stackpicks.dev
Built bystanfordnlp

dspy

DSPy: The framework for programming—not prompting—language models

34.8k stars3k forks196 watchers284 open issuesPythonMIT

TL;DR · 30-second scan

What it is

dspy (Python)DSPy: The framework for programming—not prompting—language models

What it does for you

You're building production AI systems and want a more rigorous abstraction than ad-hoc prompts.

Best for

AI & ML

34.8k GitHub starsLicense: MITLast updated 1 month ago
EDITOR'S DEEP TAKE

Stanford's framework for programming with LLMs instead of prompting them. You define what you want; DSPy optimizes the prompt automatically. Trending in 2026 as the "next layer" above LangChain. Best for production AI systems where you need reproducible, optimizable LLM pipelines.

Use this if

You're building production AI systems and want a more rigorous abstraction than ad-hoc prompts.

Skip if

You're prototyping simple chat — DSPy's mental model is more demanding than direct prompting.

Categories
Maintainer? Embed our badge

Add this badge to your README to show your project is curated on StackPicks. Free, lightweight (180×28 SVG), and gives your visitors a one-click way to see honest take + alternatives.

Preview
Featured on StackPicks
Markdown (for GitHub README)
[![Featured on StackPicks](https://stackpicks.dev/api/badge/stanfordnlp-dspy)](https://stackpicks.dev/repo/stanfordnlp-dspy)
HTML (for blogs / docs)
<a href="https://stackpicks.dev/repo/stanfordnlp-dspy"><img src="https://stackpicks.dev/api/badge/stanfordnlp-dspy" alt="Featured on StackPicks" width="180" height="28" /></a>

Are you the maintainer of stanfordnlp/dspy? Add the badge and we'll feature your project in the weekly curator newsletter.

Created 10 Jan 2023
Last push 1 month ago
Stats refreshed 1 month ago