KEMBAR78
--- hide: - toc ---
Agent Development Kit Logo

Agent Development Kit

Agent Development Kit (ADK) is a flexible and modular framework for **developing and deploying AI agents**. While optimized for Gemini and the Google ecosystem, ADK is **model-agnostic**, **deployment-agnostic**, and is built for **compatibility with other frameworks**. ADK was designed to make agent development feel more like software development, to make it easier for developers to create, deploy, and orchestrate agentic architectures that range from simple tasks to complex workflows.

Get started:

=== "Python"

pip install google-adk

=== "Java" ```xml title="pom.xml" com.google.adk google-adk 0.2.0 ``` ```gradle title="build.gradle" dependencies { implementation 'com.google.adk:google-adk:0.2.0' } ```

Start with Python Start with Java Technical overview

--- ## Learn more [:fontawesome-brands-youtube:{.youtube-red-icon} Watch "Introducing Agent Development Kit"!](https://www.youtube.com/watch?v=zgrOwow_uTQ target="_blank" rel="noopener noreferrer")
- :material-transit-connection-variant: **Flexible Orchestration** --- Define workflows using workflow agents (`Sequential`, `Parallel`, `Loop`) for predictable pipelines, or leverage LLM-driven dynamic routing (`LlmAgent` transfer) for adaptive behavior. [**Learn about agents**](agents/index.md) - :material-graph: **Multi-Agent Architecture** --- Build modular and scalable applications by composing multiple specialized agents in a hierarchy. Enable complex coordination and delegation. [**Explore multi-agent systems**](agents/multi-agents.md) - :material-toolbox-outline: **Rich Tool Ecosystem** --- Equip agents with diverse capabilities: use pre-built tools (Search, Code Exec), create custom functions, integrate 3rd-party libraries (LangChain, CrewAI), or even use other agents as tools. [**Browse tools**](tools/index.md) - :material-rocket-launch-outline: **Deployment Ready** --- Containerize and deploy your agents anywhere – run locally, scale with Vertex AI Agent Engine, or integrate into custom infrastructure using Cloud Run or Docker. [**Deploy agents**](deploy/index.md) - :material-clipboard-check-outline: **Built-in Evaluation** --- Systematically assess agent performance by evaluating both the final response quality and the step-by-step execution trajectory against predefined test cases. [**Evaluate agents**](evaluate/index.md) - :material-console-line: **Building Safe and Secure Agents** --- Learn how to building powerful and trustworthy agents by implementing security and safety patterns and best practices into your agent's design. [**Safety and Security**](safety/index.md)