Agent Development Kit (ADK) for TypeScript

An open-source, code-first TypeScript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Important Links: Docs, Samples & ADK Web.

Agent Development Kit (ADK) is a flexible and modular framework for building, deploying, and orchestrating AI agent workflows, from simple tasks to complex multi-agent systems. Define agent behavior, orchestration, and tool use directly in code, enabling robust debugging, versioning, and deployment anywhere.

The TypeScript version of ADK is built for the Node.js and browser ecosystems, with full type safety, Zod schema validation, and support for ESM, CommonJS, and web runtimes.

✨ Key Features

• Code-First TypeScript: Define agent logic, tools, and orchestration with full type safety. Tool parameters support Zod v3 and v4 schemas with compile-time type inference.

• Browser and Server: Ships ESM, CommonJS, and web bundles. Run agents in Node.js or directly in the browser.

• Rich Tool Ecosystem: Built-in tools for Google Search, Google Maps, Vertex AI Search, and URL context. Connect MCP servers, wrap any function as a tool, or add code execution.

• Multi-Agent Orchestration: Compose agents into sequential, parallel, loop, and routed workflows. Delegate to remote agents via the A2A protocol.

• Dev Tools and CLI: Interactive dev UI for testing and debugging. CLI commands for scaffolding (adk create), local testing (adk run, adk web), and deployment (adk deploy cloud_run).

🚀 Installation

Prerequisite: ADK for TypeScript requires a current Node.js LTS release.

npm install @google/adk
npm install -D @google/adk-devtools

Or with yarn:

yarn add @google/adk
yarn add -D @google/adk-devtools

This installs the core SDK and the dev tools (CLI and dev UI) as a dev dependency.

Quick Start

Set up authentication. Get an API key from Google AI Studio and put it in a .env file next to your agent:

echo "GOOGLE_GENAI_API_KEY=your-api-key-here" > .env

Using Vertex AI instead? Set GOOGLE_GENAI_USE_VERTEXAI=1, GOOGLE_CLOUD_PROJECT, and GOOGLE_CLOUD_LOCATION in place of the API key, and authenticate with gcloud auth application-default login.

Define an agent in agent.ts:

import {LlmAgent, GOOGLE_SEARCH} from '@google/adk';
export const rootAgent = new LlmAgent({
  name: 'search_assistant',
  description: 'An assistant that can search the web.',
  model: 'gemini-flash-latest',
  instruction:
    'You are a helpful assistant. Answer user questions using Google Search when needed.',
  tools: [GOOGLE_SEARCH],
});

Run from your agent project directory:

# Interactive CLI
npx @google/adk-devtools run agent.ts
# Web UI
npx @google/adk-devtools web

Always name the package. If @google/adk-devtools is not installed, bare npx adk silently downloads and runs an unrelated adk package from the public registry.

The adk web command launches a development UI for testing and debugging agents:

📚 Documentation

• Getting Started: https://adk.dev/get-started/typescript
• Samples: https://github.com/google/adk-samples

🤝 Contributing

We welcome contributions from the community! Whether it's bug reports, feature requests, documentation improvements, or code contributions, please see the contributing guide and CONTRIBUTING.md to get started.

📄 License

This project is licensed under the Apache 2.0 License - see the LICENSE file for details.