Compare frameworks
DeepEval vs Mastra vs Semantic Kernel
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 | DeepEval | Mastra | Semantic Kernel |
|---|---|---|---|
| Stars | 19,359Synced from sourceCurrent3h ago | 29,400 (highest of the compared values)Synced from sourceCurrent3h ago | 28,745Synced from sourceCurrent3h ago |
| downloads | — | 3,150,478Synced from sourceCurrent3h ago | — |
| Last commit | 2026-11-07Synced from sourceCurrent3h ago | 2026-11-08Synced from sourceCurrent3h ago | 2026-11-07Synced from sourceCurrent3h ago |
| Language | pythonSeeded, unreviewedwritten 2mo ago | typescriptSeeded, unreviewedwritten 2mo ago | csharpSeeded, unreviewedwritten 2mo ago |
| Licence | Apache-2.0Synced from sourceCurrent3h ago | — | MITSynced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | evaluationSeeded, unreviewedwritten 2mo ago | orchestrationSeeded, unreviewedwritten 2mo ago | orchestrationSeeded, unreviewedwritten 2mo ago |
| Contributors | 348Synced from sourceCurrent3h ago | 701Synced from sourceCurrent3h ago | 460Synced from sourceCurrent3h ago |
| Forks | 2177Synced from sourceCurrent3h ago | 3085Synced from sourceCurrent3h ago | 4856Synced from sourceCurrent3h ago |
| Maintainer | Confident AISeeded, unreviewedwritten 2mo ago | MastraSeeded, unreviewedwritten 2mo ago | MicrosoftSeeded, unreviewedwritten 2mo ago |
| npm downloads, monthly | — | 10391822Synced from sourceCurrent3h ago | — |
| npm downloads, weekly | — | 3150478Synced from sourceCurrent3h ago | — |
| npm package | — | @mastra/coreSynced from sourceCurrent3h ago | — |
| npm window ends | — | 2026-11-06Synced from sourceCurrent3h ago | — |
| Open issues | 814Synced from sourceCurrent3h ago | 820Synced from sourceCurrent3h ago | 315Synced from sourceCurrent3h ago |
| PyPI package | deepevalSynced from sourceCurrent3h ago | — | semantic-kernelSynced from sourceCurrent3h ago |
| PyPI released | 2026-11-04T11:29:23.499144ZSynced from sourceCurrent3h ago | — | 2026-11-05T10:58:35.730388ZSynced from sourceCurrent3h ago |
| Requires Python | <4.0,>=3.9Synced from sourceCurrent3h ago | — | >=3.11Synced from sourceCurrent3h ago |
| PyPI version | 4.3.3Synced from sourceCurrent3h ago | — | 1.47.0Synced from sourceCurrent3h ago |
| Repository | https://github.com/confident-ai/deepevalSynced from sourceCurrent3h ago | https://github.com/mastra-ai/mastraSynced from sourceCurrent3h ago | https://github.com/microsoft/semantic-kernelSynced 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.