Compare frameworks
Semantic Kernel vs CrewAI vs Haystack
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 | Semantic Kernel | CrewAI | Haystack |
|---|---|---|---|
| Stars | 28,745Synced from sourceCurrent3h ago | 60,624 (highest of the compared values)Synced from sourceCurrent3h ago | 26,943Synced from sourceCurrent3h ago |
| Last commit | 2026-11-07Synced from sourceCurrent3h ago | 2026-11-08Synced from sourceCurrent3h ago | 2026-11-07Synced from sourceCurrent3h ago |
| Language | csharpSeeded, unreviewedwritten 2mo ago | pythonSeeded, unreviewedwritten 2mo ago | pythonSeeded, unreviewedwritten 2mo ago |
| Licence | MITSynced from sourceCurrent3h ago | MITSynced from sourceCurrent3h ago | Apache-2.0Synced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | orchestrationSeeded, unreviewedwritten 2mo ago | multi-agentSeeded, unreviewedwritten 2mo ago | ragSeeded, unreviewedwritten 2mo ago |
| Contributors | 460Synced from sourceCurrent3h ago | 367Synced from sourceCurrent3h ago | 556Synced from sourceCurrent3h ago |
| Forks | 4856Synced from sourceCurrent3h ago | 9090Synced from sourceCurrent3h ago | 3406Synced from sourceCurrent3h ago |
| Maintainer | MicrosoftSeeded, unreviewedwritten 2mo ago | CrewAISeeded, unreviewedwritten 2mo ago | deepsetSeeded, unreviewedwritten 2mo ago |
| Open issues | 315Synced from sourceCurrent3h ago | 1196Synced from sourceCurrent3h ago | 173Synced from sourceCurrent3h ago |
| PyPI package | semantic-kernelSynced from sourceCurrent3h ago | crewaiSynced from sourceCurrent3h ago | haystack-aiSynced from sourceCurrent3h ago |
| PyPI released | 2026-11-05T10:58:35.730388ZSynced from sourceCurrent3h ago | 2026-11-07T02:18:43.372746ZSynced from sourceCurrent3h ago | 2026-10-21T19:10:50.167432ZSynced from sourceCurrent3h ago |
| Requires Python | >=3.11Synced from sourceCurrent3h ago | <3.14,>=3.10Synced from sourceCurrent3h ago | >=3.11Synced from sourceCurrent3h ago |
| PyPI version | 1.47.0Synced from sourceCurrent3h ago | 1.15.37Synced from sourceCurrent3h ago | 3.4.1Synced from sourceCurrent3h ago |
| Repository | https://github.com/microsoft/semantic-kernelSynced from sourceCurrent3h ago | https://github.com/crewAIInc/crewAISynced from sourceCurrent3h ago | https://github.com/deepset-ai/haystackSynced from sourceCurrent3h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 3h 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.