries that field for that framework.
| Field | CrewAI | Pydantic AI | Semantic Kernel |
|---|---|---|---|
| Stars | 59,154 (highest of the compared values)Synced from sourceCurrent5h ago | 20,249Synced from sourceCurrent5h ago | 28,607Synced from sourceCurrent5h ago |
| downloads | — | 3,076,771Synced from sourceStale1mo ago· past SLA | — |
| Last commit | 2026-09-29Synced from sourceCurrent5h ago | 2026-09-29Synced from sourceCurrent5h ago | 2026-09-28Synced from sourceCurrent5h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | csharpSeeded, unreviewedwritten 1mo ago |
| Licence | MITSynced from sourceCurrent5h ago | MITSynced from sourceCurrent5h ago | MITSynced from sourceCurrent5h ago |
| Archived | noSynced from sourceCurrent5h ago | noSynced from sourceCurrent5h ago | noSynced from sourceCurrent5h ago |
| Category | multi-agentSeeded, unreviewedwritten 1mo ago | structured-outputSeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago |
| Contributors | 340Synced from sourceCurrent5h ago | 610Synced from sourceCurrent5h ago | 416Synced from sourceCurrent5h ago |
| Forks | 8598Synced from sourceCurrent5h ago | 2810Synced from sourceCurrent5h ago | 4795Synced from sourceCurrent5h ago |
| Maintainer | CrewAISeeded, unreviewedwritten 1mo ago | PydanticSeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago |
| Open issues | 508Synced from sourceCurrent5h ago | 1137Synced from sourceCurrent5h ago | 314Synced from sourceCurrent5h ago |
| PyPI downloads, monthly | — | 13478631Synced from sourceStale1mo ago· past SLA | — |
| PyPI downloads, weekly | — | 3076771Synced from sourceStale1mo ago· past SLA | — |
| PyPI package | crewaiSynced from sourceCurrent5h ago | pydantic-aiSynced from sourceCurrent5h ago | semantic-kernelSynced from sourceCurrent5h ago |
| PyPI released | 2026-09-28T21:15:33.691987ZSynced from sourceCurrent5h ago | 2026-09-25T23:32:17.554286ZSynced from sourceCurrent5h ago | 2026-08-06T09:56:42.518861ZSynced from sourceCurrent5h ago |
| Requires Python | <3.14,>=3.10Synced from sourceCurrent5h ago | >=3.10Synced from sourceCurrent5h ago | >=3.10Synced from sourceCurrent5h ago |
| PyPI version | 1.15.23Synced from sourceCurrent5h ago | 2.51.0Synced from sourceCurrent5h ago | 1.44.1Synced from sourceCurrent5h ago |
| Repository | https://github.com/crewAIInc/crewAISynced from sourceCurrent5h ago | https://github.com/pydantic/pydantic-aiSynced from sourceCurrent5h ago | https://github.com/microsoft/semantic-kernelSynced from sourceCurrent5h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 5h ago. Where a row is marked, ▲ is the highest of the values shown and ▼ the lowest — arithmetic on the figures above, not a ranking or a recommendation. Rows where neither extreme is meaningful are left unmarked rather than given a direction they do not have.
Change the comparison
Remove one, or open the directory to pick a different set. Up to 3 at a time.