I built a VS Code extension to work with several agents

Описание и применение

Stack — расширение VS Code, позволяющее одновременно работать с несколькими агентами, сохраняя навигацию, отладку и обзор кода в привычной среде.

Задача

Agents write code, but the developer needs to read, navigate, debug, and review it within the familiar VS Code environment.

Результат

Stack enables parallel agent work while keeping all code interaction within VS Code, improving navigation, debugging, and review workflows.

Рабочий процесс

• Create a new task in Stack, which creates a branch and worktree, prepares the environment, and launches the agent.
• Read and navigate code in VS Code; agent requests appear in the sidebar.
• Review diffs in the editor, comment, and send back to the agent.
• Debug problematic code directly in the editor.
• Use the MCP server to set up tasks via the Claude Code panel with /stack-task and Jira MCP.

Доказательства

I tried several tools for running agents in parallel and none fully convinced me.

Источник

Superset: on my machine it ate the memory.

Источник

Warp: a very good terminal, but for reading and moving around the code and the documents it fell short for me.

Источник

They are good tools. They just didn't fit the way I work: I always ended up going back to VS Code to read what the agents had written.

Источник

Stack creates the branch and the worktree, prepares the environment and launches the agent.

Источник

Each worktree opens as a folder in the editor. Search and Quick Open are limited to the worktree I'm in, so the work of five agents doesn't get mixed in the results.

Источник

Each worktree has its own debug port and its own launch.json, so I can stop at a breakpoint in one task while another keeps running.

Источник

It works on macOS and Linux. It needs tmux. On Windows, only with WSL. Native notifications are macOS only.

Источник