Compare frameworks
Vercel AI SDK vs Semantic Kernel vs CrewAI
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 | Vercel AI SDK | Semantic Kernel | CrewAI |
|---|---|---|---|
| Stars | 26,922Synced from sourceCurrent2h ago | 28,593Synced from sourceCurrent2h ago | 58,958 (highest of the compared values)Synced from sourceCurrent2h ago |
| downloads | 17,883,737Synced from sourceCurrent2h ago | — | — |
| Last commit | 2026-09-24Synced from sourceCurrent2h ago | 2026-09-19Synced from sourceCurrent2h ago | 2026-09-23Synced from sourceCurrent2h ago |
| Language | typescriptSeeded, unreviewedwritten 1mo ago | csharpSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | — | MITSynced from sourceCurrent2h ago | MITSynced from sourceCurrent2h ago |
| Archived | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago |
| Category | orchestrationSeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago |
| Contributors | 715Synced from sourceCurrent2h ago | 416Synced from sourceCurrent2h ago | 340Synced from sourceCurrent2h ago |
| Forks | 5180Synced from sourceCurrent2h ago | 4787Synced from sourceCurrent2h ago | 8560Synced from sourceCurrent2h ago |
| Maintainer | VercelSeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago | CrewAISeeded, unreviewedwritten 1mo ago |
| npm downloads, monthly | 87791075Synced from sourceCurrent2h ago | — | — |
| npm downloads, weekly | 17883737Synced from sourceCurrent2h ago | — | — |
| npm package | aiSynced from sourceCurrent2h ago | — | — |
| npm window ends | 2026-09-21Synced from sourceCurrent2h ago | — | — |
| Open issues | 1462Synced from sourceCurrent2h ago | 320Synced from sourceCurrent2h ago | 463Synced from sourceCurrent2h ago |
| PyPI package | — | semantic-kernelSynced from sourceCurrent2h ago | crewaiSynced from sourceCurrent2h ago |
| PyPI released | — | 2026-08-06T09:56:42.518861ZSynced from sourceCurrent2h ago | 2026-09-16T22:10:41.471882ZSynced from sourceCurrent2h ago |
| Requires Python | — | >=3.10Synced from sourceCurrent2h ago | <3.14,>=3.10Synced from sourceCurrent2h ago |
| PyPI version | — | 1.44.1Synced from sourceCurrent2h ago | 1.15.22Synced from sourceCurrent2h ago |
| Repository | https://github.com/vercel/aiSynced from sourceCurrent2h ago | https://github.com/microsoft/semantic-kernelSynced from sourceCurrent2h ago | https://github.com/crewAIInc/crewAISynced from sourceCurrent2h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 2h 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.