Get Started

New to AI Agents?

AI agents are autonomous programs that can understand instructions, use tools, and complete complex tasks. With ADK TypeScript, you can build agents that search the web, process files, interact with APIs, and coordinate with other agents.

Quick Start Path

Follow this path to get from zero to your first working agent:

Install ADK TypeScript

Set up your development environment and install the package.

→ Installation Guide

Build Your First Agent

Create a simple agent that answers questions using Gemini models.

→ Quickstart Tutorial

Understand the Architecture

Learn about the core concepts and components.

→ About ADK TypeScript

Choose Your Learning Path

🚀 I want to build quickly

Jump straight into code with minimal setup

Start with the Quickstart - you'll have a working agent in 5 minutes.

Perfect for: Prototyping, proof of concepts, getting a feel for the framework.

📚 I want to understand first

Learn the concepts before diving into code

Read About ADK TypeScript to understand the architecture and design philosophy.

Perfect for: Planning production systems, understanding best practices.

🎯 I have a specific use case

I know what I want to build

Browse our Examples to find patterns that match your needs.

Perfect for: Specific projects, learning by example, copying working code.

What You Can Build

ADK TypeScript enables a wide range of AI agent applications:

Simple Agents

// Question answering agent
const response = await AgentBuilder
  .withModel("gemini-2.5-flash")
  .ask("Explain quantum computing in simple terms");

Use cases: Q&A bots, content generation, text analysis

Tool-Enhanced Agents

// Research agent with web search
const agent = new LlmAgent({
  name: "researcher",
  model: "gemini-2.5-flash",
  tools: [new GoogleSearch(), new FileOperationsTool()],
  instruction: "Research topics thoroughly and cite sources"
});

Use cases: Research assistants, data analysis, automated reporting

Multi-Agent Workflows

// Workflow: Research → Analyze → Summarize
const workflow = await AgentBuilder
  .create("content_pipeline")
  .asSequential([researchAgent, analysisAgent, summaryAgent])
  .build();

Use cases: Content pipelines, complex analysis, quality assurance

Interactive Applications

// Persistent chat with memory
const { runner } = await AgentBuilder
  .create("chat_assistant")
  .withModel("gemini-2.5-flash")
  .withSession(sessionService, userId, "chat-app")
  .build();