DeepYardDeepYard

DSPy vs LangGraph

Side-by-side comparison with live GitHub signals. Last updated May 22, 2026.

D

DSPy

Framework for programming — not prompting — LLMs — 33K+ stars

OSSFree
34.6Ktoday394
L

LangGraph

LangChain's framework for building stateful agent graphs — 26K+ stars

OSSFree
32.7Ktoday273
MetricDSPyLangGraph
GitHub Stars34.6K32.7K
Contributors394273
Last CommitMay 22, 2026May 21, 2026
Open Issues490553
Licenseopen-sourceopen-source
Pricingopen-sourceopen-source
Free TierYesYes
Categoryframeworksframeworks
TrendingNoNo

Shared Tags

pythonopen-source

Only in DSPy

prompt-optimizationprogrammingresearchragstanford

Only in LangGraph

graphstatefulmulti-agentlangchainpersistence

About DSPy

DSPy replaces prompt engineering with programming. Instead of writing prompts, you define modules with input/output signatures and DSPy automatically optimizes the prompts and weights for your pipeline. Supports chain-of-thought, retrieval-augmented generation, and multi-hop reasoning patterns. From Stanford NLP.

View full listing

About LangGraph

LangGraph is LangChain's framework for building stateful, multi-actor agent applications as graphs. Define agents as nodes and their interactions as edges, with built-in persistence, streaming, human-in-the-loop, and time-travel debugging. The standard for production agent orchestration in the LangChain ecosystem.

View full listing