Compare frameworks
CrewAI vs DSPy vs AutoGen
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 | DSPy | AutoGen |
|---|---|---|---|
| Stars | 59,111Synced from sourceCurrent4h ago | 38,388Synced from sourceCurrent4h ago | 61,194 (highest of the compared values)Synced from sourceCurrent4h ago |
| downloads | — | — | 47,487Synced from sourceStale10d ago |
| Last commit | 2026-09-27Synced from sourceCurrent4h ago | 2026-09-27Synced from sourceCurrent4h ago | 2026-04-15Synced from sourceCurrent4h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | MITSynced from sourceCurrent4h ago | MITSynced from sourceCurrent4h ago | CC-BY-4.0Synced from sourceCurrent4h ago |
| Archived | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago |
| Category | multi-agentSeeded, unreviewedwritten 1mo ago | optimisationSeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago |
| Contributors | 340Synced from sourceCurrent4h ago | 461Synced from sourceCurrent4h ago | 534Synced from sourceCurrent4h ago |
| Forks | 8585Synced from sourceCurrent4h ago | 3372Synced from sourceCurrent4h ago | 9256Synced from sourceCurrent4h ago |
| Maintainer | CrewAISeeded, unreviewedwritten 1mo ago | Stanford NLPSeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago |
| Open issues | 506Synced from sourceCurrent4h ago | 739Synced from sourceCurrent4h ago | 1105Synced from sourceCurrent4h ago |
| PyPI downloads, monthly | — | — | 263297Synced from sourceStale10d ago |
| PyPI downloads, weekly | — | — | 47487Synced from sourceStale10d ago |
| PyPI package | crewaiSynced from sourceCurrent4h ago | dspy-aiSynced from sourceCurrent4h ago | pyautogenSynced from sourceCurrent4h ago |
| PyPI released | 2026-09-16T22:10:41.471882ZSynced from sourceCurrent4h ago | 2026-09-25T04:04:30.339197ZSynced from sourceCurrent4h ago | 2025-07-15T00:37:26.170442ZSynced from sourceCurrent4h ago |
| Requires Python | <3.14,>=3.10Synced from sourceCurrent4h ago | >=3.9Synced from sourceCurrent4h ago | >=3.10Synced from sourceCurrent4h ago |
| PyPI version | 1.15.22Synced from sourceCurrent4h ago | 3.4.0Synced from sourceCurrent4h ago | 0.10.0Synced from sourceCurrent4h ago |
| Repository | https://github.com/crewAIInc/crewAISynced from sourceCurrent4h ago | https://github.com/stanfordnlp/dspySynced from sourceCurrent4h ago | https://github.com/microsoft/autogenSynced from sourceCurrent4h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 4h 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.