Compare frameworks
DSPy vs DeepEval 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 | DSPy | DeepEval | AutoGen |
|---|---|---|---|
| Stars | 38,243Synced from sourceCurrent2h ago | 18,419Synced from sourceCurrent2h ago | 61,130 (highest of the compared values)Synced from sourceCurrent2h ago |
| downloads | — | — | 47,487Synced from sourceAging6d ago |
| Last commit | 2026-09-23Synced from sourceCurrent2h ago | 2026-09-23Synced from sourceCurrent2h ago | 2026-04-15Synced from sourceCurrent2h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | MITSynced from sourceCurrent2h ago | Apache-2.0Synced from sourceCurrent2h ago | CC-BY-4.0Synced from sourceCurrent2h ago |
| Archived | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago |
| Category | optimisationSeeded, unreviewedwritten 1mo ago | evaluationSeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago |
| Contributors | 459Synced from sourceCurrent2h ago | 337Synced from sourceCurrent2h ago | 534Synced from sourceCurrent2h ago |
| Forks | 3353Synced from sourceCurrent2h ago | 1973Synced from sourceCurrent2h ago | 9246Synced from sourceCurrent2h ago |
| Maintainer | Stanford NLPSeeded, unreviewedwritten 1mo ago | Confident AISeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago |
| Open issues | 726Synced from sourceCurrent2h ago | 654Synced from sourceCurrent2h ago | 1098Synced from sourceCurrent2h ago |
| PyPI downloads, monthly | — | — | 263297Synced from sourceAging6d ago |
| PyPI downloads, weekly | — | — | 47487Synced from sourceAging6d ago |
| PyPI package | dspy-aiSynced from sourceCurrent2h ago | deepevalSynced from sourceCurrent2h ago | pyautogenSynced from sourceCurrent2h ago |
| PyPI released | 2026-08-21T23:06:20.945191ZSynced from sourceCurrent2h ago | 2026-09-22T19:26:34.903554ZSynced from sourceCurrent2h ago | 2025-07-15T00:37:26.170442ZSynced from sourceCurrent2h ago |
| Requires Python | >=3.9Synced from sourceCurrent2h ago | <4.0,>=3.9Synced from sourceCurrent2h ago | >=3.10Synced from sourceCurrent2h ago |
| PyPI version | 3.3.1Synced from sourceCurrent2h ago | 4.2.5Synced from sourceCurrent2h ago | 0.10.0Synced from sourceCurrent2h ago |
| Repository | https://github.com/stanfordnlp/dspySynced from sourceCurrent2h ago | https://github.com/confident-ai/deepevalSynced from sourceCurrent2h ago | https://github.com/microsoft/autogenSynced 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.