ATC: Air Traffic Control for AI Coding Sessions

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.