DSPy
Stanford NLPStanford framework for programming rather than prompting language models. Typed declarative modules - signatures with Predict, ChainOfThought and ReAct - compose into pipelines, which optimizers such as MIPROv2, BootstrapFewShot and GEPA then auto-tune against a metric, adjusting prompts or weights.
The project sells no commercial service alongside the framework. Verified 2026-08-13 via the stanfordnlp/dspy repository.
Openness
5 high confidence- license
- MIT(OSI)
- source
- public
- core-gated
- ungated
Fully MIT with no commercial tier.
- https://github.com/stanfordnlp/dspy recorded 2026-08-13
MIT license, full public source for the framework, 37.2k stars and 3.2k forks; no commercial tier or enterprise directory
Adoption
4 high confidence6,589,078 PyPI downloads in the trailing 30 days for dspy. Bands at level 4 (1M-10M) on the software and model adoption scale. A widely used prompt-programming framework.
- https://pypistats.org/api/packages/dspy/recent recorded 2026-08-12
6,589,078 downloads in the trailing 30 days for dspy
Capability
4 high confidenceBest-in-class on prompt-optimization/compilation; thinner multi-agent coordination than CrewAI/AutoGen.
- https://github.com/stanfordnlp/dspy recorded 2026-08-13
declarative modules and typed signatures, optimizers and compilation, ReAct/CoT/RAG patterns; no benchmark figure published for the framework
Verified 2026-08-12