Compare frameworks
Letta vs AutoGen vs Vercel AI SDK
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 | AutoGen | Vercel AI SDK |
|---|---|---|---|
| Stars | 24,864Synced from sourceCurrent4h ago | 61,130 (highest of the compared values)Synced from sourceCurrent4h ago | 26,922Synced from sourceCurrent4h ago |
| downloads | — | 47,487Synced from sourceAging6d ago | 17,883,737 (highest of the compared values)Synced from sourceCurrent4h ago |
| Last commit | 2026-09-10Synced from sourceCurrent4h ago | 2026-04-15Synced from sourceCurrent4h ago | 2026-09-24Synced from sourceCurrent4h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | typescriptSeeded, unreviewedwritten 1mo ago |
| Licence | Apache-2.0Synced from sourceCurrent4h ago | CC-BY-4.0Synced from sourceCurrent4h ago | — |
| Archived | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago |
| Category | memorySeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago |
| Contributors | 155Synced from sourceCurrent4h ago | 534Synced from sourceCurrent4h ago | 715Synced from sourceCurrent4h ago |
| Forks | 2628Synced from sourceCurrent4h ago | 9246Synced from sourceCurrent4h ago | 5180Synced from sourceCurrent4h ago |
| Maintainer | LettaSeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago | VercelSeeded, unreviewedwritten 1mo ago |
| npm downloads, monthly | — | — | 87791075Synced from sourceCurrent4h ago |
| npm downloads, weekly | — | — | 17883737Synced from sourceCurrent4h ago |
| npm package | — | — | aiSynced from sourceCurrent4h ago |
| npm window ends | — | — | 2026-09-21Synced from sourceCurrent4h ago |
| Open issues | 0Synced from sourceCurrent4h ago | 1098Synced from sourceCurrent4h ago | 1462Synced from sourceCurrent4h ago |
| PyPI downloads, monthly | — | 263297Synced from sourceAging6d ago | — |
| PyPI downloads, weekly | — | 47487Synced from sourceAging6d ago | — |
| PyPI package | lettaSynced from sourceCurrent4h ago | pyautogenSynced from sourceCurrent4h ago | — |
| PyPI released | 2026-09-23T23:59:05.225455ZSynced from sourceCurrent4h ago | 2025-07-15T00:37:26.170442ZSynced from sourceCurrent4h ago | — |
| Requires Python | >=3.9Synced from sourceCurrent4h ago | >=3.10Synced from sourceCurrent4h ago | — |
| PyPI version | 0.33.0Synced from sourceCurrent4h ago | 0.10.0Synced from sourceCurrent4h ago | — |
| Repository | https://github.com/letta-ai/lettaSynced from sourceCurrent4h ago | https://github.com/microsoft/autogenSynced from sourceCurrent4h ago | https://github.com/vercel/aiSynced from sourceCurrent4h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 4h 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.