DSPy

Framework for algorithmically optimizing LM prompts and pipelines

CuratedLLM Frameworks & RAG

I use this adds DSPy to your stack and finds people with similar stacks. Every mark feeds the counts on Pulse. Sign in to mark it.

No ratings yet

Who uses it

0 use this

0use it now

0tried it, dropped it

0want to try

Nobody has marked it yet. Press I use this, Tried it or Want to try to be the first.

Ratings

Only from people who use it or tried it

No ratings yet

The first rating comes from someone who uses DSPy or tried it.

Use DSPy?

What it does

DSPy is an open-source Python framework (MIT) for programming language models with code instead of hand-written prompts. You declare a task as a signature of typed inputs and outputs, choose modules such as chain-of-thought or tool use, and let optimizers like GEPA and MIPROv2 tune prompts and examples against a metric. It started at Stanford NLP and is now community-developed.

Alternatives on the map

All 24 alternatives

RAG & Memory, starting with the other LLM Frameworks & RAG.

Compare with

People who use it also use

Not enough marks yet to tell. When people who use DSPy mark the rest of their stack, it shows up here.

Open website