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.

🚀

Koog 0.4.0

is here! Koog is not only the most advanced AI framework for the JVM, but also the first framework that brings full-scale agentic flows to backend, Android and now – iOS! Highlights include: 🕵️‍♀️ Langfuse and W&B Weave support 🧩 Ktor integration 🏛️ Native structured output 📱iOS target 🧠 GPT-5 Learn more here.

Hi folks! Just published my very first Medium article about Koog and AI Agents 🎉 This one’s an introduction, and the first in a whole series I’m preparing. The next article will be out tomorrow, so stay tuned! Here’s the list of upcoming topics, subscribe if you don’t want to miss out: • Mixing the secret AI sauce: How to design a flexible, graph-based strategy in Koog. • Cooking AI agents for any taste: Koog — the only multiplatform full-scale AI framework in the world! • Kooging with different sauces: Non-graph and planning strategies, and when to use them in AI agents. • Island cruise between Kotlin and Java with a chief: Using Koog seamlessly from Java applications. • Observing the kitchen: Leveraging Langfuse and W&B Weave to debug and monitor your AI agents with Koog. • Full recipe for fault-tolerant AI agents: Building resilient systems with Koog’s Persistency feature in production. • Koog yourself a cheap meal: Cost-optimizing AI agents for production usage with Koog framework • and much more!

Hi everyone, We are conducting interviews to gain deeper insights into Kotlin users' experiences with AI tools. The study will take no more than 30 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 50 Amazon Gift Card (or the equivalent in your local Amazon store currency) or a six-month 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!

when will Android Studio provide an AI tool for refactorings that agents can use so Gemini or other models can have an accurate and efficient ability to make large changes? Right now Gemini is making way too many edits inaccurately with grep and edit-file to be trusted.

newest intellij eap:

Is there a junie version for it?

Hi! If you want to learn how to build AI agents for multiplatform, or get a few practical advices how to deal with LLM trying to escape your tool calling requirements — feel free to check out my new article: Cooking AI Agents for Every Flavor: JVM Backend, Android, iOS, JS, and WASM in One Pot

I have a general question about best practices with Junie. I am using it in a fairly large project, and almost every question/task I ask ends up timing out or throwing exceptions, as shown in the attached screenshot. My question is whether the context has become too large. How can I influence this, or reset Junie to start with the basic context from AGENTS.md or .junie/guidelines.md?

Looks like in adding Sonnet 4.5 you broke all our licences this morning, our paid for credits evaporated.

Has anyone else tried the Claude agent in JetBrains AI? My coworker has it, but I'm on EAP IntelliJ Ultimate and do not w/ a Pro Subscription for AI. Is that a limitation of EAP? Should I roll back?

Any plan to add mistral models ?

If you haven’t seen, Koog

0.5.0

came out with full A2A support among other cool things. And what’s even cooler — it features

full-scale A2A SDK for Kotlin Multiplatform

(jvm, android, js, wasm, ios) that you can use with or even without Koog! It’s a library of its own! https://blog.jetbrains.com/ai/2025/10/koog-a2a-building-connected-ai-agents-in-kotlin/

Did you know if AI plugin agent like gemini AI assistant, github copilot or more, send the context of the project if you configure local model ? Did you check it before accessibility on IDE plugins maketplace ? And Jetbrains AI Assistant plugin can be plug on local model ?

Firebender AI using the emulator directly to verify its code changes to the login page works read more at https://www.linkedin.com/feed/update/urn:li:activity:7380995352461684736

I updated documentation regarding tool use in anthropic-sdk-kotlin: https://github.com/xemantic/anthropic-sdk-kotlin/blob/main/docs/tool_use_guide.md In the 0.23.0 version I also decoupled tool execution from Anthropic API classes.

Hello “Did the Transformers paper basically replace and kill all other AI algorithms — from the early models of 1945 up to ChatGPT — or not?”