Building AI Agents with the TypeScript Agent Development Kit (ADK)

Google's Agent Development Kit (ADK) for TypeScript is now available as a flexible, model-agnostic framework for building and deploying AI agents. A sample 'Hello World' agent demonstrates local tools for weather and time, with full type safety via TypeScript and Zod schema validation. The ADK supports Node.js and browser runtimes, and is published on npm as @google/adk.

This tutorial builds a starter "Hello World" style agent using TypeScript and the native TypeScript version of the Agent Development Kit ADK . The full sample project is available on GitHub: A minimal weather and time agent built with Google's Agent Development Kit for TypeScript https://github.com/google/adk-js . npm install cp .env.example .env Edit .env and choose one authentication method: GOOGLE API KEY GOOGLE GENAI USE VERTEXAI=TRUE , GOOGLE CLOUD PROJECT , and GOOGLE CLOUD LOCATION , then run gcloud auth application-default login Never commit .env . Interactive terminal npm start ADK development UI npm run web Type-check and run unit tests npm run check The ADK CLI can also be called directly: npx adk run src/agent.ts npx adk web The agent source is in src/agent.ts . Its two local tools preserve the original sample behavior: weather and local time are available for New York, while other cities return a clear unsupported-city result. TypeScript is a strongly typed programming language built on top of JavaScript, maintained by Microsoft. It compiles to plain JavaScript and runs anywhere JavaScript runs — including Node.js, which is what the ADK for TypeScript targets. The static type system pairs naturally with agent development: tool parameters, tool results, and agent configuration are all checked at compile time, before the model ever sees them. The ADK for TypeScript requires Node.js 20 or newer . If Node.js is not installed in your environment, the Node Version Manager nvm is the easiest way to install and manage versions: Install and activate a current Node.js release: nvm install --lts nvm use --lts You can validate the installation with the version command: node --version v22.x The Agent Development Kit ADK is a flexible and modular framework for developing and deploying AI agents . While optimized for Gemini and the Google ecosystem, ADK is model-agnostic , deployment-agnostic , and built for compatibility with other frameworks . Google provides full documentation on the ADK here: Google provides the source to the complete TypeScript version of the ADK project: 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. 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 … The ADK is published to npm as @google/adk https://www.npmjs.com/package/@google/adk , with the development tooling in @google/adk-devtools . This tutorial uses If not using Application Default Credentials ADC , you will need a Gemini API key. You can get a Gemini key from Google AI Studio: Once Node.js is installed, clone the sample repo and run the init.sh script. It installs the npm dependencies and creates a starter .env file: git clone https://github.com/xbill9/adk-hello-world-typescript cd adk-hello-world-typescript source init.sh Output: Created .env from .env.example. Add your credentials before running the agent. Setup complete. Run: npm start Edit .env and choose one authentication method: GOOGLE API KEY GOOGLE GENAI USE VERTEXAI=TRUE , GOOGLE CLOUD PROJECT , and GOOGLE CLOUD LOCATION , then authenticate with ADC: gcloud auth login gcloud auth application-default login Note:Never commit .env — it is already listed in .gitignore . If your Application Default Credentials expire or your Google Cloud authentication expires, re-authenticate with: gcloud auth login gcloud auth application-default login Another common issue is missing environment variables. The agent loads .env automatically via dotenv , and the set env.sh script is provided for shell commands that need the same values: source set env.sh The entire agent lives in a single file — src/agent.ts . It defines two local tools weather and current time and wires them into an LlmAgent running on Gemini 2.5 Flash . Tool parameters are declared with Zod https://zod.dev schemas, so the ADK derives the function-calling declarations directly from the types: js import {FunctionTool, LlmAgent} from '@google/adk'; import {z} from 'zod'; const cityParameters = z.object { city: z.string .min 1 .describe 'The city to look up.' , } ; const weatherTool = new FunctionTool { name: 'get weather', description: 'Retrieves the current weather report for a specified city.', parameters: cityParameters, execute: {city} = getWeather city , } ; export const rootAgent = new LlmAgent { name: 'weather time agent', model: 'gemini-2.5-flash', description: 'Answers questions about the time and weather in a city.', instruction: 'You are a helpful assistant. Use the available tools to answer ' + 'questions about time and weather. Clearly explain when a city is ' + 'unsupported.', tools: weatherTool, currentTimeTool , } ; The tools return a discriminated union — a success result with a report, or an error result with a message — which gives the model a consistent shape to reason about: export type ToolResult = | {status: 'success'; report: string} | {status: 'error'; errorMessage: string}; Weather and local time are available for New York; other cities return a clear unsupported-city result. Unlike earlier Go and Python versions of this sample, the TypeScript project ships with a unit test suite built on the Node.js native test runner. A single command type-checks the project and runs the tests: npm run check Example test output: adk-hello-world-typescript@1.0.0 build tsc --noEmit adk-hello-world-typescript@1.0.0 test tsx --test test/ / .test.ts ▶ weather and time agent ✔ exports the ADK root agent 0.43ms ✔ returns the configured New York weather 0.16ms ✔ rejects unsupported cities 0.45ms ✔ formats New York time deterministically 12.27ms ✔ weather and time agent 14.06ms ℹ tests 4 ℹ pass 4 ℹ fail 0 Because the tools are plain exported functions, they can be tested deterministically without calling the model at all. The agent can be debugged locally from the terminal. Use cli.sh or run the npm script directly: npm start runs: adk run src/agent.ts The ADK CLI can also be called directly: npx adk run src/agent.ts Sample interaction with the agent: php User - what can you do? Agent - I can answer questions about the time and weather in a city using my tools. Currently I support New York — for other cities I will let you know that information is not available. User - what is the weather in New York? Agent - The weather in New York is sunny with a temperature of 25 degrees Celsius 77 degrees Fahrenheit . The agent can be debugged from the web GUI running in the local development environment: npm run web runs: adk web If developing on a remote VM or container and needing the UI reachable from outside, bind the server to all interfaces: npx adk web --host=0.0.0.0 The UI is the same development interface presented for Python, Java, and Go ADK agents — select agent from the dropdown and chat with full tool-calling tracing. Expose the agent as a plain HTTP API without the UI: npx adk api server For deployment options, check the official documentation: The TypeScript ADK CLI has deployment built right in. The cloudrun.sh script loads .env and calls the deploy command: npx adk deploy cloud run \ --project "$GOOGLE CLOUD PROJECT" \ --region "$GOOGLE CLOUD LOCATION" \ --service name "$SERVICE NAME" \ --with ui true \ src/agent.ts The --with ui true flag bundles the development UI into the deployed Cloud Run service. Once deployed, validate your Cloud Run service from the Google Cloud Console, or fetch the service URL from the CLI: gcloud run services describe hello-world-agent-service \ --region us-central1 --format 'value status.url ' The TypeScript Agent Development Kit ADK enables fast agent development using standard TypeScript and Node.js features: node:test . adk web . adk deploy cloud run .