Koog
Open-source task automation and interactive agents for multi agent, tool use, agentframework.
What does this agent do, and when should you use it?
The repository describes Koog as: 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. This profile is a source-based catalog entry; an independent FARS review is still pending.
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.
- Prototype a personal or team task-automation workflow.
- Test the documented interaction and tool-use model.
- Assess whether its deployment model fits local operations.
What are this agent's strengths and limitations?
- Public source and README are available for inspection.
- Focused on multi agent, tool use, agentframework.
- Setup, model-provider support, and maturity must be confirmed against the current release.
- No independent FARS score has been assigned yet.
How do you install or deploy this agent?
Follow the current installation instructions in the [repository README](https://github.com/JetBrains/koog#readme). Requirements and provider setup vary by release.
How do you use this agent?
Start with the examples and quickstart in the [repository documentation](https://github.com/JetBrains/koog#readme), then test the workflow with limited permissions and non-sensitive data.