Free tutorials for AI frameworks

Lessons on the frameworks and tools used to build AI apps, one framework at a time, with code examples and a quiz after every section.

LangChain

The layer under most agents. Models, tools, prompts and messages in one interface.

LangChainGeneral

LangGraph

Build agents as graphs. Loops, memory, human approval and full control of the flow.

LangChainGraph and workflow

Deep Agents

Agents that plan with to-do lists, keep notes in files and hand work to subagents.

LangChainGeneral

Model Context Protocol

Not a framework. The standard that lets any agent plug into any tool or data source.

AnthropicProtocols and tools

DeepEval

Unit tests for what your LLM app says: metrics with a Groq judge, RAG and agent scores, and a command that fails the build.

Confident AIEvals and testing

RAGAS

Scores a RAG bot's answer and its retrieval separately, so you know which half to fix.

RagasEvals and testing

NeMo Guardrails

Rails written as files between your app and its model, in a language of their own.

NVIDIAGuardrails

Claude Code

Anthropic's terminal agent. Reads your repo, edits it, runs your commands.

AnthropicCoding agent

LangMem

Long-term memory for LangGraph agents: extraction, consolidation and retrieval.

LangChainMemory

LLM Fundamentals

Tokens, temperature, prompts, evals, context, cost and speed, on a real model you run.

Coding LabsStarter

LiteLLM

One interface and one proxy in front of a hundred model providers.

BerriAIInfrastructure

LlamaIndex

Agents that reason over your documents. Strong on retrieval and indexing.

LlamaIndexGeneral

OpenAI Agents SDK

OpenAI's own agent loop, with handoffs, guardrails and tracing built in.

OpenAIVendor SDK

Promptfoo

A config file and one command that runs your prompts and says which answers broke.

promptfooEvals and testing

Pydantic AI

Type safe agents. If you already trust Pydantic for validation, this feels like home.

PydanticTyped output

Claude Agent SDK

Claude Code as a library. Tools, permissions, hooks, sessions, skills and plugins, with every example running keyless.

AnthropicVendor SDK

CrewAI

Give each agent a role, a goal and a backstory, then let the crew work the task.

CrewAIMulti agent

Langfuse

Open-source tracing, prompt management and evals you can host yourself.

LangfuseObservability

Agent Governance Toolkit

Policy checks between an agent deciding to call a tool and the tool running.

MicrosoftGuardrails