google/adk-java

An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

What it solves

It provides a code-first toolkit for Java developers to build, evaluate, and deploy sophisticated AI agents. It specifically addresses the need for fine-grained control and flexibility over agent behavior and orchestration, especially for those integrating with Google Cloud services.

How it works

Developers define agent logic, tool use, and orchestration directly in Java code. The toolkit allows for the creation of single agents or modular multi-agent systems where specialized agents are composed into hierarchies. It supports integrating pre-built tools, custom functions, and OpenAPI specifications to extend agent capabilities.

Who it’s for

Java developers who want to build advanced AI agents with high testability, versioning, and tight integration with the Google ecosystem.

Highlights

  • Code-First Approach: Logic and orchestration are defined in Java for better debugging and versioning.
  • Modular Multi-Agent Systems: Ability to compose multiple specialized agents into scalable hierarchies.
  • Rich Tool Ecosystem: Supports custom functions, OpenAPI specs, and pre-built tools like Google Search.
  • Development UI: Includes a built-in interface for testing, evaluating, and debugging agents.
  • A2A Integration: Supports remote agent-to-agent communication via the A2A protocol.

Related

  • Project
  • Project
  • Project
  • Project
  • Project