Junie

While other coding agents are busy turning tokens into invoices, Junie focuses on getting the job done.
AI coding agent by @jetbrains

[Junie @junie_ai]

3/3 Available in @getsome_air in IDEs and Junie CLI 26.10.20+.

Eco is on by default for supported model-and-effort configurations. You can turn it off in the model picker.

How it works, benchmarks, and supported IDE versions: https://t.co/ZJvwoU2qCQ

[Junie @junie_ai]

1/3 Not every coding step needs your most expensive model.

Meet Junie Eco Mode: your chosen model investigates and plans, then a lower-cost model handles implementation and testing. 🧵

[Junie @junie_ai]

2/3 In two internal benchmarks, Eco cut average model cost per task by 48% and 57%.

Average resolve rates changed by less than 1 percentage point.

The builder gets the full conversation and a structured plan: what to change, how to test it, and what to watch out for.

[Junie @junie_ai]

Hi! Thanks for asking 🙂 The connection respects your Figma permissions, so it can only access designs you can already open. When Junie works with a design, relevant details may be sent to the AI model to help generate code. Privacy depends on your Figma permissions, what’s shared, and your AI/data-sharing settings - not just your JetBrains or Figma license.

[Junie @junie_ai]

@zoink 😊

[Stanislav Erokhin @erokhins]

It was a fun experience to play with RTX Spark laptops! They are more powerful than the M5 Max in terms of compute, but memory speed is a bit slower.

[Vladimir Sotnikov @Vvsotnikov]

I’m already working on more optimizations and custom models for @NVIDIARTXSpark

Local inference is so fun and full of ideas to be implemented

[Junie @junie_ai]

Gemini 4 Argon has landed in Junie CLI and @getsome_air 😎

[Junie @junie_ai]

@jetbrains @NVIDIARTXSpark 🙏

[Junie @junie_ai]

Your GPU. Your code. No token bill.

Junie Local runs on NVIDIA RTX Spark from day one. Windows support is stable, too.

Reads code. Edits files. Runs tests. All locally.

Try it free → https://t.co/whHL3D11he

[Vladimir Sotnikov @Vvsotnikov]

Thank you @NVIDIAAI for giving us the opportunity to bring day-one support for @junie_ai Local on @NVIDIARTXSpark!

What I personally like the most about RTX Spark is that provides enough memory to run BOTH local AI experiments and local coding agents at the same time, all using the same CUDA stack that I use in prod

Here’s a screenshot of me asking Junie Local to run an SLM pretrain experiment - both are running on the same RTX Spark!

[Junie @junie_ai]

@figma 🤗

[JetBrains @jetbrains]

Try agentic coding with JetBrains Air and Junie Lite for free in PyCharm 2026.3 EAP 4 👇

[Figma @figma]

Announcing 20 new MCP partners at Config India (!!)

Amp, ClickUp, Dia, Junie by JetBrains, Linear, Meta Muse, Mistral, Notion, OpenCode, Sarvam Agents, Agentforce Vibes, Amazon Quick, Amplitude Wave, Cline, Delta, Dust, Glass, Gradial, Writer, Zed, Microsoft 365 Copilot

[Junie @junie_ai]

👀

[Junie @junie_ai]

Haiku 5.5 is now in Junie 😎

[JetBrains Air @getsome_air]

How to use @junie_ai in Air at no charge:

1. Install the Air plugin for your IDE
2. Choose the Lite model for Junie
3. Have fun

[Junie @junie_ai]

Your backlog just got a free coding agent.

Meet Junie Lite, powered by Qwen 3.6 27B in the cloud.

Now in the CLI and JetBrains IDEs via Air. Free for now with your JetBrains Account.

https://t.co/YEzAWFcN9h

[Junie @junie_ai]

@mandraketech @v1becoder @jetbrains Junie Lite is using Qwen 3.6-27B under the hood

[Nick Frolov @v1becoder]

Big Day for @jetbrains IDEs and for @junie_ai .
A completely new agentic experience is open today in our IDEs - we call it JetBrains Air. And the best part - Junie provides free baseline intelligence tier - Junie Lite.

In JetBrains Air you have a professional control plane over your agents (plug-in any agent you already love), agents work in parallel, you can link sessions with each other, delegate inline comments from code or md files to agents and many more.

Read the details here: https://t.co/c8p3HLuYnM