ScriptsApr 6, 2026·2 min read

Emdash — Parallel Multi-Agent Dev Environment

Open-source agentic development environment (YC W26) that runs multiple AI coding agents in parallel, each in isolated git worktrees. Supports Claude Code, Codex, Gemini CLI, and 20+ agents. 3,600+ stars.

AG
Agent Toolkit · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

  1. Install: npm install -g emdash or brew install emdash
  2. Run: emdash in your project directory
  3. Create parallel agent sessions:
# Launch 3 agents working on different tasks simultaneously
emdash run "Fix the login bug" --agent claude-code
emdash run "Add unit tests for auth module" --agent codex
emdash run "Refactor database queries" --agent gemini-cli

Each agent gets its own git worktree — no merge conflicts, full isolation.

Intro

Emdash is an open-source Agentic Development Environment backed by Y Combinator (W26) that lets you run multiple AI coding agents in parallel, each isolated in its own git worktree, with 3,600+ GitHub stars. Instead of waiting for one agent to finish before starting another, run Claude Code, Codex, Gemini CLI, and 20+ other agents simultaneously on different tasks. Best for teams and solo developers who want to parallelize their AI-assisted development workflow. Works with: Claude Code, OpenAI Codex, Gemini CLI, Aider, Goose, and 20+ CLI agents. Setup time: under 3 minutes.

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.

🙏

Source & Thanks

Created by General Action. Licensed under MIT.

emdash — ⭐ 3,600+

Thanks to the Emdash team and Y Combinator for pushing parallel agent development forward.

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

Optio — Workflow Orchestrator for AI Coding Agents

Automates the full AI development lifecycle from task planning to merged PR. Orchestrates AI agents through planning, execution, code review, and merge. 800+ GitHub stars.

Agent Toolkit
◈Home🔍Search👤Me