AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompareGuides
Submit Tool
ToolsCategoriesTrendingNewCompareGuides
Home/
Multi-Agent/
adk-java
adk-java logo

adk-java

Active·★ 1.8k·Apache-2.0·Updated 2026-10-14
★ Trending★ Essential

Agent Development Kit (ADK) for Java is an open-source, code-first toolkit for building, evaluating and deploying AI agents. The README says it is meant for developers who want fine-grained control over agents that are tightly integrated with Google Cloud services, defining behavior, orchestration and tool use directly in code so it can be debugged, versioned and deployed anywhere from a laptop to the cloud. Its features include a tool ecosystem (pre-built tools, custom functions, OpenAPI specs), code-first definitions in Java and modular multi-agent systems.

Add `com.google.adk:google-adk` (version 0.3.0 in the README) to your Maven dependencies, plus `google-adk-dev` for the built-in development UI that lets you test, debug and showcase agents. The example builds an `LlmAgent` with a name, description, model such as `gemini-2.0-flash`, an instruction and a `GoogleSearchTool`. For remote agent-to-agent communication it integrates with the A2A protocol, with setup in `a2a/README.md`. The README's "Evaluate Agents" section is marked coming soon. Documentation and samples live in the ADK docs and the adk-samples repository, and the project is Apache-2.0 licensed.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-11.

License
Apache-2.0
Latest release
v1.11.0 · 2026-10-02
Last commit
2026-10-11
Contributors
71
Forks
432
Open issues and PRs
132
First published
2025-05-05

Source: GitHub, npm and PyPI public APIs.

#Java#AI Agents#Agent Development#Google Cloud#Code-First#Web Browsing#Coding
$ Install
$ <dependency> <groupId>com.google.adk</groupId> <artifactId>google-adk</artifactId> <version>0.3.0</version> </dependency>
↗ Visit site★ GitHub
01

Features

01Rich Tool Ecosystem for diverse agent capabilities and Google ecosystem integration
02Code-First Development for defining agent logic, tools, and orchestration in Java
03Modular Multi-Agent Systems for designing scalable applications with specialized agents
04Built-in Development UI for testing, evaluating, debugging, and showcasing agents
05Integration with A2A protocol for remote agent-to-agent communication
02

Why choose it

+Official Google toolkit with the same concepts as the Python ADK
+Code-first design makes agents testable and easy to version
+Built-in development UI for testing and debugging agents
+Integrates with the A2A protocol for remote agent communication
03

Trade-offs

!Aimed at Google Cloud and Gemini; examples use Gemini models and Google Search
!The README's agent evaluation section is marked coming soon
!Version 0.3.0 in the README suggests an early API that may change
!The README is short and defers most guidance to the docs site and samples
04

Compatibility

LLMs (e.g., Gemini)
LLM Support
Verified via docs
Google Cloud
Native Integration
Verified via docs
A2A Protocol
Protocol Integration
Verified via docs
Python ADK
Feature Parity
Verified via docs
05

Quick start

1
$ <dependency>
2
$ <groupId>com.google.adk</groupId>
3
$ <artifactId>google-adk</artifactId>
4
$ <version>0.3.0</version>
5
$ </dependency>
06

Use cases

↳Building advanced AI agents with fine-grained control over their behavior and orchestration.
↳Integrating AI agents tightly with existing services, especially within Google Cloud.
↳Designing and deploying scalable, modular multi-agent systems for complex tasks.
07

Alternatives

Microsoft AutoGen logo
Microsoft AutoGen★ 61.4k
A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.
CrewAI logo
CrewAI★ 59.7k
Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.
headroom logo
headroom★ 75.4k
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. Around 20% fewer tokens for coding agents and 60-95% fewer for JSON, with the same answers. Library, proxy, and MCP server.

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases
Context7 logo
Context7★ 63.0k
MCP Server that provides up-to-date code documentation for LLMs and AI code editors.
MindsHub (formerly MindsDB) logo
MindsHub (formerly MindsDB)★ 39.8k
MindsHub (formerly MindsDB) is an agent workspace for knowledge work and software development, with connected data sources, a model router across frontier and open models, open-source agent harnesses, and publishable artifacts.
GitHub MCP Server logo
GitHub MCP Server★ 33.6k
GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).
n8n logo
n8n★ 207.4k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Brave Search MCP logo
Brave Search MCP★ 1.5k
Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.
See all alternatives →
07
Alternatives
Stats
GitHub Stars★ 1.8k
Last commit1d ago
StatusActive
LicenseApache-2.0
CategoryMulti-Agent
Trend (30d)
+0k↑ 4.5%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad