# DSPy

> MIT program LMs with signatures and optimizers (Stanford NLP)

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://dspy.ai  
**GitHub:** https://github.com/stanfordnlp/dspy  
**Added:** 2026-09-15

---

## The Hook

DSPy programs language models — signatures and optimizers instead of brittle prompt strings.

## What's Good

MIT (stanfordnlp/dspy). Declarative Python modules, compilers/optimizers that tune prompts and weights, community + Stanford NLP lineage. Docs at dspy.ai. Fits classifiers, RAG, and agent loops when you want systematic improvement over hand-tuned templates.

## The Catch

Vs LangChain/LangGraph (orchestration graphs) and Promptfoo (YAML eval/red-team): DSPy is program-and-optimize LMs, not an MCP-first runtime and not a hosted eval SaaS. Optimizer runs cost tokens/compute; you still bring models and data. Not a drop-in coding agent.

## Verdict

MIT LM programming framework. Optimize modules; do not confuse it with MCP runtime glue.