On a mission to make software development a more productive and enjoyable experience. Make it happen. With Code.
- Tweets 14,929
- Following 56
- Followers 215,202
- Likes 7,940
Pinned Tweet
More than just a product, JetBrains Air marks a new chapter for us: an open system connecting developers, agents, teams, and organizations.
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
8
12
101
17,540
Running multiple agents in parallel? Want the freedom to choose your agent?
Try JetBrains Air in your IDE – now in Early Access.
Get started for free*, with Junie Lite configuration.
*𝘛𝘦𝘳𝘮𝘴 𝘢𝘯𝘥 𝘤𝘰𝘯𝘥𝘪𝘵𝘪𝘰𝘯𝘴 𝘢𝘱𝘱𝘭𝘺
10
7
59
10,383
Start here: jb.gg/air-in-ide
1
4
1,884
The JetBrains Air in IDEs is here. Run your agents of choice in parallel and review their changes with JetBrains’ code intelligence, all in the IDE you already use.
Check below why this is the next step for JetBrains Air. 👇
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
⬇️
8
7
87
14,271
Yes, we use Air Teams to review pull requests for Air Teams.
Code review is one of the Air Teams automations we use most internally.
Ours reviews every push, tracks which findings you fixed, and collapses old comments so you only see the latest.
Oh, and you can argue with it too. Explain why a fix can wait, and it accepts that.
1
26
7,942
GPT-6.1 Sol is out!
Our colleague @kristel_tech asked GPT-6 Sol and GPT-6.1 Sol to "Build a cinematic, photorealistic rocket launch scene using Three.js"
GPT-6.1 Sol: $0.553 | 17 mins
GPT-6 Sol: $1.01 | 22 mins
Try it in JetBrains Air or Junie.
@OpenAIDevs
24
27
477
64,203
This animation was generated entirely by Claude Sonnet 5.5!
Our colleague @kristel_tech asked for “a girl growing up, one house, one camera move.” The outcome: The Journey of Life, all drawn in code as a riso print.
Try it in JetBrains Air today.
5
3
39
7,702
We gave GPT 6-Sol a prompt. It gave us a katana and a getaway mission. ⚔️
@mhartington built Neon Exit with @OpenAIDevs’ latest GPT model.
Hit the neon streets. Start a sword fight. Grab the briefcase. Get out.
Available in JetBrains, Air and Junie starting today.
2
5
35
8,129
This product video was generated entirely by Claude Opus 5.5.
Our colleague @kristel_tech gave it @HeyGen’s HyperFrames skills and pointed it at kotlinlang.org – out came this Kotlin promo.
Try it in JetBrains Air or Junie.
1
11
187
18,042
Great software is built by people who care enough to challenge the work,
not just ship it. Hear our CEO Kirill Skrygan explain why.
1
3
39
7,488
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 👇
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
6
95
24,692
Writing code faster than you can ship it?
That probably means the bottleneck has moved further down the road.
Align AI with your review and testing pipelines so the whole workflow runs smoothly.
4
2
29
6,645
The tests are green. Now you want to see the feature work.
Let Junie do the clicking 🖱
Meet Junie Agentic QA, available through /demo in Junie CLI. Describe the flow you want to check, and Junie launches your app in an isolated environment, interacts with its UI, and records what happens.
Watch the run live, then review the video, screenshots, and HTML report. See what worked, what failed, and what needs a closer look.
Learn more about it here ➡ bit.ly/4hznWs0
3
2
20
6,643
What does it take to build a production-grade RAG pipeline for semantic code search? In part 1 of our JetBrains Context developer diary, we share what we learned about structure-aware chunking and vectorization, and why more dimensions beat higher precision.
Read more: bit.ly/46yEPNh
4
2
26
7,859
We’re running our annual Kotlin Developer Survey and would love to hear from you.
How’s Kotlin treating you lately? Help us improve the language, tools, and overall developer experience by sharing your feedback.
It takes about 15 minutes:
jb.gg/4q4o7u
Looking forward to your insights! ☕
2
2
13
7,823