Compare frameworks
CrewAI vs LangChain 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 | LangChain | AutoGen |
|---|---|---|---|
| Stars | 59,111Synced from sourceCurrent1h ago | 147,178 (highest of the compared values)Synced from sourceCurrent1h ago | 61,194Synced from sourceCurrent1h ago |
| downloads | — | 3,201,198 (highest of the compared values)Synced from sourceCurrent1h ago | 47,487Synced from sourceStale10d ago |
| Last commit | 2026-09-27Synced from sourceCurrent1h ago | 2026-09-27Synced from sourceCurrent1h ago | 2026-04-15Synced from sourceCurrent1h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | MITSynced from sourceCurrent1h ago | MITSynced from sourceCurrent1h ago | CC-BY-4.0Synced from sourceCurrent1h ago |
| Archived | noSynced from sourceCurrent1h ago | noSynced from sourceCurrent1h ago | noSynced from sourceCurrent1h ago |
| Category | multi-agentSeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago |
| Contributors | 340Synced from sourceCurrent1h ago | 3741Synced from sourceCurrent1h ago | 534Synced from sourceCurrent1h ago |
| Forks | 8585Synced from sourceCurrent1h ago | 24634Synced from sourceCurrent1h ago | 9256Synced from sourceCurrent1h ago |
| Maintainer | CrewAISeeded, unreviewedwritten 1mo ago | LangChainSeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago |
| npm downloads, monthly | — | 10682493Synced from sourceCurrent1h ago | — |
| npm downloads, weekly | — | 3201198Synced from sourceCurrent1h ago | — |
| npm package | — | langchainSynced from sourceCurrent1h ago | — |
| npm window ends | — | 2026-09-26Synced from sourceCurrent1h ago | — |
| Open issues | 506Synced from sourceCurrent1h ago | 569Synced from sourceCurrent1h ago | 1105Synced from sourceCurrent1h ago |
| PyPI downloads, monthly | — | — | 263297Synced from sourceStale10d ago |
| PyPI downloads, weekly | — | — | 47487Synced from sourceStale10d ago |
| PyPI package | crewaiSynced from sourceCurrent1h ago | langchainSynced from sourceCurrent1h ago | pyautogenSynced from sourceCurrent1h ago |
| PyPI released | 2026-09-16T22:10:41.471882ZSynced from sourceCurrent1h ago | 2026-09-18T17:31:10.056247ZSynced from sourceCurrent1h ago | 2025-07-15T00:37:26.170442ZSynced from sourceCurrent1h ago |
| Requires Python | <3.14,>=3.10Synced from sourceCurrent1h ago | <4.0.0,>=3.10.0Synced from sourceCurrent1h ago | >=3.10Synced from sourceCurrent1h ago |
| PyPI version | 1.15.22Synced from sourceCurrent1h ago | 1.4.2Synced from sourceCurrent1h ago | 0.10.0Synced from sourceCurrent1h ago |
| Repository | https://github.com/crewAIInc/crewAISynced from sourceCurrent1h ago | https://github.com/langchain-ai/langchainSynced from sourceCurrent1h ago | https://github.com/microsoft/autogenSynced from sourceCurrent1h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 1h 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.