Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond

Summary

ADK for Kotlin 1.0 is announced as a general availability release for building AI agents with Kotlin across Android, JVM server applications, and Java-integrated systems. The release targets a production-ready toolkit while preserving an idiomatic, lightweight, composable approach, and it reaches feature parity with ADK 1.0 Core, including hierarchical agents, context compaction, human-in-the-loop confirmation, resumable sessions, annotated tools, and Java interoperability. A Kotlin Multiplatform core stays agnostic to model backends, session providers, and memory systems, while Android extensions support LiteRT-LM, ML Kit (beta), Firebase AI Logic, Room, AppSearch, and file artifacts. The database incident example combines compile-time KSP-generated function schemas, suspend-capable @Tool functions, and dynamically loaded SKILL.md playbooks with progressive disclosure. The release provides 1.0.0 dependencies, documentation, a repository, and sample applications.

Takeaways

1. 1

   ADK for Kotlin 1.0 aligns with ADK Python and Java capabilities, including hierarchical multi-agent systems, context compaction, confirmation flows, session resumability, annotation-based tools, and Java interoperability.

2. 2

   KSP generates function-call definitions from Kotlin @Tool and @Param annotations at build time, supporting type-safe schemas, suspend functions, and zero runtime reflection.

3. 3

   Android examples combine Room session persistence, AppSearch memory, and file artifacts with multi-turn human approval for sensitive actions; the transfer example is explicitly not designed to meet compliance requirements.