**Agent Development Kit (ADK)** is an open-source agent development
framework that lets you build, debug, and deploy reliable AI agents at
enterprise scale. Start with agents and tools and grow into
sophisticated multi-agent systems, ADK allows developers to build
everything from personal AI assistants to mission-critical business
workflows.


ADK provides developers with a comprehensive suite of tools to build,
run, evaluate, and scale AI architectures. Users can leverage flexible
orchestration to define predictable pipelines using workflow agents
or rely on agent-coordinated dynamic routing for more adaptive behavior.
It natively supports multi-agent architectures, allowing developers to
compose specialized teams of agents that can collaborate and delegate
tasks. ADK features a rich tool ecosystem for integrating third-party
applications and your own custom code. Apply built-in and partner
evaluation tools to test execution trajectories. Run agents locally or
scale them globally using Runtime, Cloud Run,
or Google Kubernetes Engine.


ADK is available in Python, TypeScript, Go, and Java.
![](https://adk.dev/assets/agent-development-kit.png)

## Start building

### [Get started](https://adk.dev/get-started/)


Set up your environment and get an agent running in a few minutes.

### [Tools and integrations](https://adk.dev/integrations/)


Check out the list of pre-built tools and integrations that you can use with ADK agents.

### [Technical overview](https://adk.dev/get-started/about/)


Learn about the core concepts and key capabilities offered by ADK.