← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

Google Releases Agent Development Kit for Kotlin 1.0 with On-Device AI Support

🔄 Updated 3d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • ADK for Kotlin 1.0 reaches feature parity with Python ADK.
  • Supports on-device and hybrid AI for Android applications.
  • Enables hierarchical multi-agent systems and context management.
  • Includes compile-time tool schema generation and human-in-the-loop workflows.

Production-Ready Kotlin ADK Released

Google has launched the Agent Development Kit (ADK) for Kotlin 1.0, providing a production-ready framework for developing AI agents. This kit supports Kotlin, Android, and JVM/server applications, bringing Kotlin to feature parity with Google's existing ADK for Python and Java. It also introduces new Android-specific functionalities for on-device and hybrid AI deployments.

Key Features and Capabilities

The ADK for Kotlin 1.0 allows developers to use idiomatic Kotlin APIs for agent orchestration, tool support, persistence, memory management, and human-in-the-loop workflows. Built on Kotlin Multiplatform, the ADK operates across various platforms, from server-side to mobile devices. Its architecture is designed to be agnostic to specific model backends, session providers, or memory systems.

New features include support for hierarchical multi-agent systems, where a parent agent can delegate tasks to child agents. It also offers context compaction and multi-turn conversation capabilities for automatic context management and history summarization, which reduces token usage. Session management allows agent states to be paused, serialized, and restored, and the kit provides first-class Java interoperability.

Enhanced Tooling and Safety

A significant design choice in ADK for Kotlin 1.0 is its support for tools and human-in-the-loop workflows. Tools can be declared using annotations like @Tool and @Param, which KSP uses to generate Kotlin function schemas at compile time. This approach avoids runtime reflection, improving type-safety and performance, particularly on mobile targets.

Human-in-the-loop workflows help prevent unintended or improper tool usage by requiring explicit human confirmation before sensitive actions are executed. Developers can set `requireConfirmation` in a tool's declaration to enable this feature, which is crucial for high-impact operations such as financial transactions. This allows generated functions to handle sensitive transactions while utilizing Android persistence services like Room for chat sessions, AppSearch for indexed memory, and direct Android storage for files.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~26 min · 21 stories · Sep 23

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Primary sources

GitHub google/adk-kotlin

Reporting from

Google has released the Agent Development Kit (ADK) for Kotlin 1.0, a production-ready framework for building AI agents across Kotlin, Android, and JVM/server applications. This release achieves feature parity with Google's Python ADK and adds Android-specific capabilities for on-device and hybrid AI, allowing developers to build AI agents using Kotlin without relying on Python.