JetBrains/koog

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

What it solves

Koog is a framework for building AI agents that allows developers to create agents that can interact with tools, manage complex workflows, and maintain conversations with users using an idiomatic, type-safe Kotlin and Java API.

How it works

It provides a modular architecture where developers can define agent behaviors using graph-based workflows and custom tools. It supports a wide range of LLM providers (including Google, OpenAI, Anthropic, DeepSeek, and Ollama) and integrates with the Model Context Protocol (MCP) and Agent Client Protocol (ACP). The framework also includes built-in mechanisms for history compression to save tokens, state persistence for fault tolerance, and RAG-based knowledge retrieval using vector embeddings.

Who it’s for

JVM and Kotlin developers who want to build AI agents that can be deployed across multiple platforms (JVM, JS, WasmJS, Android, and iOS) and integrated into enterprise applications using frameworks like Spring Boot and Ktor.

Highlights

  • Multiplatform Support: Deploy agents across JVM, JS, WasmJS, Android, and iOS.
  • LLM Flexibility: Switch between different LLM providers or reroute between them without losing conversation history.
  • Enterprise Integration: Built-in support for Spring Boot, Ktor, and OpenTelemetry exporters (W&B Weave, Langfuse).
  • Reliability: Features built-in retries and agent state persistence to restore execution at specific points.
  • Advanced Memory: Includes intelligent history compression and RAG-based knowledge retrieval.
  • Standardized Protocols: Integration with Model Context Protocol (MCP) and Agent Client Protocol (ACP).

Related

  • Project
    Ingenimax/agent-sdk-go

    A powerful Go framework for building production-ready AI agents with integrated memory management, multi-LLM support, and enterprise-grade observability.

  • Project
    microsoft/agent-framework

    A multi-language framework for building production-grade AI agents and multi-agent workflows in .NET and Python, featuring graph-based orchestration and built-in observability.

  • Project
    opensolon/solon-ai

    A full-scenario Java AI development framework for building LLM applications, RAG knowledge bases, and multi-agent systems with native integration into the Java ecosystem.

  • Project
    phodal/auto-dev

    An AI-native multi-agent development platform built on Kotlin Multiplatform that integrates coding, review, and research agents across IDEs and multiple devices.

  • Project
    cloudwego/eino

    An LLM application development framework for Golang that provides tools for building AI agents, multi-agent coordination, and graph-based workflows.