Compare frameworks
CrewAI vs Letta vs DeepEval
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 | Letta | DeepEval |
|---|---|---|---|
| Stars | 60,624 (highest of the compared values)Synced from sourceCurrent3h ago | 25,382Synced from sourceCurrent3h ago | 19,359Synced from sourceCurrent3h ago |
| Last commit | 2026-11-08Synced from sourceCurrent3h ago | 2026-10-18Synced from sourceCurrent3h ago | 2026-11-07Synced from sourceCurrent3h ago |
| Language | pythonSeeded, unreviewedwritten 2mo ago | pythonSeeded, unreviewedwritten 2mo ago | pythonSeeded, unreviewedwritten 2mo ago |
| Licence | MITSynced from sourceCurrent3h ago | Apache-2.0Synced from sourceCurrent3h ago | Apache-2.0Synced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | multi-agentSeeded, unreviewedwritten 2mo ago | memorySeeded, unreviewedwritten 2mo ago | evaluationSeeded, unreviewedwritten 2mo ago |
| Contributors | 367Synced from sourceCurrent3h ago | 155Synced from sourceCurrent3h ago | 348Synced from sourceCurrent3h ago |
| Forks | 9090Synced from sourceCurrent3h ago | 2667Synced from sourceCurrent3h ago | 2177Synced from sourceCurrent3h ago |
| Maintainer | CrewAISeeded, unreviewedwritten 2mo ago | LettaSeeded, unreviewedwritten 2mo ago | Confident AISeeded, unreviewedwritten 2mo ago |
| Open issues | 1196Synced from sourceCurrent3h ago | 0Synced from sourceCurrent3h ago | 814Synced from sourceCurrent3h ago |
| PyPI package | crewaiSynced from sourceCurrent3h ago | lettaSynced from sourceCurrent3h ago | deepevalSynced from sourceCurrent3h ago |
| PyPI released | 2026-11-07T02:18:43.372746ZSynced from sourceCurrent3h ago | 2026-10-12T20:47:35.858621ZSynced from sourceCurrent3h ago | 2026-11-04T11:29:23.499144ZSynced from sourceCurrent3h ago |
| Requires Python | <3.14,>=3.10Synced from sourceCurrent3h ago | >=3.9Synced from sourceCurrent3h ago | <4.0,>=3.9Synced from sourceCurrent3h ago |
| PyPI version | 1.15.37Synced from sourceCurrent3h ago | 0.34.12Synced from sourceCurrent3h ago | 4.3.3Synced from sourceCurrent3h ago |
| Repository | https://github.com/crewAIInc/crewAISynced from sourceCurrent3h ago | https://github.com/letta-ai/lettaSynced from sourceCurrent3h ago | https://github.com/confident-ai/deepevalSynced 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.