JetBrains Air - Run Codex, Claude Agents, Gemini CLI, and Junie side by side
by•
JetBrains Air is built for agent-driven development. It brings your favorite coding agents – Codex, Claude Agent, Gemini CLI, and Junie – into one coherent workflow designed for real codebases.
Air helps you define tasks precisely, run them in isolation, and review the results with full code intelligence – all in one place.
Download Air – free for macOS. Windows and Linux versions coming soon.
Replies
A recent thread [1] suggested running more coding agents in parallel. Products like @Axel and @Superset initiated the movement. This is @JetBrains' response. LFG
[1]: How many Claude Codes do you run in parallel?
Looks great so far. Would be cool if you could add a live comparison view between agents in future updates.
Confs.tech
@trevor_nicholas2 Hi, Trevor! Ekaterina from the Air team here. Thanks for the suggestion! Would you like to see how different agents perform on the same task? Or do you have something else in mind?
been a user of IntelliJ IDEA, Android Studio for ages hence this launch feels personal.
Congrats on the launch team!
@theanimeshs curious: what are your favorite JetBrains plugins?
@fmerian need to revisit and see, nowadays i'm coding more in ts, nextjs ecosystem
prominent ones I remember are SonarLint, Lombok etc (while building Java & Android apps)
& great thread bdw, got to know a lot more about what JetBrains is upto these days :)
Been juggling Claude Code and Codex on the same codebase and they keep stepping on each other's files. So the isolation part — does each agent get its own worktree, or is it more branch-per-task? Curious how the review works when two agents touch the same file.
Confs.tech
@alan_silverstreams hi, Alan! I'm Ekaterina from the Air team. Right now Air supports three ways of running agents: local (your main working copy with the active branch you have selected), git worktree (a new copy of your project sources with a new worktree-assigned branch created) and Docker (similar to worktree but since the workspace is inside the container, you can run multiple instances of your application without port conflicts). It depends where you run review by default it will review task-specific changes, but you can also run review slash command and specify what you want to review (all changes, specific file, commit, or branch).
Kona
I can't recommend this product, because I've tried to make it work and it just doesn't. Command execution didn't start (it got stuck in a scheduled state). I've tried to reach out to @JetBrains on X, but no reply. Eventually I found an issue in their issue tracker, started to wait for the resolution and guess what? The issue is gone now. I used to love JetBrains, I'm paying for WebStorm and JetBrains AI (Ultimate), but this is the last year I'm doing it, because the frustration from their products is immeasurable nowdays.
oh that's good feedback. what alternatives have you considered?
Kona
@fmerian I haven't tried many, to be honest, because Codex desktop works like a charm. The only downside is that there is no $100 plan, many people would love that!
As a middle-out option between Plus and Pro? makes sense.
You're spot on re: Codex. I really like the unified UI, better than running tabs in @Claude Code. On the other hand, being limited to @OpenAI 's models is a blocker to me.
Full disclosure: I'm currently enjoying using @Axel (open-source alternative).
Everything just flows seamlessly—no bumps, no confusion, just pure elegance
@katyaprigara frame this!
As a JetBrains subscriber for over a decade (grandfathered, still using WebStorm + AI Ultimate), I’m curious: what’s the one key improvement or use case in JetBrains Air that justifies switching from my current workflow, especially given the reported stability issues i'm seeing down below?
Good luck on the launch. Hope it smooths out quickly for longtime users like me
Confs.tech
@marcelino_gmx3c thanks! The review flow: you can see the whole file that was changed and not only the diff, you can leave comments to the agent right in the code, you can review the code with another agent. We don't see Air is not a replacement for an IDE (if you still use it), more like a companion that is build around agents like CLIs but has a more convenient UI.
@katyaprigara Thanks for that explanation.
Product Hunt
Been using JetBrains for years and their database tool window still feels like having a senior DBA sitting next to me - caught a production query that would've cost us $3k/day in unnecessary joins last week. The way they surface performance hints while you're writing SQL is almost unfair to other IDEs.
This is exactly the workflow we've been doing manually.
We're 3 people building Vidtreo — a video recording API (also launching on PH today). Our daily reality is running Claude agents across three repos simultaneously: backend on Cloudflare Workers, browser SDK with WebCodecs transcoding, and a React dashboard. The context switching between terminals and agents is brutal.
The idea of referencing a specific line or method when defining a task for an agent — that alone would save us hours. Right now we paste file paths and line numbers into prompts like cavemen.
Sandboxing agents in worktrees is the other killer feature. We've had agents step on each other's changes more times than I'd like to admit.
Really excited to try this with our stack. Multi-agent development isn't hypothetical anymore — teams are shipping production infrastructure this way today.