Building AI Agents with the TypeScript Agent Development Kit (ADK)
Build, test, and deploy AI agents using Google's native TypeScript Agent Development Kit (ADK), Gemini 2.5 Flash, and Cloud Run....
- Extract the principle, then apply it to your audience: what should change in your strategy this week?
- Turn insights into a repeatable process (calendar, SOPs, KPIs) so execution is consistent.
- Keep it measurable: pick one outcome metric and one behavioral leading indicator to track weekly.
Quick answer
Build, test, and deploy AI agents using Google's native TypeScript Agent Development Kit (ADK), Gemini 2.5 Flash, and Cloud Run....
xbill for Google Developer Experts Posted on Jul 27
Building AI Agents with the TypeScript Agent Development Kit (ADK) # typescript # ai # gemini # webdev
ADK (12 Part Series)
1 Creating a Low-code Agent with the ADK Visual Builder
2 Building a Multimodal Agent with the ADK and Gemini Flash Live 3.1... 8 more parts...
3 Multi-Agent A2A with the Agent Development Kit(ADK), Cloud Run, and Gemini CLI
4 Multi-Agent Deployment with the Agent Development Kit(ADK), GKE, GKE MCP Server, and Gemini CLI
5 Multi-Agent A2A with the Agent Development Kit(ADK), Cloud Run, Agent Skills, and Gemini CLI
6 Multi-Agent A2A with the Agent Development Kit(ADK), Amazon EKS, and Gemini CLI
7 Building with the Google Cloud Run MCP Server for Multi-Agent A2A Deployment
8 Building AI Agents with the GO Agent Development Kit (ADK) — 2026 Edition (v2)
9 Building AI Agents with the Python Agent Development Kit (ADK) — 2026 Edition (v2)
10 Building AI Agents with the TypeScript Agent Development Kit (ADK)
11 Build and Deploy Java AI Agents with Google ADK
12 Building AI Agents with the Kotlin Agent Development Kit (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:
xbill9 / adk-hello-world-typescript
ADK Hello World for TypeScript
A minimal weather and time agent built with Google's Agent Development Kit for TypeScript.
Requirements
- Node.js 20 or newer
- A Gemini API key, or Google Cloud credentials for Vertex AI
Setup
npm install cp.env.example.env
Enter fullscreen mode
Exit fullscreen mode
Edit.env and choose one authentication method:
- Gemini Developer API: set GOOGLE_API_KEY
- Vertex AI: set GOOGLE_GENAI_USE_VERTEXAI=TRUE, GOOGLE_CLOUD_PROJECT, and GOOGLE_CLOUD_LOCATION, then run gcloud auth application-default login
Never commit.env.
Run
# Interactive terminal npm start
# ADK development UI npm run web
# Type-check and run unit tests npm run check
Enter fullscreen mode
Exit fullscreen mode
The ADK CLI can also be called directly:
npx adk run src/agent.ts npx adk web
Enter fullscreen mode
Exit fullscreen mode
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.