DSPy
Program — don’t prompt — language models.
Declarative framework that compiles LM programs and optimizes prompts and weights automatically.
- Vendor
- Stanford NLP
- Category
- LLM & RAG frameworks
- Pricing
- Open source
- Open source
- Yes
- License
- MIT
- Platforms
- Python
- Launched
- 2023
- Website
- dspy.ai
Features
- Prompt optimizers
- Signatures
- Modules
Best for
- Reasoning
- Extraction & classification
More llm & rag frameworks
- LangChain — LangChain. The most widely used LLM application framework.
- AI SDK — Vercel. The TypeScript toolkit for AI apps.
- LlamaIndex — LlamaIndex. Data framework for RAG and document agents.
- Haystack — deepset. Production-ready RAG pipelines.
- Instructor — Jason Liu & community. Pydantic-typed structured outputs from any LLM.
- Outlines — .txt (dottxt). Guaranteed structured generation with regex, JSON Schema and grammars.
- BAML — Boundary. A typed language for defining and testing LLM functions.