Ross ROSS = Recommend OSS · open-source software intelligence for agents

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 observed · 2026-08-28

github.com/JetBrains/koog · homepage · Kotlin · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

84/100

  • Activity 99
  • Release rhythm 93
  • Longevity 34
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: 14.5
  • age_days: 489
  • days_rel: 44
  • days_push: 7
  • n_releases_24m: 23

Full methodology

Adoption not part of the score

4536 stars · 463 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Koog is a JetBrains-built Kotlin/Java framework for creating fault-tolerant, enterprise-ready AI agents on the JVM, with multiplatform deployment to Android, iOS, JS, and WasmJS via Kotlin Multiplatform. It provides a type-safe Kotlin DSL and fluent Java API for agent workflows, tool use, MCP integration, RAG memory, LLM provider switching, and observability.

Use cases

  • build ai agents in kotlin or java
  • create llm agents for spring boot backends
  • run ai agents on android and ios from one codebase
  • add tool calling and mcp support to an llm app
  • build multi-agent workflows with graph strategies
  • add chat memory and rag to a conversational agent
  • switch between openai, anthropic, and ollama models without losing history
  • monitor and trace agent execution with opentelemetry

When to choose

  • your team works on the JVM with Kotlin or Java and wants idiomatic, type-safe agent APIs
  • you need enterprise features like retries, state persistence, and observability out of the box
  • you want one agent codebase deployable to JVM, Android, iOS, and browser via Kotlin Multiplatform
  • you need Spring Boot or Ktor integration and multi-provider LLM switching

When to avoid

  • you want a Python-based agent framework like LangChain or a JS/TS stack
  • your project is not on the JVM or Kotlin Multiplatform targets
  • you need a minimal, lightweight agent loop without framework abstractions
  • you depend on beta modules (planner agents, knowledge retrieval) that may change between releases

Facets

framework · maturity active

agent-framework llm-inference rag mcp chatbot tracing workflow-automation sdk large-language-models artificial-intelligence developer-tools backend mobile-development jvm wasm cross-platform self-hosted kotlin-multiplatform llm-agents spring-boot ktor multi-llm-providers agent-persistence history-compression streaming-api opentelemetry graph-workflows ai-agents android ios docker

10 sources

Member repositories

RepositoryRoleHealth v2
JetBrains/koogmain84

For agents

markdown · JSON · MCP: product_card(name="JetBrains/koog")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem