#88th of 10 in Learning and cookbooks
claude-cookbooks
Jupyter notebooks of copy-able Claude API recipes in Python
- Stars
- 53.4k
- License
- MIT
- Last commit
- Oct 2026
- Language
- Jupyter Notebook
35,546 on 24 Mar 202653,417 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Anthropic is hiring: 647 open roles
Overview
Anthropic's collection of runnable notebooks and guides for building with the Claude API. Recipes cover classification, RAG, summarization, tool use, vision, sub-agents, JSON mode, prompt caching, evals and cost optimization. Examples are mainly Python, and a Claude API key is required.
Who it is for: Developers learning to build applications on the Claude API
Strengths
- Covers tool use, RAG, vision, prompt caching and evals with runnable notebooks
- Maintained by Anthropic, so examples target the Claude API directly
- MIT licensed, snippets can be copied into your own projects
- Includes third-party recipes such as Pinecone, Voyage AI embeddings and Wikipedia search
Weaknesses
- Requires a Claude API key; examples do not run on local models
- Examples are primarily Python; other languages must be adapted
- Recipe links in the README point to the older anthropic-cookbook repo path
- Reference snippets, not an installable library or application
What it needs
- no GPU
- Needs Claude API key, Pinecone (some recipes), Voyage AI (some recipes)
- Models: Claude
Also in Learning and cookbooks
See all 10| Rank | Project | Score |
|---|---|---|
| 1 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 80 out of 100 |
| 2 | ai-engineering-from-scratchHands-on curriculum for building AI systems from math to agents | 79 out of 100 |
| 3 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 75 out of 100 |
| #4 | hello-agentsChinese-language course on building LLM agents from scratch | 74 out of 100 |
| #5 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 72 out of 100 |