Compare frameworks
DeepEval vs Vercel AI SDK vs LangGraph
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 | DeepEval | Vercel AI SDK | LangGraph |
|---|---|---|---|
| Stars | 18,419Synced from sourceCurrent3h ago | 26,922Synced from sourceCurrent3h ago | 42,201 (highest of the compared values)Synced from sourceCurrent3h ago |
| downloads | — | 17,883,737 (highest of the compared values)Synced from sourceCurrent3h ago | 2,342,174Synced from sourceCurrent3h ago |
| Last commit | 2026-09-23Synced from sourceCurrent3h ago | 2026-09-24Synced from sourceCurrent3h ago | 2026-09-23Synced from sourceCurrent3h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | typescriptSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | Apache-2.0Synced from sourceCurrent3h ago | — | MITSynced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | evaluationSeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago | orchestrationSeeded, unreviewedwritten 1mo ago |
| Contributors | 337Synced from sourceCurrent3h ago | 715Synced from sourceCurrent3h ago | 287Synced from sourceCurrent3h ago |
| Forks | 1973Synced from sourceCurrent3h ago | 5180Synced from sourceCurrent3h ago | 7139Synced from sourceCurrent3h ago |
| Maintainer | Confident AISeeded, unreviewedwritten 1mo ago | VercelSeeded, unreviewedwritten 1mo ago | LangChainSeeded, unreviewedwritten 1mo ago |
| npm downloads, monthly | — | 87791075Synced from sourceCurrent3h ago | 12112794Synced from sourceCurrent3h ago |
| npm downloads, weekly | — | 17883737Synced from sourceCurrent3h ago | 2342174Synced from sourceCurrent3h ago |
| npm package | — | aiSynced from sourceCurrent3h ago | @langchain/langgraphSynced from sourceCurrent3h ago |
| npm window ends | — | 2026-09-21Synced from sourceCurrent3h ago | 2026-09-21Synced from sourceCurrent3h ago |
| Open issues | 654Synced from sourceCurrent3h ago | 1462Synced from sourceCurrent3h ago | 816Synced from sourceCurrent3h ago |
| PyPI package | deepevalSynced from sourceCurrent3h ago | — | langgraphSynced from sourceCurrent3h ago |
| PyPI released | 2026-09-22T19:26:34.903554ZSynced from sourceCurrent3h ago | — | 2026-09-21T14:43:28.196799ZSynced from sourceCurrent3h ago |
| Requires Python | <4.0,>=3.9Synced from sourceCurrent3h ago | — | >=3.10Synced from sourceCurrent3h ago |
| PyPI version | 4.2.5Synced from sourceCurrent3h ago | — | 1.2.12Synced from sourceCurrent3h ago |
| Repository | https://github.com/confident-ai/deepevalSynced from sourceCurrent3h ago | https://github.com/vercel/aiSynced from sourceCurrent3h ago | https://github.com/langchain-ai/langgraphSynced 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.