Technology RadarTechnology Radar

Koog

langchain4jmcpstreamingsdk
Assess

Koog is JetBrains' open-source JVM-native AI agent framework — built in Kotlin with first-class Java interoperability since v0.7. It provides structured workflow strategies (functional, graph-based, planning) for building predictable, fault-tolerant AI agents on the JVM. Version 1.0.0-preview (May 18, 2026) introduces a stable/beta module split — stable APIs are now declared and won't break without a deprecation cycle.

Why It's in Assess

Koog launched Java support on March 17, 2026 at v0.7, backed by JetBrains' experience building AI products (IntelliJ AI Assistant, Junie). With 1.0.0-preview now live and the stable/beta API split in place, the framework is on a clear path to GA — but it's still a preview, with no public production adoption data, entering a market where Spring AI and LangChain4j are already established. Track it; don't commit yet.

What makes it interesting:

  • Three workflow strategies: Functional chains (sequential steps), graph-based orchestration (complex pipelines), and planning (autonomous goal pursuit). This is more structured than LangChain4j's agent primitives.
  • Stable/beta module split (1.0.0-preview): Production code can now pin to stable APIs that won't break without a deprecation cycle. Experimental APIs continue to evolve in beta modules — a meaningful step toward commitment-safe adoption.
  • Spring AI integration (0.8.0): ChatMemoryRepository and VectorStore support — Koog can now use Spring AI's persistence and vector infrastructure, positioning it as complementary to Spring AI rather than purely competitive.
  • Pluggable HTTP transport (1.0.0-preview): KoogHttpClient.Factory abstraction enables drop-in use of Java's HTTP client, OkHttp, or Spring's RestClient instead of requiring Ktor.
  • Fault tolerance with persistence: Agent state can be checkpointed and recovered without repeating expensive LLM calls. Note: LangChain4j 1.13.0 also offers agentic state persistence, so this is no longer Koog-unique in the JVM ecosystem.
  • Observability: Built-in OpenTelemetry spans with Langfuse, Weights & Biases Weave, DataDog LLM Observability, and now multiplatform OTel via Ktor-based OTLP/JSON exporter (1.0.0-preview) — works on every Koog target.
  • Expanded backend support (1.0.0-preview): LiteRT LLM client for local Google model execution; Oracle Database ChatHistoryProvider; Amazon Bedrock AgentCore as LongTermMemory backend.
  • Anthropic prompt caching (1.0.0-preview): Automatic and explicit cache control reduces cost and latency for agents that re-send long system prompts.
  • Multi-provider: OpenAI, Anthropic, Google (including LiteRT), DeepSeek, Ollama, and more.

Breaking changes in 1.0.0-preview worth noting:

  • AgentMemory feature replaced by LongTermMemory — migration required for any code using the old API.
  • Planners moved to dedicated agents-planners module — update build dependencies.
  • ExecutorService parameters removed from blocking Java wrappers — the agent's configured dispatcher handles execution now.
  • OpenTelemetry event APIs deprecated and removed — use the new OTLP exporter.

Why not higher:

  • 1.0.0-preview — stable APIs declared but not yet GA. The stable/beta split reduces risk, but production commitment is premature until 1.0.0-RC or GA.
  • No production adoption data — no named organizations using it at scale.
  • Kotlin-first design — while Java interop has improved significantly (1.0.0-preview's redesigned entry points, deadlock prevention), the API idioms may feel less natural to pure Java teams than Spring AI's annotation-driven model.
  • Crowded space — Spring AI owns the Spring ecosystem, LangChain4j owns the framework-agnostic space. Koog needs to differentiate beyond "JetBrains made it."

When to Evaluate Koog Over Alternatives

Scenario Recommendation
Kotlin-first project needing agents Koog is the natural fit
Spring Boot app adding basic LLM features Spring AI — more mature, familiar abstractions
Framework-agnostic Java with complex agents LangChain4j — 1.x stable, wider community
Need fault-tolerant agent state recovery Koog or LangChain4j 1.13.0 — both now offer persistence
IntelliJ-heavy team wanting IDE integration Koog + ACP for JetBrains IDE connectivity

Key Characteristics

Property Value
Status v1.0.0-preview (May 18 2026)
License Apache 2.0
Provider JetBrains
Requires Java 17+ / Kotlin 1.9+
GitHub JetBrains/koog
Website jetbrains.com/koog
Docs docs.koog.ai

Further Reading