AI & Agents resources
DSPy
Stanford’s framework for programming — not prompting — language models, with automatic prompt optimization
Haystack
Open-source framework for building production-grade retrieval-augmented generation and search pipelines
Microsoft AutoGen
Framework for building multi-agent AI systems where LLM agents collaborate, debate, and use tools to solve complex tasks — from Microsoft Research
CrewAI
Python framework for orchestrating role-based multi-agent teams that collaborate to complete complex tasks
Hugging Face
The hub for open-source machine learning models, datasets, and spaces — essential for working with transformers and LLMs in Python
Instructor
Structured outputs from LLMs using Pydantic — extracts typed, validated data from any LLM response, eliminating JSON parsing headaches in AI pipelines
LangChain
The most widely used Python framework for building LLM-powered applications, with 700+ integrations and tools for agents, RAG, and chains
LangGraph
Framework for building stateful, multi-step AI agent workflows as graphs — ideal for complex reasoning and tool-use pipelines
LlamaIndex
Data framework for building LLM-powered applications over your own data — handles ingestion, indexing, retrieval, and query pipelines for RAG systems
Ollama
Run large language models locally with a simple Python API — supports Llama, Mistral, Gemma, and dozens more open-source models
OpenAI Python SDK
Official Python client for the OpenAI API — supports chat completions, embeddings, assistants, streaming, and function calling with full async support
Pydantic AI
Type-safe Python framework for building production AI agents, built by the Pydantic team with structured outputs and dependency injection
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