anthropics/claude-quickstarts

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

What it solves

This repository provides a set of reference implementations and starter templates to help developers quickly build and deploy applications powered by the Claude API. It bridges the gap between raw API documentation and fully functional AI agents and tools.

How it works

The project is organized as a collection of independent quickstart projects. Each project demonstrates a specific AI capability, such as:

  • Agentic Workflows: Implementing autonomous coding agents, customer support agents, and managed agents for research or finance.
  • Computer and Browser Use: Providing tools and environments for Claude to control a desktop computer (including macOS native implementations) or automate browser navigation via Playwright.
  • Knowledge Management: Creating a versioned memory-store knowledge wiki from document corpora using parallel extraction and consolidation.
  • Data Analysis: Integrating interactive data visualization for financial analysis via chat.

Who it’s for

Developers who want to build AI applications using the Claude API and the tools provided by Anthropic, including those interested in agentic frameworks, browser automation, and complex knowledge retrieval systems.

Highlights

  • Computer Use: Includes both containerized demos and native macOS reference implementations with best practices for reliability and cost-effectiveness.
  • Autonomous Coding: A two-agent pattern (initializer + coding agent) that persists progress via git.
  • Managed Agents: Demonstrations of integrating Claude Managed Agents with Vercel's Chat SDK and CopilotKit for generative UI.
  • Knowledge Wiki: A system for distilling document corpora into a versioned memory-store to reduce token costs for repeated queries.

Related

  • Project
    browserbase/skills

    A collection of skills for Claude Code that enable browser automation, web research, and AI-powered UI testing via Browserbase.

  • Project
    Shubhamsaboo/awesome-llm-apps

    A collection of 100+ open-source AI agent templates and RAG applications, providing ready-to-use examples for building agentic workflows and multimodal AI apps.

  • Project
    darcyegb/ClaudeCodeAgents

    A collection of specialized agent definitions for Claude Code that provide focused expertise for code review, implementation verification, and UI testing.

  • Project
    spring-ai-community/spring-ai-agent-utils

    A Spring AI library that provides Claude Code-inspired tools for file operations, shell execution, web access, and long-term memory to enable agentic workflows in Java applications.

  • Project
    mxyhi/ok-skills

    A curated collection of reusable skills and playbooks for AI coding agents, providing portable instructions for tasks like browser automation, documentation lookup, and codebase planning.