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
How does Air handle agent conflicts or differing outputs when running multiple agents like Codex vs. Claude on the same codebase task? Any built-in diff tools or voting mechanisms to streamline reviews?
Confs.tech
@swati_paliwal hi, I'm Ekaterina from the Air team. For running multiple tasks at the same time Air supports using git worktrees or Docker containers to isolate agents from each other. At the end of the task, you'll be able to review the results, providing agent the feedback, before you bring changes back to the local copy (at this stage you might need to resolve the merge conflicts if main has been updated).
Air shows changes in a diff view. To streamline the review flow, there's a built-in agentic review flow where another agents checks the code (either all changes or specific files only via /review command in chat) and leaves comments. You can also provide agent's comments right in the code, like in a regular code review.
LiveDemo
Great,
I am a fan of all JetBrains products,
I hope this fixes the problem of using different AI models inside JetBrains
Having multiple AI agents in one coherent workflow is the right direction. I've been using Claude Code as my primary dev tool and the biggest friction is switching contexts when you need a different model's strengths. Being able to run them side by side and compare outputs on the same codebase solves a real problem. Curious how it handles conflicts when two agents suggest different approaches to the same task.
MacQuit
Really cool to see JetBrains tackling the multi-agent workflow problem. As a Mac developer, I've been running Claude Code heavily for my projects and the biggest friction is exactly what you described — context switching between agents and terminals. Being able to define tasks precisely and run them in isolation is key. Curious about the review experience: does Air give you a unified diff view across all agents, or do you review each agent's output separately? Also, any plans for Linux support timeline? Love that it's free — will definitely give it a spin.
Confs.tech
@lzhgus hi! I'm from the Air team. Thanks for your feedback! In Air you work with tasks (and one task is one agent's session) and then you review the task's results as a diff. For tasks we provide a different level of isolation - task/agent is fully isolated if you're using git worktree or Docker container and you will review only the results of this task before bringing changes to the main copy (in this case merge conflicts can occure). If several tasks are running in a local copy, we try to show changes groupped per task if possible.
Linux version is planned for Q2, please stay tuned.