stanfordnlp

DSPy

Program — don't prompt — your language models. Compile declarative pipelines into optimized prompts.

★ 35,871⑂ 3,063● Python⚖ MITupdated yesterday

README.md

DSPy lets you write LLM pipelines as code and compile them into optimized prompts/weights, replacing brittle hand-written prompts with a programmable, optimizable approach.

pip install dspy

Continue your stack

What teams reach for next — and why each earns a place beside DSPy.

Alternative to

LangGraph

Build stateful, multi-actor LLM apps as graphs — durable execution, human-in-the-loop, streaming.

Why it fitsA different bet: optimize prompts as code rather than orchestrate them.