Compare frameworks
Letta vs CrewAI vs LangChain
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 | Letta | CrewAI | LangChain |
|---|---|---|---|
| Stars | 25,382Synced from sourceCurrent3h ago | 60,624Synced from sourceCurrent3h ago | 149,181 (highest of the compared values)Synced from sourceCurrent3h ago |
| downloads | — | — | 4,045,383Synced from sourceCurrent3h ago |
| Last commit | 2026-10-18Synced from sourceCurrent3h ago | 2026-11-08Synced from sourceCurrent3h ago | 2026-11-07Synced from sourceCurrent3h ago |
| Language | pythonSeeded, unreviewedwritten 2mo ago | pythonSeeded, unreviewedwritten 2mo ago | pythonSeeded, unreviewedwritten 2mo ago |
| Licence | Apache-2.0Synced 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 | memorySeeded, unreviewedwritten 2mo ago | multi-agentSeeded, unreviewedwritten 2mo ago | orchestrationSeeded, unreviewedwritten 2mo ago |
| Contributors | 155Synced from sourceCurrent3h ago | 367Synced from sourceCurrent3h ago | 3751Synced from sourceCurrent3h ago |
| Forks | 2667Synced from sourceCurrent3h ago | 9090Synced from sourceCurrent3h ago | 25088Synced from sourceCurrent3h ago |
| Maintainer | LettaSeeded, unreviewedwritten 2mo ago | CrewAISeeded, unreviewedwritten 2mo ago | LangChainSeeded, unreviewedwritten 2mo ago |
| npm downloads, monthly | — | — | 13919147Synced from sourceCurrent3h ago |
| npm downloads, weekly | — | — | 4045383Synced from sourceCurrent3h ago |
| npm package | — | — | langchainSynced from sourceCurrent3h ago |
| npm window ends | — | — | 2026-11-06Synced from sourceCurrent3h ago |
| Open issues | 0Synced from sourceCurrent3h ago | 1196Synced from sourceCurrent3h ago | 727Synced from sourceCurrent3h ago |
| PyPI package | lettaSynced from sourceCurrent3h ago | crewaiSynced from sourceCurrent3h ago | langchainSynced from sourceCurrent3h ago |
| PyPI released | 2026-10-12T20:47:35.858621ZSynced from sourceCurrent3h ago | 2026-11-07T02:18:43.372746ZSynced from sourceCurrent3h ago | 2026-11-04T17:07:20.201103ZSynced from sourceCurrent3h ago |
| Requires Python | >=3.9Synced from sourceCurrent3h ago | <3.14,>=3.10Synced from sourceCurrent3h ago | <4.0.0,>=3.10.0Synced from sourceCurrent3h ago |
| PyPI version | 0.34.12Synced from sourceCurrent3h ago | 1.15.37Synced from sourceCurrent3h ago | 1.4.9Synced from sourceCurrent3h ago |
| Repository | https://github.com/letta-ai/lettaSynced from sourceCurrent3h ago | https://github.com/crewAIInc/crewAISynced from sourceCurrent3h ago | https://github.com/langchain-ai/langchainSynced 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.