DSPy
Stanford NLP'/%3e%3cdefs%3e%3cpattern%20id='pattern0_1240_293949'%20patternUnits='userSpaceOnUse'%20patternTransform='matrix(11.2%200%200%2011.2%203.93617%200)'%20preserveAspectRatio='none'%20viewBox='0%200%2016%2016'%20width='1'%20height='1'%3e%3cg%20id='pattern0_1240_293949_inner'%3e%3crect%20width='16'%20height='16'%20fill='%23f88376'%20mask='url(%23hatch_gaps)'/%3e%3cmask%20id='hatch_gaps'%20maskUnits='userSpaceOnUse'%20x='0'%20y='0'%20width='16'%20height='16'%3e%3crect%20width='16'%20height='16'%20fill='white'/%3e%3crect%20x='6'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='6'%20y='8'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='4'%20y='2'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='4'%20y='10'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='2'%20y='4'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='2'%20y='12'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20y='6'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20y='14'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='14'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='14'%20y='8'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='12'%20y='2'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='12'%20y='10'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='10'%20y='4'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='10'%20y='12'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='8'%20y='6'%20width='2'%20height='2'%20fill='black'/%3e%3crect%20x='8'%20y='14'%20width='2'%20height='2'%20fill='black'/%3e%3c/mask%3e%3c/g%3e%3c/pattern%3e%3c/defs%3e%3c/svg%3e)
Stanford 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.
Openness
5 high confidence- license
- MIT(OSI)
- source
- public
- core features withheld
- no
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
- https://raw.githubusercontent.com/stanfordnlp/dspy/main/LICENSE recorded 2026-09-29
The LICENSE file is the MIT License held by Stanford, granting "Permission is hereby granted, free of charge" to use, modify and sell; searched for additional commercial or non-commercial terms: none.
- https://raw.githubusercontent.com/stanfordnlp/dspy/main/README.md recorded 2026-09-29
The README offers the whole framework from source with "pip install git+https://github.com/stanfordnlp/dspy.git"; searched for enterprise, paid tier and license-key gating: none.
Adoption
4 high confidenceAdoption is measured by PyPI downloads of dspy, the framework's own package, so the figure reflects direct use of the framework rather than a proxy signal.
- 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
- https://raw.githubusercontent.com/stanfordnlp/dspy/main/README.md recorded 2026-09-29
The README describes DSPy as a framework for building "modular AI systems" with "algorithms for **optimizing their prompts and weights**" across classifiers, RAG pipelines and agent loops.
Verified 2026-09-24