Why it matters
This tool offers developers a centralized view of their AI development workflow, consolidating disparate tools like AI coding environments, version control, and task management. By visualizing the connections between sessions, worktrees, and tickets, ATC aims to reduce context switching and improve productivity for AI builders.

What changed

The chaehy5665/atc project introduces a local web application that functions as an "air traffic control" system for AI coding sessions. This tool aims to consolidate and visualize various aspects of a developer's workflow, including AI coding sessions (specifically mentioning Claude Code and Codex), git worktrees, and Linear tickets, all presented on a single radar screen. The application runs locally, accessible via http://localhost:7700 after installation and build, and is developed in TypeScript. It operates in a read-only mode by default, ensuring it does not alter worktrees or write to Linear.

Key features include:

  • RADAR Screen (#radar): Displays sessions, worktrees, and tickets in a three-column format, highlighting worktrees without owners and in-progress tickets lacking associated worktrees.
  • FLIGHT STRIPS Screen (#strips): Provides a card-based view for each session (e.g., ALPHA, Codex), detailing its state, associated worktrees, and linked tickets.
  • FIDS Screen (#board): Presents ticket cards organized by Linear state columns, each with a badge indicating the team responsible.
  • Metrics Screen (#metrics): Offers operating metrics, readiness checks, and trend data.
  • AIRPORT Screen (#airports): Manages a registry of repositories, allowing for opening, renaming, closing, and deleting "AIRPORTs" (repositories).
  • FLEET Screen (#fleet): Lists "AIRCRAFT" (teams) with their status, current flights, crew details, type ratings, and route information.
  • NETWORK Screen (#network): Visualizes project milestones (Linear tickets) on a route map, showing active flights and progress.
  • DISPATCH Screen (#dispatch): Shows the current plan and proposal cards with OCC notes and verdicts.
  • SCHEDULE Screen (#schedule): Displays OCC SCHEDULE drafts and candidate counts.
  • DOCS Screen (#docs): Provides documentation on how to use ATC.

The application uses aviation-themed terminology for its interface, such as Session mapped to AIRCRAFT, Workspace to STAND, and Ticket to FLIGHT NUMBER. It requires Node.js 24 or later, Claude Code or Codex, and a git worktree repository. For Linear ticket integration, a LINEAR_API_KEY is needed.

Why it matters for builders

ATC addresses the challenge of managing complex AI development workflows by providing a unified dashboard. Developers often juggle multiple tools for coding, version control, and task tracking, leading to fragmented visibility and potential inefficiencies. By centralizing these elements, ATC allows builders to see the relationships between their AI sessions, codebases, and project tasks at a glance. This improved oversight can help in identifying bottlenecks, understanding project status, and coordinating efforts more effectively.

Practical impact

Developers working with AI coding assistants like Claude Code or Codex, alongside git for version control and Linear for task management, can benefit from installing and running ATC. The setup involves installing Node.js, cloning the repository, and running npm install followed by npm start. For those using Linear, configuring the LINEAR_API_KEY in .env.local is necessary to enable ticket integration. Builders can explore the various screens like RADAR, FLIGHT STRIPS, and FIDS to visualize their current projects. The AIRPORT and FLEET screens offer management capabilities for repositories and teams, respectively. Experimenting with the different views can help developers identify which aspects of their workflow are most effectively represented and managed through ATC.

Caveats and source limits

This project is described as a "fresh release" with version v0.1.0 and has 0 stars and 0 forks on GitHub, indicating it is very early in its development lifecycle. The source does not provide independent benchmark results for performance or scalability. Information regarding pricing, specific supported AI models beyond Claude Code and Codex, or detailed integration capabilities with other AI platforms is not available. The project's maturity and long-term support are also not detailed in the provided excerpts. The documentation is extensive but uses a specific aviation metaphor which may require some learning curve for new users.

Sources

Written with AI assistance from the linked sources; every claim below was checked against them automatically. How we produce articles.

Claim check: 7/7 supported claims - 7 evidence links - 100% avg confidence
  • ATC is a local web application that provides an "air traffic control" interface for AI coding sessions.supported - github.com
  • ATC integrates Claude Code and Codex sessions, git worktrees, and Linear tickets into a single dashboard.supported - github.com
  • The application runs locally on port 7700 and is accessible via a web browser.supported - github.com
  • ATC operates in a read-only mode by default, not creating or deleting worktrees, and not writing to Linear.supported - github.com
  • The project is developed in TypeScript.supported - github.com
  • The latest release is v0.1.0.supported - github.com
  • ATC requires Node 24 or later, Claude Code or Codex, and a git worktree repository.supported - github.com

Caveats

  • Single-source caution: verify critical details at the linked source.
Radar score 84/100 - how it was calculated
Reliability82
Freshness92
Novelty77
Technical66
Developer96
Ecosystem72
Confidence100
  • Reliability 82: GitHub metadata supports source trust
  • Freshness 92: Fresh GitHub activity
  • Novelty 77: Fresh GitHub release
  • Technical 66: Repository technical metadata
  • Developer 96: Developer tooling signals
  • Ecosystem 72: Fresh GitHub release
  • Confidence 100: Claims have reliable evidence
Share
XLinkedInHacker News

Discussion

Loading comments...

Related articles

Agents - Nov 16, 2026aisync: Context Management for AI Coding Agentsaisync is a new local hub designed to manage context and coordinate multiple AI coding agents. It offers features like shared rules, a hash-chained journal for verification, file claims to prevent conflicts, and mid-session updates for agents like Claude Code, Codex, and Cursor.Agents - Nov 14, 2026Lich v0.90.0: Multi-Agent IDE with Worktrees and Browser ControlLich has released version 0.90.0, a multi-agent IDE that allows multiple AI agents to work concurrently on separate branches within a single window. The tool supports agents like Claude Code and Codex, managing their tasks in individual worktrees and offering features like inline code review and browser-driven agent interaction.Agents - Nov 16, 2026Node9 Proxy Adds Access Control for AI AgentsNode9 Proxy has released version 2.61.1, introducing enhanced access control for AI agents. This tool allows developers to define permissions for agents interacting with tools like Claude Code, Codex, and Gemini, and provides auditing capabilities.Agents - Nov 18, 2026TonyDzi/agent-sessions: Dataset of Real AI Agent ConversationsThe TonyDzi/agent-sessions dataset on Hugging Face offers a collection of real-world AI agent conversations, including interactions with Claude Code, ChatGPT, and Codex. It captures actual work sessions, including agent failures and repairs, rather than curated benchmark results.Agents - Nov 14, 2026Intent CLI: Semantic Git for AI Coding SessionsIntent CLI introduces a semantic history layer for AI coding agents, storing project goals, verified checkpoints, and decisions in plain JSON. This aims to help agents retain context across sessions, preventing the need for repeated explanations.AI Coding - Nov 20, 2026iPhone CLI: AI Agents Control Real iPhones via Accessibility TreeThe iphone-cli tool allows AI agents to interact with real iPhones using the accessibility tree, bypassing the need for Xcode, WebDriverAgent, or on-device app installations. This Rust-based CLI tool supports iOS 27+ and operates directly from the terminal on macOS and Windows.