Ivan Kuleshov (@Merocle) | teapawt

Ivan Kuleshov retweeted

@jetbrainsOct 16

Junie Local now runs on @NVIDIARTXSpark from day one. Get a full-fledged coding agent on your PC. It reads your code, edits files, and runs tests. There are no tokens or quotas, and no code leaves the machine. Windows support is stable, too. All you need is a 24 GB Nvidia RTX card. Try it for free: junie.jetbrains.com/local

Image with a black background features text: "Your RTX Spark just got an agent. Junie Local runs on it from day one." The text is in white and green. The top corners display the logos for Junie and JetBrains. The bottom shows a green command line: "> /local".

ALT Image with a black background features text: "Your RTX Spark just got an agent. Junie Local runs on it from day one." The text is in white and green. The top corners display the logos for Junie and JetBrains. The bottom shows a green command line: "> /local".

6

78

7,810

Ivan Kuleshov retweeted

@kskryganOct 16

Today we have hit a new milestone for Junie Local. It can run on your RTX devices and Windows version is stable. 100% local. Zero costs. Available both though Air in IDEs / Junie CLI. More supported hardware and more powerful models coming soon!

2

84

3,530

Now, starting at 24 GB of VRAM on Windows junie.jetbrains.com/local

Junie by JetBrains

Junie by JetBrains. AI Coding Agent.

junie.jetbrains.com

3

937

They added a banana for scale 🤣

Roadster xitter.cf/i/broadcasts/1yKAPwNgg…

0:00

Tesla

Roadster

2

80

43,051

You asked about cooling. It's all serious, with redundancy

Temporary. 1Tb unified memory, 8x DGX Sparks with 200Gbit interconnection

2

43

2,983

Temporary. 1Tb unified memory, 8x DGX Sparks with 200Gbit interconnection

78

1,010

52,332

The remaining credits on AI Diablo style

1

15

1,927

Free Junie Lite, interesting

We've reimagined JetBrains IDEs to become the ultimate agentic workbench. Air is an open hub for agents inside your IDE: -Any agents to run (Claude, Codex & many more) -Agents are more efficient with IDE intelligence -Free Junie Lite agent bundled -Cloud runs via Air Teams ⬇️

12

1,778

Ivan Kuleshov retweeted

The first merch @SidePulse Pro’s with the JetBrains Junie logo. An AI Agent status indicator for the SD Card slot. We’ll share which conference to get them at.

In collaboration with @pkuhar

1

15

1,326

In collaboration with @pkuhar

8

257

31,238

link to the original product sidepulse.io/sidepulse.html

SidePulse Pro — 8 RGB LEDs for your MacBook Pro SD slot

SidePulse Pro tucks into the unused SD card slot of a MacBook Pro. 8 RGB LEDs show AI agent status, builds, battery and more — controlled by writing a file.

1

11

1,823

A colleague at JetBrains built a cool model based on Qwen 3.6 and 3.8 27B Essentially, he combined the two models and ended up with a model that performs better than 3.6 and is significantly faster than 3.8 when run locally. I ran this model all last week, and it performs very well in real-world scenarios. The model is available for free on HuggingFace huggingface.co/collections/J…

3

95

8,038

Ivan Kuleshov retweeted

@kskryganSep 22

Today we introduce JetBrains Air - the product system for software development orgs in the age of agents. Built for developers, team leads & engineering directors. Open and flexible: steer and control almost any LLM & harness. Read more: jb.gg/air-announce

JetBrains Air: Building a System of Products for Agentic Software Development - The JetBrains Blog

AI can produce code. Organizations still have to produce software. Agentic development is changing how software gets made, but it hasn’t changed what it costs to be wrong. Six months ago, we began

blog.jetbrains.com

78

465

254,486

Ivan Kuleshov retweeted

@jetbrainsSep 18

Junie has a new home on X: @junie_ai 👋 Follow for new features and announcements. First up: a smarter Junie Local, a new blended model, and experimental Windows support. The team has the details below 👇

@junie_aiSep 18

We mixed Qwen 3.8 and 3.6. Literally. A 50/50 weight merge. One 27B model. 71% fewer output tokens than 3.8 in our internal coding eval. Junie Local has an update. Windows devs, you're invited too 🤝

4

93

24,804

Technical details blog.jetbrains.com/junie/202…

There's a lot of work behind this. And the results are really great, especially for running it on hardware that isn't the fastest

5

1,677

There's a lot of work behind this. And the results are really great, especially for running it on hardware that isn't the fastest

@junie_aiSep 18

We mixed Qwen 3.8 and 3.6. Literally. A 50/50 weight merge. One 27B model. 71% fewer output tokens than 3.8 in our internal coding eval. Junie Local has an update. Windows devs, you're invited too 🤝

1

10

3,203

Ivan Kuleshov retweeted

@kskryganAug 24

JetBrains takes its first step toward Local AI. MacBook M5 users can set up Junie Local in one click and get a solid agentic experience. Unlimited & Fully local. Folks also had some fun presenting it on a plane :) Check it out & stay tuned for more: junie.jetbrains.com/local

@jetbrainsAug 24

Junie can now run entirely on your machine, and it’s completely free to use. One command: /local. We picked and optimized the whole stack around the model: agent harness, model parameters, and inference engine. No tokens, no quota, no code ever leaving your machine.

20

414

65,955

A project we've been working on lately. I mentioned it before under the name "Junie Cage" 😁 blog.jetbrains.com/junie/202…

Junie Local: Run the AI Coding Agent on Your Mac | JetBrains

Junie Local runs the full AI coding agent on your M5 Mac. One command, no configuration, no tokens. Your code never leaves your machine. Completely Free.

blog.jetbrains.com

15

1,644

Set up the entire environment to launch and use a local model with a single command directly from the agent. The hardware options are currently very limited, but the list will expand in the coming weeks. We are testing various configurations right now

@jetbrainsAug 24

Junie can now run entirely on your machine, and it’s completely free to use. One command: /local. We picked and optimized the whole stack around the model: agent harness, model parameters, and inference engine. No tokens, no quota, no code ever leaving your machine.

10

1,795