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

It provides a set of reference implementations and starter templates for developers to build AI applications using the Claude API, reducing the friction of starting a new project from scratch.

How it works

The repository contains a collection of standalone "quickstart" projects. Each project demonstrates a specific capability of the Claude API, such as computer use, browser automation, or managed agents. Developers clone the repository, navigate to a specific project folder, install dependencies, and provide an API key to run the application.

Who it’s for

Developers who want to implement specific AI patterns (like autonomous coding or customer support) using Claude and need concrete code examples to build upon.

Highlights

  • Computer Use: Demos for controlling a desktop computer and a native-macOS reference implementation for building reliable agents.
  • Browser Automation: A Playwright-backed implementation for navigating websites and interacting with DOM elements.
  • Managed Agents: A wide variety of agentic patterns including scheduled tasks (Sentry triage, Daily Brief), platform integrations (Slack, Linear), and knowledge wikis.
  • Autonomous Coding: A two-agent pattern (initializer and coding agent) that persists progress via git.
  • Specialized Analysts: Templates for customer support and financial data analysis with interactive visualization.

Related

  • Project
    anthropics/claude-agent-sdk-demos

    A collection of demonstration applications showcasing various ways to build AI-powered agents and apps using the Claude Agent SDK.

  • Project
    browserbase/skills

    A collection of skills for Claude Code that enable AI agents to perform browser automation, UI testing, and deep web research via Browserbase.

  • 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
    ajsahni/agents-office

    Agents Office is a beta, locally‑run visual platform that turns Claude into a team of 35 role‑based AI agents. You type tasks, the system routes them to the right agent (or a team), the agents use Claude Code connectors (Gmail, Slack, Chrome, etc.) to do the work, and results are saved as notes in your personal “Brain”. Features include customizable briefs/skills, recurring routines, a calendar view, team‑splitting, model/effort selection, and a non‑commercial license.

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

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