Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

Learning resourcesJupyter NotebookMIT

anthropics/anthropic-cookbook

Anthropic's cookbook demonstrates tool use, retrieval, evaluation, vision, sub-agents and prompt patterns with runnable notebooks. It is useful both as a reference and as a source of tested patterns for Claude's XML-style prompting conventions.

15.0k stars1.8k forks90 contributors40 open issuesUpdated

What it does

  • Shows Claude API patterns with runnable notebooks.
  • Covers tool use, RAG, evaluation and multimodal inputs.
  • Demonstrates prompt engineering techniques specific to Claude.

Key features

  • Official maintained examples.
  • Clear explanations alongside code.
  • Coverage of agent and sub-agent patterns.
  • Integration examples with common libraries.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

Use
git clone https://github.com/anthropics/anthropic-cookbook.git

Alternatives to consider

anthropic-cookbook is a strong default for learning resources, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

OpenAI CookbookPrompt Engineering GuideClaude docs

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

anthropic-cookbook FAQ

Adoption questions we hear most often about this project.

Related repositories

Learning resources · Jupyter Notebook

Practical, runnable examples for the OpenAI API, from embeddings to agents and evals.

72.0k11.5kMIT

Learning resources · Python

A curated collection of practical LLM application examples with source code.

65.0k8.1kApache-2.0