ADK-TS

ADK-TS: Build AI Agents in TypeScript

ADK-TS is a powerful framework designed for creating sophisticated AI agents using TypeScript. It is built to support enterprise-grade applications, offering advanced features for tool integration, memory management, and real-time streaming. This framework leverages TypeScript's type safety and modern tooling to ensure robust and scalable AI agent development.

Benefits

ADK-TS provides a comprehensive suite of features to streamline the development of production-ready AI agents. Here are some key advantages:

AgentBuilder API

The AgentBuilder API offers a fluent interface for rapid agent creation with minimal boilerplate. This allows developers to focus on building intelligent agents without getting bogged down by complex configurations.

Multi-LLM Support

ADK-TS supports multiple large language models (LLMs), including OpenAI, Google Gemini, and Anthropic Claude, through a unified interface. This flexibility allows developers to seamlessly switch between different models based on their specific needs.

Production Ready

The framework is built with enterprise deployment in mind, featuring built-in session management, memory services, streaming, and artifact handling. These features ensure that agents can be deployed in production environments with confidence.

Advanced Tooling

ADK-TS offers advanced tooling capabilities, including custom tools, function integration, Google Cloud tools, MCP support, and automatic schema generation. These tools enhance the functionality and versatility of the agents.

Developer Experience

ADK-TS prioritizes developer experience with TypeScript IntelliSense, comprehensive examples, and intuitive APIs. This makes it easier for developers to build and deploy AI agents efficiently.

Use Cases

ADK-TS is versatile and can be used in various scenarios, including:

Simple Agent Creation

With just a few lines of code, developers can create simple AI agents that can answer questions or perform basic tasks.

Complex Multi-Agent Workflows

ADK-TS supports the creation of complex multi-agent systems, allowing for seamless orchestration of tasks across multiple agents. This includes support for parallel, sequential, and hierarchical agent architectures.

Real-Time Applications

The framework supports real-time streaming, enabling agents to process and respond to data in real-time. This is crucial for applications requiring immediate feedback.

Getting Started

Getting started with ADK-TS is straightforward. Here are the steps to begin:

1. Install the @iqai/adk package
2. Choose your LLM provider
3. Start building agents

Supported Models

ADK-TS supports a variety of models, including GPT-4, Claude-3.5-Sonnet, Gemini-2.5-Flash, and more.

import{AgentBuilder}from'@iqai/adk';// One-line agent creationconstresponse=awaitAgentBuilder.withModel("gemini-2.5-flash").ask("What is the primary function of an AI agent?");// Agent with session and toolsconst{agent,runner,session}=awaitAgentBuilder.create("my_assistant").withModel("gpt-4.1").withDescription("A helpful AI assistant").withInstruction("Provide concise responses.").withTools(newGoogleSearch(),newHttpRequestTool()).build();// Multi-agent workflowconstworkflow=awaitAgentBuilder.create("research_workflow").asSequential([researchAgent,summaryAgent]).build();

Ready to Build Your First Agent?

Join developers building the future of AI with TypeScript. Get started with our comprehensive documentation and examples.