Compare frameworks
Pydantic AI vs Letta vs smolagents
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 | Letta | smolagents |
|---|---|---|---|
| Stars | 20,133Synced from sourceCurrent2h ago | 24,864Synced from sourceCurrent2h ago | 29,463 (highest of the compared values)Synced from sourceCurrent2h ago |
| downloads | 3,076,771 (highest of the compared values)Synced from sourceStale1mo ago· past SLA | — | 132,630Synced from sourceStale1mo ago· past SLA |
| Last commit | 2026-09-24Synced from sourceCurrent2h ago | 2026-09-10Synced from sourceCurrent2h ago | 2026-09-23Synced from sourceCurrent2h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | MITSynced from sourceCurrent2h ago | Apache-2.0Synced from sourceCurrent2h ago | Apache-2.0Synced from sourceCurrent2h ago |
| Archived | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago |
| Category | structured-outputSeeded, unreviewedwritten 1mo ago | memorySeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago |
| Contributors | 589Synced from sourceCurrent2h ago | 155Synced from sourceCurrent2h ago | 208Synced from sourceCurrent2h ago |
| Forks | 2768Synced from sourceCurrent2h ago | 2628Synced from sourceCurrent2h ago | 2991Synced from sourceCurrent2h ago |
| Maintainer | PydanticSeeded, unreviewedwritten 1mo ago | LettaSeeded, unreviewedwritten 1mo ago | Hugging FaceSeeded, unreviewedwritten 1mo ago |
| Open issues | 965Synced from sourceCurrent2h ago | 0Synced from sourceCurrent2h ago | 827Synced from sourceCurrent2h ago |
| PyPI downloads, monthly | 13478631Synced from sourceStale1mo ago· past SLA | — | 614573Synced from sourceStale1mo ago· past SLA |
| PyPI downloads, weekly | 3076771Synced from sourceStale1mo ago· past SLA | — | 132630Synced from sourceStale1mo ago· past SLA |
| PyPI package | pydantic-aiSynced from sourceCurrent2h ago | lettaSynced from sourceCurrent2h ago | smolagentsSynced from sourceCurrent2h ago |
| PyPI released | 2026-09-24T03:23:01.147978ZSynced from sourceCurrent2h ago | 2026-09-23T23:59:05.225455ZSynced from sourceCurrent2h ago | 2026-05-29T05:08:43.280962ZSynced from sourceCurrent2h ago |
| Requires Python | >=3.10Synced from sourceCurrent2h ago | >=3.9Synced from sourceCurrent2h ago | >=3.10Synced from sourceCurrent2h ago |
| PyPI version | 2.49.0Synced from sourceCurrent2h ago | 0.33.0Synced from sourceCurrent2h ago | 1.26.0Synced from sourceCurrent2h ago |
| Repository | https://github.com/pydantic/pydantic-aiSynced from sourceCurrent2h ago | https://github.com/letta-ai/lettaSynced from sourceCurrent2h ago | https://github.com/huggingface/smolagentsSynced from sourceCurrent2h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 2h 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.