Building Better Agents: What’s New in Koog 0.3.0

Daniela Bentrup Olga Galchenko

We’ve just released Koog 0.3.0, which comes with many updates that make building, running, and managing intelligent agents easier.

This version focuses on durability, speed, observability, and smoother integration with real-world systems. If you’ve been exploring how to develop your own intelligent agent that can handle complex workflows, the new and updated Koog could be just what you’re looking for. Find it now on GitHub.

Here’s a breakdown of what’s new in v0.3.0:

Learn more

Agents that don’t forget

In Koog 0.3.0, agents can now remember what they were doing. You can save and reload their state from a local disk, S3 buckets, or a database. This powerful feature enables server-side developers to build fault-tolerant agentic solutions by restoring the agent’s entire state machine at the exact point of strategy execution instead of just recovering the message history.

This means you can shut down machines without losing progress. There’s also a new checkpoint feature, so agents can roll back to any earlier state if needed.

Smarter storage for better retrieval

Koog now supports persistent vector storage for docs. Whether you’re working with local files or connecting to a vector database, you can use Koog to build retrieval-augmented generation (RAG) pipelines.

The setup is modular, allowing you to add support for different formats, ranking methods, and backends.

Built-In observability and moderation for agents

We’ve added native OpenTelemetry support. This means you can now trace, log, and measure your agents using the same tools you’d use elsewhere in your system, enabling you to spot bottlenecks, track behaviour, and keep things running smoothly.

And if you’re deploying in regulated environments, there’s also built-in support for moderation. Agents can now check their own outputs to make sure they’re appropriate and safe. This is especially useful when trust and compliance are a priority.

Running tasks in parallel

Sometimes your agent graph includes steps that can run independently. Koog now supports parallel execution of those nodes, following a familiar MapReduce-style API.

You can launch several branches simultaneously, transform their results asynchronously, and collect everything at the end. This approach is useful when you want to try multiple strategies at once or speed up multi-step workflows.

A better fit for your stack

Koog now works better with Spring. If you’re using Spring Boot, you’ll get ready-made beans and auto-configured LLM clients out of the box.

The release also adds support for ReAct-style agent thinking. Agents can now follow step-by-step reasoning paths, switching between thoughts and actions.

You’ll also find updates that help agents handle uncertainty better. The new Retry component makes them more resilient, and multiple-choice reasoning gives them new ways to explore options and respond to user preferences.

A few more things to get excited about

This version brings a handful of other improvements that are worth highlighting:

• Agents can now receive image input when running with Ollama-backed models.
• Full WebAssembly (WASM) support means you can now deploy Koog agents to the browser.
• Native support for Amazon Bedrock has been added.
• Fact-retrieval history compression has been improved to help agents focus on the correct data without getting confused by unrelated context.
• Agents can now work with arbitrary input and output types, providing greater flexibility in the execution flow.
• We’ve also fixed several bugs to make the overall UX smoother.

Koog 0.3.0 is a step toward making agents more robust, portable, and valuable.

Many of these updates were implemented on the basis of community feedback, so thanks to everyone who’s tried it out, opened issues, or shared ideas.

If you haven’t yet, now’s a good time to try Koog and see what you can build.

Your contributions make the difference

We’d like to take this opportunity to extend a huge thank-you to the entire community for contributing to the development of Koog through your feedback, issue reports, and pull requests!

Here’s a list of this release’s top contributors:

Nathan Fallet Azure OpenAI and other general improvements

Didier Villevalois Ollama updates

Jason Pearson AWS Bedrock improvements

Denys Kurylenko MCP enhancements

Subscribe to JetBrains AI Blog updates

Subscribe form

By submitting this form, I agree to the JetBrains Privacy Policy Notification icon

By submitting this form, I agree that JetBrains s.r.o. ("JetBrains") may use my name, email address, and location data to send me newsletters, including commercial communications, and to process my personal data for this purpose. I agree that JetBrains may process said data using third-party services for this purpose in accordance with the JetBrains Privacy Policy. I understand that I can revoke this consent at any time in my profile. In addition, an unsubscribe link is included in each email.

Submit

Thanks, we've got you!