Skip to content
HomeNewsDigestsConceptsGuidesToolbox
AboutSubscribeUA
Subscribe

AI Today Brief

The daily AI-engineering brief. Built in public. EN · UA.

XTelegramLinkedInYouTubeRSS

Follow AI Today Brief on LinkedIn for daily AI-engineering updates and the weekly “5 shifts that changed how developers work” PDF.

Explore

NewsDigestsConceptsGuides

Company

SubscribeAdvertiseAbout

Legal

Editorial policyAI disclosurePrivacyTerms

© 2026 AI Today Brief. All rights reserved.

  1. Home/
  2. News/
  3. Agents & MCP/
  4. Airport Manages Multiple Coding Agent Terminals Concurrently in Visual Studio Code
Agents & MCP

Airport Manages Multiple Coding Agent Terminals Concurrently in Visual Studio Code

Airport is an open-source Visual Studio Code extension built to orchestrate multiple concurrent AI coding agents like Claude Code, Codex, and Devin. It uses shell integration to track agent execution status and notify developers when manual intervention is required.

September 19, 2026· 6 min read
OKCurated by Oleksandr Kuzmenko, AI Product Engineer·Updated September 19, 2026·Sources cited on every story
AI-assisted · editor-reviewed·How we use AI
Airport Manages Multiple Coding Agent Terminals Concurrently in Visual Studio Code

Impact: Medium

Why it matters

You can monitor long-running background coding agents across multiple workspaces in a single window without constantly switching terminals to check if tasks are blocked.

TL;DR

  • 01Monitors agent terminal status without brittle log parsing by using VS Code shell integration.
  • 02Centralizes multi-workspace agent execution and file viewing inside a single editor window.
  • 03Enables side-by-side agent comparison via one-click terminal duplication.

Key facts

Supported Shells
bash, zsh, fish, pwsh, cmd
Integration Hook
VS Code Shell Integration API
Supported Agents
Claude Code, Codex, Devin, Antigravity

Terminal Status and Notification Integration

Airport embeds an orchestrator control panel directly into the Visual Studio Code sidebar. Rather than switching between multiple workspace windows or Electron wrappers, it integrates natively with built-in VS Code terminals. The extension leverages VS Code's shell integration API (bash, zsh, fish, pwsh, cmd) to inspect command execution states without parsing proprietary model logs. When an agent enters an interactive prompt or halts waiting for tool execution approval, a red status indicator alerts the developer immediately.

Multi-Workspace and Agent Comparison

Developers running parallel agents often lose track of which directory an assistant is modifying. Airport introduces a focused Files view that dynamically syncs with the currently selected terminal, displaying only the active directory context. Additionally, the extension provides two key terminal cloning actions:

  • Duplicate Terminal: Recreates the exact workspace terminal environment instantly.
  • Duplicate Terminal with Another AI Agent: Clones the terminal workspace state while launching an alternative agent (such as comparing Claude Code against Codex on the same refactor).

The extension supports one-click launching for Claude Code, Codex, Devin, and Antigravity, and includes session resumption to restore terminal configurations when re-opening workspaces.

Try it in 2 minutes

code --install-extension VignaeshRamA.airport

bash

✓ When to use

  • Running concurrent coding agents across multiple directories in Visual Studio Code.
  • Benchmarking agent workflows side-by-side using identical repository contexts.

✕ When NOT to use

  • Using terminals without VS Code shell integration support enabled.
  • Running standalone CLI workflows inside tmux or headless remote servers.

What to do today

  • →Install the Airport extension from the VS Code Marketplace.
  • →Verify that VS Code shell integration is enabled for your default terminal shell.
#Visual Studio Code#Claude Code#Codex#Devin#Antigravity#Airport

Sources

  • Airport Marketplace Extension
  • Airport GitHub Repository
  • Airport: Manage Multiple AI Agent Terminals Happily
ShareShare on XShare on LinkedIn
Next story →TypeSafe AI Launches Jev Probability Model for Fast Non-Hallucinating Agent Workflows

Related stories

  • Agents & MCPChatGPT Plugins Support Multi-Account Authentication with Model Context Protocol Profile Tools
  • Agents & MCPHardening Agent Sandboxes After Gemini Test Breakout Breaches External Systems
  • Agents & MCPMnemosyne Adds Local Memory Quickstart for Hermes Agent Workflows
  • Agents & MCPGoogle Labs Deploys CC Multi-User Agent Harness on Isolated Cloud Environments

Email digest

Get the morning AI brief

One email a day — the stories that matter for engineers, founders and tech leads. Human-edited, with links to primary sources.

  • ✓120+ sources scanned daily
  • ✓Edited by a human
  • ✓1 email per day
  • ✓EN + UA

By subscribing you agree to the privacy policy.