Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems
Koog is a Kotlin Multiplatform framework from JetBrains for building AI agents that run on JVM, Android, iOS, JavaScript, and WasmJS targets. Developers define agent behavior using a type-safe Kotlin DSL, compose complex workflows through graph-based pipelines, and attach custom tools that reach external systems and APIs. It connects to Anthropic's Claude alongside Google, OpenAI, DeepSeek, OpenRouter, Ollama, and Bedrock through a pluggable provider model, and supports the Model Context Protocol so agents can consume MCP tools directly. Built-in agent persistence lets execution resume from specific checkpoints after failures, and an intelligent history compression layer trims token usage during long-running conversations without dropping context. Spring Boot and Ktor integrations make embedding agents into existing JVM services straightforward, while OpenTelemetry exporters feed observability data to providers such as Weights and Biases Weave and Langfuse. The framework targets JVM backend engineers and Kotlin Multiplatform developers who need reproducible, production-grade agent infrastructure without leaving the JVM ecosystem.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/JetBrains/koog && cp koog/*.md ~/.claude/agents/2 items en este repositorio
Use when the user asks to add Java tabs/examples to mkdocs docs that already have Kotlin examples (files under docs/docs/**.md using === "Kotlin" / Knit INCLUDE+SUFFIX blocks). Handles mkdocs-material tabs, Knit directives, @JavaAPI bridge methods, and JVM factory classes.
Resumen de Subagents
Lo que la gente pregunta sobre koog
¿Qué es JetBrains/koog?
+
JetBrains/koog es subagents para el ecosistema de Claude AI. Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems Tiene 4.3k estrellas en GitHub y se actualizó por última vez today.
¿Cómo se instala koog?
+
Puedes instalar koog clonando el repositorio (https://github.com/JetBrains/koog) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar JetBrains/koog?
+
Nuestro agente de seguridad ha analizado JetBrains/koog y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene JetBrains/koog?
+
JetBrains/koog es mantenido por JetBrains. La última actividad registrada en GitHub es de today, con 141 issues abiertos.
¿Hay alternativas a koog?
+
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
Despliega koog en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/jetbrains-koog)<a href="https://claudewave.com/repo/jetbrains-koog"><img src="https://claudewave.com/api/badge/jetbrains-koog" alt="Featured on ClaudeWave: JetBrains/koog" width="320" height="64" /></a>Más Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.