Search

More Filters

Show More
Add Listing
Go Back

koog

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Koog is a Kotlin-based framework for building and running AI agents using idiomatic Kotlin. It provides infrastructure to create agents that interact with external tools, manage complex workflows and maintain conversation state. The project is aimed at developers who want to implement production-ready agents with features such as model management via Model Context Protocol (MCP), vector embeddings for semantic search, persistent memory across sessions and agents, and configurable tracing and debugging. Koog supplies ready-to-use components and a modular feature system so teams can compose capabilities for simple chatbots up to enterprise-scale applications. The framework targets multiple platforms and runtimes, including JVM, JavaScript and WasmJS, and supports popular LLM providers to power agent behavior.

Links

Stars
1551
App URL
https://github.com/JetBrains/koog
Github Repository
https://github.com/JetBrains/koog/blob/main/README.md

Categorization

App Details

Features
Koog offers a pure Kotlin implementation so agents are written in natural Kotlin idioms. It integrates with MCP for enhanced model management and supports vector embeddings for retrieval and semantic search. You can create custom tools for external systems and use pre-built components to accelerate development. The framework includes intelligent history compression strategies to optimize token usage, a streaming API with real-time response processing and parallel tool calls, persistent agent memory for knowledge retention, and comprehensive tracing for debugging and monitoring executions. Complex agent behaviors can be modeled with flexible graph-based workflows. The architecture is modular and composable, designed to scale from simple prototypes to larger applications, and it is multiplatform across JVM, JS and WasmJS. Supported LLM providers include Google, OpenAI, Anthropic, OpenRouter and Ollama.
Use Cases
Koog helps developers deliver agentic applications faster by providing an end-to-end Kotlin framework with production-focused features. Its pure Kotlin design reduces impedance between application code and agent logic, while ready-to-use components and a modular feature system shorten implementation time. Embeddings and memory support enable retrieval-augmented behavior and cross-session knowledge retention. Streaming and parallel tool calls allow real-time workflows and lower latency in multi-step processes. Tracing and history compression improve observability and cost efficiency when using large models. The project is distributed via Maven Central as ai.koog:koog-agents (version 0.3.0 shown) and integrates into Gradle and Maven builds. It supports JVM, JS and WasmJS targets and requires JDK 17 or higher on the JVM, making it practical for teams building scalable, cross-platform agent solutions.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*