anthropics/claude-cookbooks

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

What it solves

Claude Cookbooks provides a collection of ready-to-use code examples and guides that help developers integrate Claude into their own applications, reducing the time spent figuring out how to implement specific AI features.

How it works

The repository contains "recipes"—mostly Python-based code snippets—that demonstrate how to perform common tasks with the Claude API. These range from basic capabilities like text summarization and classification to advanced workflows like tool integration, vision processing, and cost optimization.

Who it’s for

This resource is designed for developers who want to build with Claude. It is particularly useful for those who have a basic understanding of the API and are looking for practical, copy-able code to implement specific functionalities like RAG, multimodal vision tasks, or automated prompt evaluation.

Highlights

  • Practical recipes for core capabilities like classification, summarization, and RAG.
  • Guides for integrating external tools, databases, and third-party services.
  • Examples for multimodal tasks, including image analysis and chart interpretation.
  • Advanced techniques for prompt caching, JSON mode, and cost optimization.
  • Community-driven content that is open for contributions and improvements.

Related

  • Project
    run-llama/llama_index

    An open-source data framework for building agentic applications by connecting LLMs to private data sources through ingestion, indexing, and retrieval.

  • Project
    Ebony-Vinyl/dsh-our-free-model

    A DSH plug‑in that adds free, no‑login LLMs (DeepSeek Flash, Kimi K3, etc.) to the model selector, provides a local OpenAI‑compatible endpoint, token‑saving features, aggregated provider support, combo routing, usage dashboard, and one‑click in‑app upgrades.

  • Project
    zylon-ai/private-gpt

    An open-source API layer that turns local LLM inference servers into production-ready AI applications by providing RAG, tool use, and Claude API compatibility.

  • Project
    pathwaycom/serviette

    Pathway Live Data Framework AI Pipelines offers Docker‑based RAG app templates that sync live data sources, index documents in‑memory, and expose an HTTP API for LLM‑powered question answering. It bundles ingestion, vector/hybrid indexing, and LLM calls using the open‑source Pathway library, letting developers prototype enterprise search or multimodal AI apps quickly.