Compare frameworks
Letta vs Pydantic AI vs AutoGen
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 | Pydantic AI | AutoGen |
|---|---|---|---|
| Stars | 25,382Synced from sourceCurrent3h ago | 21,085Synced from sourceCurrent3h ago | 61,743 (highest of the compared values)Synced from sourceCurrent3h ago |
| downloads | — | 3,076,771 (highest of the compared values)Synced from sourceStale2mo ago· past SLA | 47,487Synced from sourceStale1mo ago· past SLA |
| Last commit | 2026-10-18Synced from sourceCurrent3h ago | 2026-11-08Synced from sourceCurrent3h ago | 2026-10-28Synced 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 | CC-BY-4.0Synced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | memorySeeded, unreviewedwritten 2mo ago | structured-outputSeeded, unreviewedwritten 2mo ago | multi-agentSeeded, unreviewedwritten 2mo ago |
| Contributors | 155Synced from sourceCurrent3h ago | 658Synced from sourceCurrent3h ago | 536Synced from sourceCurrent3h ago |
| Forks | 2667Synced from sourceCurrent3h ago | 3127Synced from sourceCurrent3h ago | 9380Synced from sourceCurrent3h ago |
| Maintainer | LettaSeeded, unreviewedwritten 2mo ago | PydanticSeeded, unreviewedwritten 2mo ago | MicrosoftSeeded, unreviewedwritten 2mo ago |
| Open issues | 0Synced from sourceCurrent3h ago | 1825Synced from sourceCurrent3h ago | 1165Synced from sourceCurrent3h ago |
| PyPI downloads, monthly | — | 13478631Synced from sourceStale2mo ago· past SLA | 263297Synced from sourceStale1mo ago· past SLA |
| PyPI downloads, weekly | — | 3076771Synced from sourceStale2mo ago· past SLA | 47487Synced from sourceStale1mo ago· past SLA |
| PyPI package | lettaSynced from sourceCurrent3h ago | pydantic-aiSynced from sourceCurrent3h ago | pyautogenSynced from sourceCurrent3h ago |
| PyPI released | 2026-10-12T20:47:35.858621ZSynced from sourceCurrent3h ago | 2026-11-04T10:28:38.510837ZSynced from sourceCurrent3h ago | 2025-07-15T00:37:26.170442ZSynced from sourceCurrent3h ago |
| Requires Python | >=3.9Synced from sourceCurrent3h ago | >=3.11Synced from sourceCurrent3h ago | >=3.10Synced from sourceCurrent3h ago |
| PyPI version | 0.34.12Synced from sourceCurrent3h ago | 2.66.0Synced from sourceCurrent3h ago | 0.10.0Synced from sourceCurrent3h ago |
| Repository | https://github.com/letta-ai/lettaSynced from sourceCurrent3h ago | https://github.com/pydantic/pydantic-aiSynced from sourceCurrent3h ago | https://github.com/microsoft/autogenSynced 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.