Instructor
Structured outputs from LLMs using Pydantic — extracts typed, validated data from any LLM response, eliminating JSON parsing headaches in AI pipelines
Visit Instructor →More in AI & Agents
DSPy
Stanford’s framework for programming — not prompting — language models, with automatic prompt optimization
FeaturedPrompt OptimizationLLM
smolagents
Hugging Face’s lightweight agent library — minimal, readable code for building tool-using LLM agents with support for any model via the Transformers ecosystem
agentshuggingface
LlamaIndex
Data framework for building LLM-powered applications over your own data — handles ingestion, indexing, retrieval, and query pipelines for RAG systems
ragllm