What is Air and what does it do?

Air is an agentic development environment built by JetBrains. It allows developers to delegate coding tasks to multiple AI agents (specifically Codex, Claude Agent, Gemini CLI, and Junie) and run them concurrently. Air provides a coherent workflow for real codebases, helping you define tasks precisely using code-aware context, run them in isolated environments, and review results with integrated code intelligence—all within a single application.

How is Air different from using AI agents in a CLI or chat?

While most agent tools focus primarily on the AI model itself, Air focuses on the development workflow around it. Instead of juggling multiple terminals, manually pasting file paths, and reviewing raw diffs, Air provides a structured environment with code-aware task definition (using symbols, classes, methods, commits), isolated execution via Docker or Git worktrees, context-aware review throughout your project, and dedicated workspaces to manage concurrent tasks seamlessly.

Which AI agents are currently supported in Air?

According to the provided information, Air currently supports four AI agents: Claude Agent (from Anthropic), Codex (from OpenAI), Gemini CLI (from Google), and Junie (from JetBrains). You can use these agents individually or compare their outputs side-by-side.

Can I use my existing JetBrains AI subscription with Air?

Yes, you can use your JetBrains AI subscription with Air under specific conditions. If you have a JetBrains AI Pro or Ultimate subscription, you can sign in and use all supported agents at no additional cost. However, JetBrains AI Free and JetBrains AI Enterprise subscriptions are not supported, and trials cannot be activated from within Air.

What is the BYOK (Bring Your Own Key) option in Air?

Air offers a BYOK (Bring Your Own Key) model as an alternative to using a JetBrains AI subscription. This allows you to connect your own API keys directly from providers like Anthropic, OpenAI, or Google. When using BYOK, you pay those providers at their standard rates. You can also bring your own subscription for Codex and Gemini. Air allows using both methods simultaneously, with BYOK taking priority when configured.

What are Workspaces in Air?

Workspaces are a core concept in Air that keep agent sessions, Git state, navigation, and tools scoped to a single project. They enable you to run multiple tasks concurrently, preserve session history, avoid branch collisions between different agent tasks, and manage complex AI-powered workflows without having to juggle multiple application windows or terminal instances.

Is Air a replacement for my JetBrains IDE (like IntelliJ IDEA)?

No, Air is not a replacement for traditional JetBrains IDEs. It is a standalone desktop application specifically designed for orchestrating agent-powered development workflows. Its focus is on task definition, multi-agent execution, and result review. Your primary IDE continues to handle the rest of the standard development work. Air is meant to complement, not replace, your existing development tools.

What operating systems does Air support?

Based on the webpage, Air is currently available for download for macOS. The page also states that preview versions for Windows and Linux are coming soon.

Does Air support cloud-based execution for agents?

According to the 'what's coming' section on the webpage, cloud-based execution is a planned future feature. The intent is to allow users to run agents in the cloud without local setup, scale effortlessly, start and review tasks from a browser, and access cloud agents directly from within a JetBrains IDE.

Air by JetBrains - Multi-Agent AI Coding Environment & Workflow

Air Overview

Air is a specialized desktop application developed by JetBrains, designed as an agentic development environment for managing AI-assisted coding workflows. Unlike single-agent chat interfaces, Air orchestrates multiple AI coding agents to work concurrently on different tasks within a single project. It integrates leading AI agents including Claude Agent, Codex, Gemini CLI, and Junie, allowing developers to match the right tool to each job. Air provides structured workflows for defining tasks with precise code context, running agents in isolated environments to prevent conflicts, and reviewing changes with full code intelligence.

How to use Air

Air operates as a standalone desktop application, primarily for macOS with previews for Windows and Linux coming soon. To use Air, developers first define a coding task by exploring their project and gathering context through references to files, commits, symbols, or images. They then select and launch one or more supported AI agents (Codex, Claude Agent, Gemini CLI, or Junie) to execute the task. Air handles the setup using isolated execution methods like Docker containers or Git worktrees to run tasks in parallel without interference. Users can monitor all active agent progress from a central overview, quickly switch context to provide additional input, and finally review, accept/reject changes, and commit the results back to their local project.

Core Features of Air

Concurrent Multi-Agent Execution: Run multiple AI coding agents (Claude Agent, Codex, Gemini CLI, Junie) side-by-side on different tasks without conflicts.
Isolated Task Environments: Automatically sets up isolated execution using Docker, Git worktrees, or (coming soon) cloud environments for each agent task.
Code-Aware Task Definition: Define tasks with precise context by referencing specific files, code symbols, commits, or images from the project.
Centralized Progress Oversight: Get an overview of all agents' progress on async tasks, enabling easy monitoring and course correction.
Integrated Review Workflow: Review agent-generated changes at the file level, accept or reject code comments, and prepare changes for commit within Air.
Agent-Agnostic Flexibility: Switch between or compare outputs from different AI agents (Claude, OpenAI, Google, JetBrains) for the same task.
Workspace Management: Use workspaces to scope agent sessions, Git state, and tools to a single project, preserving history and avoiding branch collisions.

Use Cases for Air

Air is designed for software developers and teams engaged in AI-augmented coding. Key use cases include: rapidly prototyping or building features in unfamiliar languages or frameworks by delegating to specialized agents; breaking down large development tasks into smaller sub-tasks executed concurrently by different agents; experimenting with and comparing outputs from multiple AI coding models (Claude, GPT, Gemini) on the same problem; and maintaining oversight and control when automating repetitive coding or refactoring workflows with AI assistance.

Advantages of Air

Air's primary advantage is shifting focus from managing individual AI models to orchestrating a complete, controlled development workflow. It increases velocity by enabling true parallel task execution rather than sequential agent use. It provides better delegation by allowing developers to break work apart and assign the most suitable agent to each sub-task. Enhanced oversight and visibility let developers monitor progress and intervene when needed without losing context. Finally, its integrated, code-intelligent review process improves the quality and integration of AI-generated code into the main project.

Air FAQ

Air Comments (0)

Sign in to comment.

Sign in

No comments yet.

Traffic

Latest traffic

Monthly visits226.8K

Avg visit duration0:20

Pages per visit1.40

Bounce rate53.2%

Status

Rising+1.7%vs previous month

Updated at 2026-06-15

Monthly traffic trend

Geography

Top 5 countries / regions

🇺🇸United States
26.1%
🇨🇳China
23.0%
🇩🇪Germany
19.6%
🇮🇳India
17.1%
🇰🇷South Korea
14.2%

Traffic sources

Source type	Percentage
Direct	70.3%
Referral	24.6%
Email	5.0%

Total

100%

Direct70.3%

Referral24.6%

Email5.0%

Top keywords

Keyword	Cost per click
antigravity ide	$1.80
claude code	$2.93
codex	$4.45
codex cli	$7.74
jetbrains air	$6.02

Air Videos on YouTube