Compare frameworks
Pydantic AI vs Agno 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 | Pydantic AI | Agno | DeepEval |
|---|---|---|---|
| Stars | 20,220Synced from sourceCurrent3h ago | 42,358 (highest of the compared values)Synced from sourceCurrent3h ago | 18,476Synced from sourceCurrent3h ago |
| downloads | 3,076,771 (highest of the compared values)Synced from sourceStale1mo ago· past SLA | 520,626Synced from sourceStale1mo ago· past SLA | — |
| Last commit | 2026-09-28Synced from sourceCurrent3h ago | 2026-09-28Synced from sourceCurrent3h ago | 2026-09-25Synced from sourceCurrent3h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo 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 | structured-outputSeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago | evaluationSeeded, unreviewedwritten 1mo ago |
| Contributors | 609Synced from sourceCurrent3h ago | 585Synced from sourceCurrent3h ago | 337Synced from sourceCurrent3h ago |
| Forks | 2796Synced from sourceCurrent3h ago | 6023Synced from sourceCurrent3h ago | 1989Synced from sourceCurrent3h ago |
| Maintainer | PydanticSeeded, unreviewedwritten 1mo ago | AgnoSeeded, unreviewedwritten 1mo ago | Confident AISeeded, unreviewedwritten 1mo ago |
| Open issues | 1013Synced from sourceCurrent3h ago | 1689Synced from sourceCurrent3h ago | 676Synced from sourceCurrent3h ago |
| PyPI downloads, monthly | 13478631Synced from sourceStale1mo ago· past SLA | 2183543Synced from sourceStale1mo ago· past SLA | — |
| PyPI downloads, weekly | 3076771Synced from sourceStale1mo ago· past SLA | 520626Synced from sourceStale1mo ago· past SLA | — |
| PyPI package | pydantic-aiSynced from sourceCurrent3h ago | agnoSynced from sourceCurrent3h ago | deepevalSynced from sourceCurrent3h ago |
| PyPI released | 2026-09-25T23:32:17.554286ZSynced from sourceCurrent3h ago | 2026-09-23T13:15:37.685447ZSynced from sourceCurrent3h ago | 2026-09-24T09:31:55.310624ZSynced from sourceCurrent3h ago |
| Requires Python | >=3.10Synced from sourceCurrent3h ago | <4,>=3.9Synced from sourceCurrent3h ago | <4.0,>=3.9Synced from sourceCurrent3h ago |
| PyPI version | 2.51.0Synced from sourceCurrent3h ago | 3.0.11Synced from sourceCurrent3h ago | 4.2.6Synced from sourceCurrent3h ago |
| Repository | https://github.com/pydantic/pydantic-aiSynced from sourceCurrent3h ago | https://github.com/agno-agi/agnoSynced 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.