🏠/jetbrains/2026/05/27/Koog 1.0 Is Out Stable Core, Better Interop, and Multiplatform Observability
📝 Резюме · 🧾 Транскрипт (формат) · 📄 Оригинал (2.6 KB)
https://blog.jetbrains.com/ai/2026/05/koog-1-0-is-out-stable-core-better-interop

JetBrains: Koog 1.0 — стабильное ядро, Java interop, Multiplatform-наблюдаемость

Источник: https://blog.jetbrains.com/ai/2026/05/koog-1-0-is-out-stable-core-better-interop-and-multiplatform-observability/

Краткое содержание

Анонс релиза Koog 1.0 — open-source-фреймворка JetBrains для построения AI-агентов на Kotlin и Java. Анонс прозвучал в keynote KotlinConf 2026 неделей ранее. Koog даёт строительные блоки агентных приложений: tools, workflows, persistence, memory, observability и интеграции с JVM/Kotlin Multiplatform.

Главное в 1.0 — обязательство стабильности. JetBrains гарантирует отсутствие breaking changes для stable-модулей минимум год. Это делает Koog кандидатом для production-агентов в enterprise.

Что нового:

  • Local Android AI — интеграция с провайдерами, включая LiteRT-модели локально на устройстве.
  • Redesigned Java interop layer — чище и согласованнее API.
  • Decoupled HTTP transport — Koog проще встраивается в существующую инфраструктуру; можно подменять HTTP-клиенты.
  • OpenTelemetry — поддержка по всем target'ам, включая Kotlin Multiplatform.
  • Persistence и memory для долгоживущих агентов.
  • Anthropic prompt caching — снижение latency и token-cost для повторяющихся промптов.

Плюс много API cleanup'ов и миграционных улучшений. Рекомендуется работать со stable-модулями; beta-модули — там, где функциональность ещё развивается.

Значимость

Koog становится JetBrains-овским ответом на LangChain/LlamaIndex для JVM-стека. Главное обещание — год без breaking changes — закрывает основное возражение enterprise-команд против early-стадии agent-фреймворков. OpenTelemetry и Anthropic prompt caching — практические рычаги снижения операционной стоимости. Параллельно с серией постов про IDE-как-MCP-провайдер для агентов (Rider finding-tests, IDEA 2026.2 EAP, TeamCity-experiments) Koog 1.0 закрывает противоположную сторону уравнения — фреймворк для построения самих агентов.

🧾 Транскрипт (формат)

Koog 1.0 Is Out: Stable Core, Better Interop, and Multiplatform Observability Source: https://blog.jetbrains.com/ai/2026/05/koog-1-0-is-out-stable-core-better-interop-and-multiplatform-observability/

Last week at the KotlinConf 2026 keynote (watch the recording here), we announced Koog 1.0.

Koog is JetBrains’ open-source framework for building AI agents in Kotlin and Java. It provides the core building blocks for agentic applications: tools, workflows, persistence, memory, observability, and integrations with existing JVM and Kotlin Multiplatform projects.

We introduced Koog at KotlinConf last year. Since then, the framework has evolved through community feedback, internal use, and several public releases. Koog 1.0 is the next step: a more stable foundation for building reliable enterprise-ready agents.

What’s new in Koog 1.0 The biggest change in 1.0 is a strict commitment to stability. To give you a solid foundation for production, we guarantee no breaking changes for stable modules for at least one year.

This release also brings several major improvements across the framework:

Local Android AI: New provider integrations, featuring support for running LiteRT models locally on Android devices. A redesigned Java interop layer with a cleaner and more consistent API. Decoupled HTTP transport, which makes it easier to integrate Koog into existing infrastructure and use different HTTP clients. OpenTelemetry support across Koog targets, including Kotlin Multiplatform environments. Improved persistence and memory support for long-running agents. Anthropic prompt caching support to help reduce latency and token costs for repeated prompts. Koog 1.0 also includes many fixes, API cleanups, and migration improvements that prepare the framework for a more stable long-term evolution. For the full list of changes, see the Koog 1.0 release notes.

Try Koog 1.0 Koog 1.0 marks the framework’s move to a stable core API.

If you’re building agents that need tools, structured workflows, persistence, memory, observability, or integration with existing Kotlin and JVM applications, this release gives you a sturdier foundation to build on.

Explore the docs, update your dependencies, and start with the stable core modules. Add Beta modules only where you need functionality that is still evolving.

Thank you We’d like to thank everyone who tried Koog, submitted issues, shared feedback, and contributed to the project over the past year. Koog 1.0 reflects a lot of that input, and we’re excited to keep building it with the community.