# 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-brow

- **URL**: https://www.freshcrate.ai/projects/koog
- **Author**: JetBrains
- **Category**: MCP Servers
- **Latest version**: `1.0.0` (2026-05-21)
- **License**: Apache-2.0
- **Source**: https://github.com/JetBrains/koog
- **Homepage**: https://docs.koog.ai
- **Language**: Kotlin
- **GitHub**: 4,101 stars, 380 forks
- **Registry**: github
- **Tags**: `agentframework`, `agentic-ai`, `agents`, `ai`, `ai-agents-framework`, `aiagentframework`, `android-ai`, `anthropic`, `kotlin`

## Description

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

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `1.0.0` | 2026-05-21 | High | This is the **first stable release of Koog**. The 1.0 line establishes a long-term-supported surface across the framework: modules are split into stable and beta streams so production code can pin to APIs that won't break without a deprecation cycle, every previously deprecated API has been removed, and the graph DSL's node names are finalized. Alongside that, 1.0 lands a redesigned Java interop layer, decouples HTTP transport from Ktor, brings OpenTelemetry to Kotlin Multiplatform, and adds Ant |
| `0.8.0` | 2026-04-11 | High | # 0.8.0 > Published 10 April 2026  ## Major Features  - **Spring AI Integration**: Added comprehensive Spring AI support with `ChatMemoryRepository` and `VectorStore` integration for seamless persistence and retrieval (#1719, #1763) - **Amazon Bedrock AgentCore Memory**: Introduced `ChatHistoryProvider` backed by Amazon Bedrock AgentCore Memory for managed conversation state (#1758) - **DataDog LLM Observability**: Added DataDog LLM Observability exporter with response metadata forwarding |
| `0.7.3` | 2026-03-26 | Medium | > Published 26 March 2026  ## New Features  - **Bedrock prompt caching**: Added `CacheControl` property on Assistant, User, and System messages within the Prompt and integrated explicit cache blocks in the Bedrock Converse API (#1583)  ## Bug Fixes  - **Agent deadlock fix**: Fixed deadlock when `agent.run()` is called from within `executor.submit` — when the agent was invoked from a worker thread of the configured `ExecutorService`, `runBlocking(context)` would dispatch the coroutine bac |
| `0.7.2` | 2026-03-19 | Low | > Published 19 March 2026  ## Bug Fixes  - **Java API for OpenTelemetry extensions**: Fixed Java API inside `OpenTelemetryConfig` class annotated with `@JavaOverride`   that relied on Kotlin `Duration` class, causing all further attributes to be skipped by the compiler in Langfuse and Weave extensions ([KG-754](https://youtrack.jetbrains.com/issue/KG-754), #1682) - **System prompt preservation in agent builder**: Fixed `systemPrompt` method in agent builders to preserve previously configur |
| `0.7.1` | 2026-03-17 | Low | > Published 17 March 2026  ## Major Features  - **Java API**: Introduced comprehensive Java interoperability across the framework:   - Java API for creating and running agents from pure Java projects (#1185)   - Builder-based Java API for graph strategies (#1581, #1617, #1366)   - Java-friendly API for `AIAgentStorage` with JVM-specific methods (#1600)   - Blocking API builders for `PromptExecutor` and `LLMClient` for Java (#1555, #1604)   - Jackson as the default serializer for Java AP |
| `0.6.4` | 2026-03-04 | Low | ## Major Features - **LLM Client Router**: Added support for routing requests across multiple LLM clients with pluggable load balancing strategies. Includes a built-in round-robin router and fallback handling when a provider is unavailable (#1503)  ## Improvements - **Anthropic models list**: Implemented `models()` for the Anthropic LLM client, consistent with other supported providers ([KG-527](https://youtrack.jetbrains.com/issue/KG-527), #1460) - **Dependency updates**: Updated `io.lettu |
| `0.6.3` | 2026-02-26 | Low | ## Improvements - **Streaming reasoning support**: Models with reasoning capabilities (like Claude Sonnet 4.5 or GPT-o1) now stream their reasoning process in real-time, allowing you to see how the model thinks through problems as it generates responses ([KG-592](https://youtrack.jetbrains.com/issue/KG-592), #1264) - **LLModel API enhancement**: LLM clients now return `List<LLModel>` instead of `List<String>` for improved type safety and direct access to model metadata (#1452) - **Multiple ev |
| `0.6.2` | 2026-02-10 | Low | > Published 10 February 2026  ## Improvements - **Structured output with examples**: Include examples in the prompt with `StructuredRequest.Native` to help LLMs better understand desired data format (#1328, #1396)  ## Bug fixes - **Kotlin/Wasm support**: Applied workaround for Kotlin/Wasm compiler bug which produced invalid Wasm files ([KT-83728](https://youtrack.jetbrains.com/issue/KT-83728), #1365) |
| `0.6.1` | 2026-01-28 | Low | > Published 28 January 2026  ## Major Features **Block of changes**: - **Converse API support in Bedrock LLM client**: Added support for the Converse API in the Bedrock LLM client, enabling richer prompt-based interactions ([KG-543](https://youtrack.jetbrains.com/issue/KG-543), #1384) - **Tool choice heuristics**: Introduced heuristic-based required tool selection via `LLMBasedToolCallFixProcessor` for models that do not support explicit tool choice ([KG-200](https://youtrack.jetbrains.com/ |
| `0.6.0` | 2025-12-22 | Low | > Published 22 December 2025  ## Major Features  - **ACP Integration**: Introduce initial ACP (Agent Communication Protocol) integration to create ACP-compatible agents in Koog (#1253) - **Planner Agent Type**: Introduce new "planner" agent type with iterative planning capabilities. Provide two out-of-the box strategies: simple LLM planner and GOAP (Goal-Oriented Action Planning) (#1232) - **Response Processor**: Introduce `ResponseProcessor` to fix tool call messages from weak models that |

## Citation

- HTML: https://www.freshcrate.ai/projects/koog
- Markdown: https://www.freshcrate.ai/projects/koog.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/koog/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._