Compare frameworks
AutoGen vs CrewAI vs Pydantic AI
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 | AutoGen | CrewAI | Pydantic AI |
|---|---|---|---|
| Stars | 61,194 (highest of the compared values)Synced from sourceCurrent3h ago | 59,111Synced from sourceCurrent3h ago | 20,220Synced from sourceCurrent3h ago |
| downloads | 47,487Synced from sourceStale10d ago | — | 3,076,771 (highest of the compared values)Synced from sourceStale1mo ago· past SLA |
| Last commit | 2026-04-15Synced from sourceCurrent3h ago | 2026-09-27Synced from sourceCurrent3h ago | 2026-09-28Synced from sourceCurrent3h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | CC-BY-4.0Synced 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 | multi-agentSeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago | structured-outputSeeded, unreviewedwritten 1mo ago |
| Contributors | 534Synced from sourceCurrent3h ago | 340Synced from sourceCurrent3h ago | 609Synced from sourceCurrent3h ago |
| Forks | 9256Synced from sourceCurrent3h ago | 8585Synced from sourceCurrent3h ago | 2796Synced from sourceCurrent3h ago |
| Maintainer | MicrosoftSeeded, unreviewedwritten 1mo ago | CrewAISeeded, unreviewedwritten 1mo ago | PydanticSeeded, unreviewedwritten 1mo ago |
| Open issues | 1105Synced from sourceCurrent3h ago | 506Synced from sourceCurrent3h ago | 1013Synced from sourceCurrent3h ago |
| PyPI downloads, monthly | 263297Synced from sourceStale10d ago | — | 13478631Synced from sourceStale1mo ago· past SLA |
| PyPI downloads, weekly | 47487Synced from sourceStale10d ago | — | 3076771Synced from sourceStale1mo ago· past SLA |
| PyPI package | pyautogenSynced from sourceCurrent3h ago | crewaiSynced from sourceCurrent3h ago | pydantic-aiSynced from sourceCurrent3h ago |
| PyPI released | 2025-07-15T00:37:26.170442ZSynced from sourceCurrent3h ago | 2026-09-16T22:10:41.471882ZSynced from sourceCurrent3h ago | 2026-09-25T23:32:17.554286ZSynced from sourceCurrent3h ago |
| Requires Python | >=3.10Synced from sourceCurrent3h ago | <3.14,>=3.10Synced from sourceCurrent3h ago | >=3.10Synced from sourceCurrent3h ago |
| PyPI version | 0.10.0Synced from sourceCurrent3h ago | 1.15.22Synced from sourceCurrent3h ago | 2.51.0Synced from sourceCurrent3h ago |
| Repository | https://github.com/microsoft/autogenSynced from sourceCurrent3h ago | https://github.com/crewAIInc/crewAISynced from sourceCurrent3h ago | https://github.com/pydantic/pydantic-aiSynced 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.