Compare frameworks
DeepEval vs LangGraph vs DSPy
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 | LangGraph | DSPy |
|---|---|---|---|
| Stars | 19,359Synced from sourceCurrent3h ago | 44,631 (highest of the compared values)Synced from sourceCurrent3h ago | 38,971Synced from sourceCurrent3h ago |
| downloads | — | 4,881,657Synced from sourceCurrent3h ago | — |
| Last commit | 2026-11-07Synced from sourceCurrent3h ago | 2026-11-08Synced from sourceCurrent3h ago | 2026-11-07Synced 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 | MITSynced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | evaluationSeeded, unreviewedwritten 2mo ago | orchestrationSeeded, unreviewedwritten 2mo ago | optimisationSeeded, unreviewedwritten 2mo ago |
| Contributors | 348Synced from sourceCurrent3h ago | 294Synced from sourceCurrent3h ago | 484Synced from sourceCurrent3h ago |
| Forks | 2177Synced from sourceCurrent3h ago | 7690Synced from sourceCurrent3h ago | 3491Synced from sourceCurrent3h ago |
| Maintainer | Confident AISeeded, unreviewedwritten 2mo ago | LangChainSeeded, unreviewedwritten 2mo ago | Stanford NLPSeeded, unreviewedwritten 2mo ago |
| npm downloads, monthly | — | 16705433Synced from sourceCurrent3h ago | — |
| npm downloads, weekly | — | 4881657Synced from sourceCurrent3h ago | — |
| npm package | — | @langchain/langgraphSynced from sourceCurrent3h ago | — |
| npm window ends | — | 2026-11-06Synced from sourceCurrent3h ago | — |
| Open issues | 814Synced from sourceCurrent3h ago | 475Synced from sourceCurrent3h ago | 770Synced from sourceCurrent3h ago |
| PyPI package | deepevalSynced from sourceCurrent3h ago | langgraphSynced from sourceCurrent3h ago | dspy-aiSynced from sourceCurrent3h ago |
| PyPI released | 2026-11-04T11:29:23.499144ZSynced from sourceCurrent3h ago | 2026-11-05T02:20:37.999716ZSynced from sourceCurrent3h ago | 2026-10-12T23:07:31.783801ZSynced from sourceCurrent3h ago |
| Requires Python | <4.0,>=3.9Synced from sourceCurrent3h ago | >=3.10Synced from sourceCurrent3h ago | >=3.9Synced from sourceCurrent3h ago |
| PyPI version | 4.3.3Synced from sourceCurrent3h ago | 1.2.20Synced from sourceCurrent3h ago | 3.4.1Synced from sourceCurrent3h ago |
| Repository | https://github.com/confident-ai/deepevalSynced from sourceCurrent3h ago | https://github.com/langchain-ai/langgraphSynced from sourceCurrent3h ago | https://github.com/stanfordnlp/dspySynced 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.