# anthropics/claude-quickstarts

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

Repository: https://github.com/anthropics/claude-quickstarts
Canonical: https://ross.abutalabs.com/products/claude-quickstarts
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-25T14:48:13+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 52
- inputs: {"age_days": 734, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 17525, forks 3021 (observed 2026-08-28T04:11:19.951104+00:00)

## What it is
A collection of official Anthropic quickstart projects demonstrating how to build deployable applications with the Claude API, including customer support agents, financial data analysts, computer-use and browser-use agents, and autonomous coding agents. Each project is a working foundation in TypeScript and Python that developers can clone, customize, and extend for their own LLM-powered applications.

## Use cases
- build a customer support chatbot with a knowledge base using the claude api
- get started with anthropic claude api example projects
- create an ai agent that controls a desktop computer
- automate browser tasks like form filling and web scraping with an llm
- build an autonomous coding agent that works across multiple sessions
- analyze financial data through a chat interface with charts
- learn best practices for building reliable computer-use agents on macos

## When to choose
- you want runnable, production-oriented starter code for the Claude API rather than snippets
- you need reference implementations of agent patterns like computer use, browser automation, or multi-session coding agents
- you are evaluating what can be built with Claude and want to see complete working examples
- you want official Anthropic guidance paired with code, such as computer-use best practices

## When to avoid
- you need a production-ready application without modifications - these are starting points, not finished products
- you use a different LLM provider and do not want Claude-specific code
- you are looking for a library or SDK to install rather than example projects to study and adapt
- you need a lightweight tutorial - these projects involve full application stacks with dependencies

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, chatbot, rag, computer-vision, data-visualization, developer-tools, sdk
- domain: large-language-models, chatbots, developer-tools, tutorials, data-visualization
- platform: python, cross-platform
- tags: claude-api, anthropic, quickstart, computer-use, browser-automation, customer-support-agent, financial-analysis, coding-agent, llm-applications, example-projects, ai-agents, automation, typescript, macos, web-server, docker

## Member repositories
- anthropics/claude-quickstarts (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:19.951104+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:02:54.569399+00:00, confidence not recorded.
  - readme: https://github.com/anthropics/claude-quickstarts (fetched 2026-08-28T04:11:19.951104+00:00, sha 4541754ad835)
- Data as of 2026-08-30T08:39:29.467469+00:00.