koog

Portable AI agent runtime for the JVM. One @agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

A modern, BYOK and FOSS android app to summarize videos(YouTube, BiliBili), articles, images and documents with AI/LLM

Agentic ✧ Gemma Inference for Android System Intelligence

AI-powered test automation tool which allows developers to run mobile automated tests

LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.

AI agent toolkit for Compose multiplatform

WhatsApp bot powered by Google Gemini 3 Flash Preview and the Koog AI agent framework.

Community blueprints, runnable examples, and architecture guidance for building AI agent systems with Koog 1.0.

Kotlin + SpringBoot + Koog + Promptfoo example

The finishing touch to JetBrains Koog

A bridge between JetBrains Koog framework and on-device LLM inference engines

AI-powered deep research agent running locally via Ollama. Multi-agent pipeline with persistent memory, RAG, and GraalVM native image support.

Edge Agent Lab is an Android testing platform for evaluating small language model (SLM) agents directly on mobile devices.

一个具备情感、记忆、心流、主动行为，以及事项提醒与自我规则管理的 AI 群聊机器人。

JCConf 2025《以 Kotlin 打造 AI Agent：Koog Agent Framework 實戰入門》範例程式碼

A Modular MultiPlatform App (KMP + CMP + Koog) Features personality synthesis via LLMs, localized RAG, Decompose, Koin, DB.

AI-driven, Pentest Android APKs, 100% local . Runs hooks, then an LLM agent investigates the evidence in a tool-use loop following leads across dozens of inspection tools until it produces a vulnerability report.

This project is AI-powered test-automation tool which allows developers to run mobile automated tests

WebView automation for Kotlin Multiplatform. Run page workflows in an embedded WebView on Android, iOS and desktop, from your app, a test, or an LLM agent over MCP or Koog.

Advanced large language model deployment framework featuring ultra-long context window tokenization, multi-stage semantic reasoning, and automated tool pipeline integration.