DSPy

Stanford framework for programming LLMs declaratively with signatures, modules, and prompt optimizers.

agent-frameworksRecently released
59
Hero Score
Popularity
64
Performance
70
Ecosystem
50
Maturity
61
Dev Experience
50
⭐ 34,760 stars⬇ 231.6K downloads/wkFirst release: Aug 2023Last release: May 2026
Async Support: YesPlugin Extensions: MediumSpeed: MediumDoc Quality: HighLearning Curve: Hard

Pros

  • Declarative, composable signatures and modules
  • Automatic prompt and weight optimization
  • Research-grade with strong academic backing

Cons

  • Different paradigm than typical prompt engineering
  • Smaller community than mainstream agent frameworks
  • Debugging optimizers can be opaque

Alternatives in agent-frameworks

Compare Python Packages with ease.