Announcing ADK for Java 1.0.0: Building the Future of AI Agents in Java

2026-03-30 · Source: Google Developers Blog - AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Robotics & Autonomous Systems · Depth: Intermediate, long

Summary

Google has released version 1.0.0 of its open-source Agent Development Kit (ADK) for Java, expanding its multi-language ecosystem which already includes Python, Go, and TypeScript. This release introduces significant enhancements for building AI agents, including new grounding tools like `GoogleMapsTool` and `UrlContextTool`, and code executors such as `ContainerCodeExecutor` and `VertexAiCodeExecutor`. The framework now features a centralized `App` container with a plugin architecture for global execution control, improved context engineering via event compaction, and Human-in-the-Loop (HITL) support for `ToolConfirmation` workflows. Additionally, ADK for Java 1.0.0 provides defined contracts for session and memory services, with persistence options in Vertex AI and Firestore, and native support for the Agent2Agent (A2A) Protocol, enabling seamless collaboration between remote agents.

Key takeaway

For AI Architects designing robust, scalable agentic applications, ADK for Java 1.0.0 offers critical features for enhanced control and interoperability. You should explore its new plugin architecture for global guardrails and logging, leverage event compaction for efficient context management, and integrate HITL `ToolConfirmation` for critical operations. The native A2A Protocol support also simplifies building collaborative agent ecosystems, allowing your Java agents to interact with others across different frameworks.

Key insights

ADK for Java 1.0.0 enhances AI agent development with advanced tools, control, and interoperability.

Principles

• Agents require external tools for world interaction beyond LLM knowledge.
• Centralized control improves agent application management and consistency.
• Human-in-the-Loop is crucial for validating agent actions.

Method

ADK for Java enables agent development by integrating tools, managing context with event compaction, supporting HITL workflows, and facilitating agent-to-agent communication via the A2A protocol.

In practice

• Use `GoogleMapsTool` for location-aware agent responses.
• Implement `ToolConfirmation` for human approval of agent actions.
• Configure `LoggingPlugin` for structured agent execution logs.

Topics

• ADK for Java
• AI Agents
• Agent Tools
• Context Engineering
• Human-in-the-Loop

Code references

• google/adk-java
• a2aproject/a2a-java

Best for: AI Architect, AI Engineer, Software Engineer, Machine Learning Engineer

Related on AIssential

• Google ADK for Java 1.0 Introduces New App and Plugin Architecture, External Tools Support, and More — ADK for Java 1.0 enhances AI agent development with new tools, architecture, and collaboration features.
• Java News Roundup: A2A Java SDK 1.0, Jakarta EE 12, JNoSQL, GraalVM, Micrometer, OpenXava, Gradle — The Java ecosystem continues its rapid evolution with numerous SDKs, frameworks, and build tools receiving significant updates.
• [ AI Agent ] Google ADK 2.0 Beta Version 研究— 從 Agent 到 Graph：Google ADK 2.0 到底改了什麼？ — ADK 2.0 shifts AI agent orchestration from implicit LLM-driven prompts to explicit, code-defined workflow graphs.
• Issue #118: Middleware in LangChain — Middleware provides essential control and safety for AI agents, transforming prototypes into production-ready applications.
• Supercharge your AI agents: The New ADK Integrations Ecosystem — ADK's expanded ecosystem enables AI agents to perform real-world actions across diverse platforms with simple code.
• AI Agents: Why exactly do you need them? — AI agents provide crucial conversational intelligence and task management capabilities beyond standalone LLMs.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Google Developers Blog - AI.