Compare frameworks
Semantic Kernel vs CrewAI vs LlamaIndex
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 | LlamaIndex |
|---|---|---|---|
| Stars | 28,608Synced from sourceCurrent3h ago | 59,111 (highest of the compared values)Synced from sourceCurrent3h ago | 52,334Synced from sourceCurrent3h ago |
| downloads | — | — | 149,503Synced from sourceCurrent3h ago |
| Last commit | 2026-09-19Synced from sourceCurrent3h ago | 2026-09-27Synced from sourceCurrent3h ago | 2026-09-27Synced from sourceCurrent3h ago |
| Language | csharpSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | MITSynced from sourceCurrent3h ago | MITSynced from sourceCurrent3h ago | MITSynced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | orchestrationSeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago | ragSeeded, unreviewedwritten 1mo ago |
| Contributors | 416Synced from sourceCurrent3h ago | 340Synced from sourceCurrent3h ago | 2001Synced from sourceCurrent3h ago |
| Forks | 4793Synced from sourceCurrent3h ago | 8585Synced from sourceCurrent3h ago | 8232Synced from sourceCurrent3h ago |
| Maintainer | MicrosoftSeeded, unreviewedwritten 1mo ago | CrewAISeeded, unreviewedwritten 1mo ago | LlamaIndexSeeded, unreviewedwritten 1mo ago |
| npm downloads, monthly | — | — | 445795Synced from sourceCurrent3h ago |
| npm downloads, weekly | — | — | 149503Synced from sourceCurrent3h ago |
| npm package | — | — | llamaindexSynced from sourceCurrent3h ago |
| npm window ends | — | — | 2026-09-26Synced from sourceCurrent3h ago |
| Open issues | 338Synced from sourceCurrent3h ago | 506Synced from sourceCurrent3h ago | 896Synced from sourceCurrent3h ago |
| PyPI package | semantic-kernelSynced from sourceCurrent3h ago | crewaiSynced from sourceCurrent3h ago | llama-indexSynced from sourceCurrent3h ago |
| PyPI released | 2026-08-06T09:56:42.518861ZSynced from sourceCurrent3h ago | 2026-09-16T22:10:41.471882ZSynced from sourceCurrent3h ago | 2026-09-21T16:22:20.056831ZSynced from sourceCurrent3h ago |
| Requires Python | >=3.10Synced from sourceCurrent3h ago | <3.14,>=3.10Synced from sourceCurrent3h ago | <4.0,>=3.10Synced from sourceCurrent3h ago |
| PyPI version | 1.44.1Synced from sourceCurrent3h ago | 1.15.22Synced from sourceCurrent3h ago | 0.14.25Synced from sourceCurrent3h ago |
| Repository | https://github.com/microsoft/semantic-kernelSynced from sourceCurrent3h ago | https://github.com/crewAIInc/crewAISynced from sourceCurrent3h ago | https://github.com/run-llama/llama_indexSynced 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.