Get Started

What is ADK-TS?

Agent Development Kit (ADK) for TypeScript is a powerful, open-source framework for building, orchestrating, and deploying AI agents.

Inspired by the architectural principles of Google's Python ADK, our project is reimagined for the TypeScript ecosystem. We offer first-class support for Google Gemini models while providing the freedom to integrate with any LLM, tool, or data source. ADK-TS makes it easy to start with simple agents and scales to support complex, multi-agent systems in any Node.js environment.

Why Choose ADK-TS?

Our vision is to empower every developer to build intelligent agents with the same confidence as any modern software. We achieve this through three core pillars:

• Unparalleled Developer Experience: We are TypeScript-first, providing full type-safety and autocompletion out of the box. Our intuitive AgentBuilder API lets you create powerful agents with minimal, readable code.
• Powerful & Flexible Architecture: ADK-TS is modular by design. Compose multiple agents, equip them with custom tools, and orchestrate complex workflows. Our provider-agnostic foundation means you're never locked into a single ecosystem.
• Production-Ready from Day One: Go beyond prototypes. With built-in session management, persistent memory, and first-class OpenTelemetry support for observability, ADK-TS provides the robust foundation needed for real-world applications.

What You Can Build

ADK-TS 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 and file operations
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")
  .withSessionService(sessionService, userId, "chat-app")
  .build();

Use cases: Chatbots, virtual assistants, customer support

Core Concepts

ADK-TS is built on a set of powerful, modular concepts that allow you to build sophisticated AI agents with ease. These are the features that make ADK-TS special.

Next Steps

Ready to start building? Here's how to get started:

Community & Support

Join our community for help, discussions, and updates: