How could I choose a different Ollama model in KOOG? For example "qwen3:14b"

Hey, at Kotlinconf Duncan and Dmitry had this auto generated commit messages with Junie is this already available in public Junie version or ?

Is there a KMP library for running LLM inference (locally)?

If I create an agent and call multiple times to

agent.runAndGetResult(it)

it returns always the first response. Is it a bug?

AI Agent versus MCP ——— An AI agent is a software program that can interact with its environment, gather data, and use that data to achieve predetermined goals. AI agents can choose the best actions to perform to meet those goals. Key characteristics of AI agents are as follows: 1. An agent can perform autonomous actions without constant human intervention. Also, they can have a human in the loop to maintain control. 2. Agents have a memory to store individual preferences and allow for personalization. It can also store knowledge. An LLM can undertake information processing and decision-making functions. 3. Agents must be able to perceive and process the information available from their environment. ——— Model Context Protocol (MCP) is a new system introduced by Anthropic to make AI models more powerful. It is an open standard that allows AI models (like Claude) to connect to databases, APIs, file systems, and other tools without needing custom code for each new integration. MCP follows a client-server model with 3 key components: 1. Host: AI applications like Claude 2. MCP Client: Component inside an AI model (like Claude) that allows it to communicate with MCP servers 3. MCP Server: Middleman that connects an AI model to an external system Over to you: Have you used AI Agents or MCP? ——— Source: ByteByteGo

Is there a specific place to ask questions about Junie?

Hi! Koog

0.2.0

has just been released with all the latest updates and fixes. Thank you everyone for your contributions! Full changelog https://github.com/JetBrains/koog/releases/tag/0.2.0 Some notable changes: • media types support (image, audio, document) • token counting support • Lots of Ollama-related bug fixes + dynamic model discovery support for Ollama • Fixed structured data bugs with property serialization • Fixed missing support for Double and List in the annotation-based tools API • … and many other bug-fixes and improvements (see the full CHANGELOG) Slack Conversation

I start to believe that Junie (or Clause as the LLM behind) can't to web searches. It fails to add https://github.com/whyoleg/cryptography-kotlin to my project. It uses a wrong / non-existing artifact & version numbers. I asked it to read the GitHub documentation, but it seemingly can't.

🚀 New release of nirmato-ollama v0.2.0 is out! Ollama API client for Kotlin multiplatform. github - https://github.com/nirmato/nirmato-ollama

Hey guys! I tried Junie for Android dev and it’s quite impressive. Do you know if it is limited/well trained mostly for Kotlin/Android/KMP or will it also be as good in python coding? I wonder if some of you tried it out elsewhere.

Hey, do you know if JetBrains AI can modify the files inside the AS?

i just learned about https://github.com/embabel/embabel-agent today. has anyone played with it?

🎉 Exciting news! My at KotlinConf is now publicly available! Koog is a powerful framework for building AI agents in Kotlin, making it easy to integrate AI into any type of application — whether it’s mobile, backend, or web. If you’re curious about bringing AI into your Kotlin projects, I’d love for you to check it out. Let’s build smarter products together — let’s cook some AI! 🍳🤖

does anyone here know what JB is using to build Junie?

Is there a way in Junie to save the entire transcript of a task? Is it stored on disk?

Hi everyone, We are conducting interviews to gain deeper insights into users’ experiences with Junie. In this study, we're focusing on how developers use Junie for Android and/or Kotlin Multiplatform development and the challenges they face while working with it. The study will take no more than 60 minutes to complete and will be conducted via Google Meet. As a thank-you for devoting your time to our research, you will receive a USD 100 Amazon Gift Card (or the equivalent in your local Amazon store currency) or a one-year JetBrains All Products Pack subscription. Please note that this reward assumes your full participation in the study. ➡️ Click here to complete a short questionnaire. If your profile matches our study criteria, you will be redirected to our Calendly sign-up page. Questions? We’d be more than happy to answer them. We look forward to meeting you!

Hi, I would like to add a terminal command to the whitelist of Junie, e.g., to avoid the confirmation step for

echo filename.txt

. Could you please provide me with a sample of how to define it? My multiple attempts did not work.

Hello! Just wanted to know more about the Junie cloud credits. I’m developing daily for work + on open source projects on my free time. I would go for the AI Ultimate since it says Daily coding with Junie, but I want to be sure it would suite my needs (like I won’t run out of credits after 2 days). I consumed all my free credits in 2 hours. I guess since we’re working on projects with pretty big code size, it’s normal. Also, I saw a ticket on YouTrack about running Junie with local models. We have a server running Ollama in our company, that could be a great improvement to have a base subscription but using local LLMs to have unlimited usage.

Hey guys! which AI are you using as a plugin in the AS?

Gemini

,

Windsurf

,

Junie

?? what more?

This message was deleted.

Would it be possible to pass a "knowledge base" to Junie? I have a compiled AI training documentation (Markdown, 400 KB) that contains examples, explanations, etc. It would be great to have this "loaded" into Junie, so the actual information is there and it does not have to check the code for basic things such as how to add a text editor.

Is Junie supported in regular PyCharm or will it work only in PyCharm Pro? Junie stopped working in PyCharm after recent update - getting an error “We are having trouble accessing LLM…“. At the same time it works just fine on Android Studio. I’ve got Junie with “AI Ultimate” plan. Junie website says it works with PyCharm, Junie plugin website says it works with PyCharm Pro. I had Pro trial, but a week ago it expired and I decided to continue without Pro. Junie worked just fine for couple of days after that, but now, after an update, it is stuck in this “having trouble” message.

✨ Koog 0.3.0 is out! This release brings powerful new capabilities for building scalable and production-ready AI agents, including: 💾 Agent persistence 🗂️ Vector document storage 🔭 Native OpenTelemetry support 🍃 Spring Boot integration 🌟 And more! Learn more here. Slack Conversation

hey all! there are a ton of ppl who use firebender here, and was wondering if we could get a shared slack channel so we can offer quick adhoc technical support? maybe similar to #C06QXPC7064 but #firebender instead? wasn't sure where else to ask this

Am I the only one for who Junie is broken since yesterday? (The window does not load, stays empty)

Hi there! Dummy question: why can't junie run tests for only a single target in a KMP project? no matter how direct and all-caps with a gazillion exclamation marks I tell it to ignore other targets it still runs tests on all targets. It perfectly respects narrowing down the test scope to individual tests, though.

Are there any plans to allow users to choose different LLM models and even connect an existing subscription? I'm happy to pay a premium for Junie but would like to be able to swap models and not get metered on token usage. A fixed bundling price for Junie would make sense while allowing me to use subscriptions (Claude etc) I already pay for

Hey everyone! 👋 We from Flock have been working on a Kotlin multiplatform library called Aigentic for building AI agents, and we would love to get some feedback from the community. It allows you to create AI agents using a clean, native DSL. If you're looking to integrate LLMs into your Kotlin apps, we think you'll find it useful. We are in the early stages, so any thoughts on the API, documentation, or overall experience would be incredibly valuable. - 📚 Check out the docs here: https://aigentic.io/ - ⭐ GitHub: https://github.com/flock-community/aigentic - 🏃‍➡️ Init: https://github.com/flock-community/aigentic-initializr Let us know what you think in this thread. Thanks!

Hi folks! I'm exploring idea of Personal AI companion that follows you in your daily routine, reads incoming messages, help with organising them, reminds about anything that was missed. I'm doing round of pre-flight interviews to verify my hypotheses. I'm looking for Software Engineers to interview (10-15 mins). If you're interested and willing to help please DM me or react with plus1 and I will DM you back 🙂 ! PS: It is unrelated to Kotlin or my job at JetBrains. It is just my initiative that I'd like to explore.

👋 Are there any plans for Junie to support

AGENTS.md

for guidelines? https://agents.md. For now I'm symlinked

.junie/guidelines.md

to

AGENTS.md

and it seems to work, but it would be nice if Junie supported an emerging standard.