[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-7308":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":47,"readmeContent":48,"aiSummary":49,"trendingCount":16,"starSnapshotCount":16,"syncStatus":50,"lastSyncTime":51,"discoverSource":52},7308,"koog","JetBrains\u002Fkoog","JetBrains","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","https:\u002F\u002Fdocs.koog.ai",null,"Kotlin",4338,426,160,70,0,4,29,158,23,92.39,"Apache License 2.0",false,"develop",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"agentframework","agentic-ai","agents","ai","ai-agents-framework","aiagentframework","android-ai","anthropic","genai","generative-ai","java","jvm","kotlin","ktor","llm","mcp","multi-agent-systems","ollama","openai","spring","2026-06-12 04:00:33","# Koog\n\n[![Kotlin Beta](https:\u002F\u002Fkotl.in\u002Fbadges\u002Fbeta.svg)](https:\u002F\u002Fkotlinlang.org\u002Fdocs\u002Fcomponents-stability.html)\n[![Maven Central](https:\u002F\u002Fimg.shields.io\u002Fmaven-central\u002Fv\u002Fai.koog\u002Fkoog-agents)](https:\u002F\u002Fsearch.maven.org\u002Fartifact\u002Fai.koog\u002Fkoog-agents)\n[![JetBrains incubator project](https:\u002F\u002Fjb.gg\u002Fbadges\u002Fincubator.svg)](https:\u002F\u002Fgithub.com\u002FJetBrains#jetbrains-on-github)\n[![Kotlin](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fkotlin-2.2-blue.svg?logo=kotlin)](http:\u002F\u002Fkotlinlang.org)\n[![CI status](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fchecks-status\u002FJetBrains\u002Fkoog\u002Fmain)](https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fkoog\u002Factions?query=branch%3Amain)\n[![GitHub license](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002FJetBrains\u002Fkoog)](LICENSE.txt)\n\nBuild status:\n\n[![Checks](https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fkoog\u002Factions\u002Fworkflows\u002Fchecks.yml\u002Fbadge.svg?branch=develop)](https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fkoog\u002Factions\u002Fworkflows\u002Fchecks.yml?query=branch%3Adevelop)\n[![Heavy Tests](https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fkoog\u002Factions\u002Fworkflows\u002Fheavy-tests.yml\u002Fbadge.svg?branch=develop)](https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fkoog\u002Factions\u002Fworkflows\u002Fheavy-tests.yml?query=branch%3Adevelop)\n[![Ollama Tests](https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fkoog\u002Factions\u002Fworkflows\u002Follama-tests.yml\u002Fbadge.svg?branch=develop)](https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fkoog\u002Factions\u002Fworkflows\u002Follama-tests.yml?query=branch%3Adevelop)\n\nUseful links:\n\n* [Documentation](https:\u002F\u002Fdocs.koog.ai\u002F)\n* [API reference](https:\u002F\u002Fapi.koog.ai\u002F)\n* [Slack channel](https:\u002F\u002Fdocs.koog.ai\u002Fkoog-slack-channel\u002F)\n* [Issue tracker](https:\u002F\u002Fyoutrack.jetbrains.com\u002Fissues\u002FKG)\n\n## Overview\n\nKoog is a Kotlin-based framework designed to build and run AI agents entirely in idiomatic Kotlin and Java API. It lets you create agents that can interact with tools, handle complex workflows, and communicate with users.\n\n### Key features\n\nKey features of Koog include:\n\n- **Multiplatform development**: Deploy agents across JVM, JS, WasmJS, Android, and iOS targets using Kotlin Multiplatform.\n- **Reliability and fault-tolerance**: Handle failures with built-in retries and restore the agent state at specific points during execution with the agent persistence feature.\n- **Intelligent history compression**: Optimize token usage while maintaining context in long-running conversations using advanced built-in history compression techniques.\n- **Enterprise-ready integrations**: Utilize integration with popular JVM frameworks such as Spring Boot and Ktor to embed Koog into your applications.\n- **Observability with OpenTelemetry exporters**: Monitor and debug applications with built-in support for popular observability providers (W&B Weave, Langfuse).\n- **LLM switching and seamless history adaptation**: Switch to a different LLM at any point without losing the existing conversation history, or reroute between multiple LLM providers.