emdash: a desktop orchestrator for running multiple AI coding agents in parallel using isolated Git worktrees

What it solves

Emdash solves the friction of managing multiple AI coding agents simultaneously. Instead of juggling multiple terminal windows and manually managing branches, it provides a unified desktop interface to run agents in parallel, each isolated in its own environment.

How it works

The app acts as an orchestrator for existing CLI-based AI agents (such as Claude Code, Gemini, and OpenCode). It leverages Git worktrees to ensure every task runs in its own isolated branch and directory, preventing agents from interfering with each other. It also integrates with project management tools like GitHub, Jira, and Linear to feed tickets directly into agents and provides a centralized place to review diffs and merge changes.

Who it’s for

Developers who use AI coding agents and want to manage multiple concurrent tasks, explore different implementation paths for the same feature, or run agents on remote machines via SSH.

Highlights

• Parallel Agent Execution: Run multiple agents at once without terminal clutter.
• Git Worktree Isolation: Every agent task is kept in its own isolated worktree and branch.
• Integration Ecosystem: Direct imports from Linear, GitHub, Jira, GitLab, and other ticket systems.
• Remote Support: Ability to run workflows on remote machines using SSH/SFTP.
• Local-First Privacy: App state is stored locally in SQLite, and code is not sent to Emdash servers.