Agent Development Kit (ADK) for TypeScript is an open-source framework created by IQ AI to facilitate the development, orchestration, and deployment of intelligent AI agents. It provides a TypeScript-first toolkit for building a range of AI systems, from simple question-and-answer bots to complex multi-agent architectures capable of performing real-world tasks, with a focus on type safety and modularity ^{[1] [3]}.

Overview

The Agent Development Kit (ADK) for TypeScript is an enterprise-grade framework that enables developers to construct sophisticated multi-agent AI systems. Inspired by Google's Python ADK, it reimagines the architecture for the TypeScript ecosystem, emphasizing type safety, modularity, and a streamlined developer experience. The kit is designed to support hierarchical agents, integrate various tools, manage memory, and handle real-time streaming, making it suitable for production environments. Its role encompasses the building, orchestration, and deployment of AI agents ^{[2] [4]}. Launched on July 17, 2025, ADK for TypeScript aims to empower developers to build intelligent, autonomous, and on-chain-ready agents ^[1].

ADK for TypeScript serves as an all-in-one toolkit for creating diverse AI applications. Its design prioritizes a seamless developer experience, offering features like autocompletion and robust type safety inherent to TypeScript. The framework's modular and flexible architecture allows for easy composition of agents, attachment of various tools, and integration with multiple large language models (LLMs) ^[1]. It is built to scale from initial prototypes to full production deployments, incorporating essential functionalities such as session management, persistent memory, and OpenTelemetry support for tracing and performance monitoring ^[2].

Key Features

ADK for TypeScript is built around several core features that enhance its power, scalability, and usability for developers. These features collectively contribute to its capability to support complex AI agent development.

AgentBuilder API

The AgentBuilder API provides a fluent interface that simplifies the creation of AI agents, minimizing the need for boilerplate code. This intuitive API allows developers to quickly set up agents with minimal, readable code, supporting both simple one-line agent instantiations and the construction of complex multi-agent workflows. Common patterns can be implemented as one-liners, and the API is designed for gradual complexity, allowing developers to start simple and add power as needed. It is designed to scale with varying project needs, from basic agents to intricate systems ^{[2] [4]}.

Multi-LLM Compatibility

The framework offers seamless compatibility with a wide range of large language models (LLMs) through a unified interface. This allows developers to easily switch between different models such as OpenAI's GPT series, Google Gemini, Anthropic Claude, and Mistral, providing flexibility in model selection based on specific application requirements or performance considerations. The system is powered by the Vercel AI SDK, and its provider-agnostic foundation ensures that developers are not locked into a single ecosystem ^{[1] [4]}.

Modular Architecture and Tool Integration

ADK for TypeScript features a modular and flexible architecture that enables developers to compose agents and integrate various tools. Developers can compose multiple agents, equip them with custom tools, and orchestrate complex workflows. Agents can be equipped with ready-to-use tools or custom-built functionalities. Tool integration is facilitated via the Model Context Protocol (MCP), which supports advanced tooling, function integration, and automatic schema generation, allowing connection to a wide range of MCP servers in the market or the creation of custom ones. This modularity provides developers with complete freedom in designing and extending their AI systems ^{[2] [4]}.

Memory Management and Session Handling

The kit includes robust features for stateful memory and session management, allowing agents to maintain long-term context and state across multiple interactions or sessions. This is crucial for building AI assistants and autonomous agents that require persistent knowledge and continuity in their operations. Built-in session management and memory services are designed for enterprise deployment, ensuring reliability and scalability, making the framework production-ready from day one ^{[1] [4]}.

Tracing and Evaluation

ADK for TypeScript incorporates OpenTelemetry support for tracing and performance evaluation. This allows developers to debug agent behavior, monitor performance metrics, and gain insights into the execution flow of complex multi-agent systems. The tracing capabilities are essential for optimizing agent performance and ensuring reliability in production environments. Additionally, it includes a built-in evaluation system to systematically assess agent performance by testing final responses and execution trajectories ^{[1] [4]}.

Multi-Agent Workflows

ADK for TypeScript provides comprehensive support for orchestrating complex multi-agent workflows. It allows for the coordination of teams of agents to handle intricate tasks and processes. The framework supports various orchestration logics, including sequential, parallel, and LLM-driven routing, enabling developers to design collaborative workflows where specialized agent chains can work together to achieve a common goal ^[2]. This capability is fundamental for building sophisticated AI systems that can break down and manage multi-step tasks effectively.

On-Chain Capabilities

For developers working within the Web3 ecosystem, ADK for TypeScript offers native support for integrating with blockchain and decentralized finance (DeFi) applications. This enables AI agents to interact directly with on-chain data and protocols. These capabilities are powered by a suite of specialized Model Context Protocol (MCP) servers developed by IQAI, designed to enhance and extend the capabilities of ADK TypeScript agents by providing seamless integration with various external services and data sources. Examples of these servers include MCP ABI for smart contract interactions, MCP ATP for the Agent Tokenization Platform, MCP BAMM for Borrow Automated Market Maker operations, MCP Fraxlend for lending platform interactions, MCP IQWiki for IQ.wiki data access, MCP NEAR Agent for NEAR Protocol integration, MCP ODOS for decentralized exchange aggregation, and MCP Discord/Telegram for messaging automation ^[5].

Specific on-chain functionalities include:

• Analyzing DeFi positions on platforms such as Fraxlend and BAMM.
• Executing token swaps through decentralized exchange aggregators like ODOS.
• Managing tokenized agents on the Agent Tokenization Platform (ATP).
• Interacting with smart contracts directly via their Application Binary Interface (ABI).
• Bridging assets or information across different blockchain networks, including NEAR Protocol. These capabilities are powered by a suite of Model Context Protocol (MCP) servers specifically designed for blockchain interaction, facilitating the creation of AI agents that can operate autonomously within decentralized environments ^[1].