\n- **Integration with JVM and Kotlin applications**: Build AI agents with an idiomatic, type-safe Kotlin DSL designed specifically for JVM and Kotlin developers.\n- **Model Context Protocol integration**: Use Model Context Protocol (MCP) tools in AI agents.\n- **Agent Client Protocol integration**: Build ACP-compliant agents that can communicate with standardized client applications using the Agent Client Protocol (ACP).\n- **Knowledge retrieval and memory**: Retain and retrieve knowledge across conversations using vector embeddings, RAG, and shared agent memory.\n- **Powerful Streaming API**: Process responses in real-time with streaming support and parallel tool calls.\n- **Modular feature system**: Customize agent capabilities through a composable architecture.\n- **Flexible graph workflows**: Design complex agent behaviors using intuitive graph-based workflows.\n- **Custom tool creation**: Enhance your agents with tools that access external systems and APIs.\n- **Comprehensive tracing**: Debug and monitor agent execution with detailed, configurable tracing.\n\n### Available LLM providers and platforms\n\nThe LLM providers and platforms whose LLMs you can use to power your agent capabilities:\n\n- Google\n- OpenAI\n- Anthropic\n- DeepSeek\n- OpenRouter\n- Ollama\n- Bedrock\n\n### Quickstart example\n\nTo help you get started with AI agents, here is a quick example:\n\n```kotlin\nfun main() = runBlocking {\n    \u002F\u002F Before you run the example, assign a corresponding API key as an environment variable.\n   val apiKey = System.getenv(\"OPENAI_API_KEY\") \u002F\u002F or Anthropic, Google, OpenRouter, etc.\n\n   val agent = AIAgent(\n      promptExecutor = simpleOpenAIExecutor(apiKey), \u002F\u002F or Anthropic, Google, OpenRouter, etc.\n      systemPrompt = \"You are a helpful assistant. Answer user questions concisely.\",\n      llmModel = OpenAIModels.Chat.GPT4o\n   )\n\n   val result = agent.run(\"Hello! How can you help me?\")\n   println(result)\n}\n```\n\n## Using in your projects\n\n### Supported targets\n\nCurrently, the framework supports the JVM, JS, WasmJS and iOS targets.\n\n### Requirements\n\n- JDK 17 or higher is required to use the framework on JVM.\n- Kotlin 2.3.10 or higher should be set explicitly in existing projects. Please check the [libs.versions.toml](gradle\u002Flibs.versions.toml) to know more about Kotlin dependencies (currently it uses kotlinx-coroutines 1.10.2, kotlinx-serialization 1.10.0 and kotlinx-datetime 0.7.1)\n\n### Gradle (Kotlin DSL)\n\n1. Add dependencies to the `build.gradle.kts` file:\n\n    ```\n    dependencies {\n        implementation(\"ai.koog:koog-agents:0.7.3\")\n    }\n    ```\n2. Make sure that you have `mavenCentral()` in the list of repositories.\n### Gradle (Groovy)\n\n1. Add dependencies to the `build.gradle` file:\n\n    ```\n    dependencies {\n        implementation 'ai.koog:koog-agents:0.7.3'\n    }\n    ```\n2. Make sure that you have `mavenCentral()` in the list of repositories.\n### Maven\n\n1. Add dependencies to the `pom.xml` file:\n\n    ```\n    \u003Cdependency>\n        \u003CgroupId>ai.koog\u003C\u002FgroupId>\n        \u003CartifactId>koog-agents-jvm\u003C\u002FartifactId>\n        \u003Cversion>0.7.3\u003C\u002Fversion>\n    \u003C\u002Fdependency>\n    ```\n2. Make sure that you have `mavenCentral` in the list of repositories.\n## Contributing\nRead the [Contributing Guidelines](CONTRIBUTING.md).\n\n## Code of Conduct\nThis project and the corresponding community are governed by the [JetBrains Open Source and Community Code of Conduct](https:\u002F\u002Fgithub.com\u002Fjetbrains#code-of-conduct). Please make sure you read it.\n\n## License\nKoog is licensed under the [Apache 2.0 License](LICENSE.txt).\n\n## Support\n\nPlease feel free to ask any questions in our [official Slack\nchannel](https:\u002F\u002Fdocs.koog.ai\u002Fkoog-slack-channel\u002F) and to\nuse [Koog official YouTrack project](https:\u002F\u002Fyoutrack.jetbrains.com\u002Fissues\u002FKG)\nfor filing feature requests and bug reports.\n\n\n","Koog 是一个基于 Kotlin 的 JVM 框架，用于构建可预测、容错且企业级的 AI 代理，适用于从后端服务到 Android 和 iOS，乃至浏览器环境的各种平台。其核心功能包括多平台开发支持、内置重试机制和状态恢复以增强可靠性、智能历史压缩技术优化对话中的令牌使用等。此外，Koog 还提供了与 Spring Boot 和 Ktor 等流行框架的集成，并支持 OpenTelemetry 导出器以实现应用监控。该框架特别适合需要在不同平台上部署复杂AI解决方案的企业或开发者，尤其是在需要高度可靠性和跨平台一致性的场景下。",2,"2026-06-11 03:11:43","top_language"]