Emdash — Parallel Multi-Agent Dev Environment

Core Features

Git Worktree Isolation

Each agent session runs in its own git worktree — a lightweight, isolated copy of your repo. Agents can make changes freely without interfering with each other:

main/
├── .worktrees/
│   ├── fix-login-bug/     (Claude Code working here)
│   ├── add-auth-tests/    (Codex working here)
│   └── refactor-db/       (Gemini CLI working here)

Multi-Agent Dashboard

Visual dashboard showing all running agents, their progress, diffs, and status. Review and merge changes from any agent with one click.

Diff Review Across Agents

Compare changes from different agents side-by-side. Choose the best implementation or merge parts from multiple agents.

Task Management Integration

Connect to Linear, Jira, or GitHub Issues. Assign tickets directly to agents:

emdash assign LINEAR-123 --agent claude-code
emdash assign JIRA-456 --agent codex

Kanban View

Visual board showing tasks assigned to agents, in-progress work, and completed items ready for review.

Key Stats

• 3,600+ GitHub stars
• Y Combinator W26 backed
• 20+ supported CLI agents
• Git worktree isolation (zero conflicts)
• Linear, Jira, GitHub Issues integration

FAQ

Q: What is Emdash? A: Emdash is an open-source development environment that runs multiple AI coding agents in parallel, each isolated in its own git worktree, so they can work on different tasks simultaneously without conflicts.

Q: Is Emdash free? A: Yes, fully open-source under MIT license.

Q: Which AI agents does Emdash support? A: Claude Code, OpenAI Codex, Gemini CLI, Aider, Goose, and 20+ other CLI-based coding agents.