Compare frameworks
Letta vs Vercel AI SDK vs LlamaIndex
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 | Vercel AI SDK | LlamaIndex |
|---|---|---|---|
| Stars | 24,864Synced from sourceCurrent2h ago | 26,922Synced from sourceCurrent2h ago | 52,306 (highest of the compared values)Synced from sourceCurrent2h ago |
| downloads | — | 17,883,737 (highest of the compared values)Synced from sourceCurrent2h ago | 83,631Synced from sourceCurrent2h ago |
| Last commit | 2026-09-10Synced from sourceCurrent2h ago | 2026-09-24Synced from sourceCurrent2h ago | 2026-09-24Synced from sourceCurrent2h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | typescriptSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | Apache-2.0Synced from sourceCurrent2h ago | — | MITSynced from sourceCurrent2h ago |
| Archived | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago |
| Category | memorySeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago | ragSeeded, unreviewedwritten 1mo ago |
| Contributors | 155Synced from sourceCurrent2h ago | 715Synced from sourceCurrent2h ago | 1999Synced from sourceCurrent2h ago |
| Forks | 2628Synced from sourceCurrent2h ago | 5180Synced from sourceCurrent2h ago | 8203Synced from sourceCurrent2h ago |
| Maintainer | LettaSeeded, unreviewedwritten 1mo ago | VercelSeeded, unreviewedwritten 1mo ago | LlamaIndexSeeded, unreviewedwritten 1mo ago |
| npm downloads, monthly | — | 87791075Synced from sourceCurrent2h ago | 429018Synced from sourceCurrent2h ago |
| npm downloads, weekly | — | 17883737Synced from sourceCurrent2h ago | 83631Synced from sourceCurrent2h ago |
| npm package | — | aiSynced from sourceCurrent2h ago | llamaindexSynced from sourceCurrent2h ago |
| npm window ends | — | 2026-09-21Synced from sourceCurrent2h ago | 2026-09-21Synced from sourceCurrent2h ago |
| Open issues | 0Synced from sourceCurrent2h ago | 1462Synced from sourceCurrent2h ago | 849Synced from sourceCurrent2h ago |
| PyPI package | lettaSynced from sourceCurrent2h ago | — | llama-indexSynced from sourceCurrent2h ago |
| PyPI released | 2026-09-23T23:59:05.225455ZSynced from sourceCurrent2h ago | — | 2026-09-21T16:22:20.056831ZSynced from sourceCurrent2h ago |
| Requires Python | >=3.9Synced from sourceCurrent2h ago | — | <4.0,>=3.10Synced from sourceCurrent2h ago |
| PyPI version | 0.33.0Synced from sourceCurrent2h ago | — | 0.14.25Synced from sourceCurrent2h ago |
| Repository | https://github.com/letta-ai/lettaSynced from sourceCurrent2h ago | https://github.com/vercel/aiSynced from sourceCurrent2h ago | https://github.com/run-llama/llama_indexSynced 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.