Emdash

Emdash

A free, open-source desktop app for running multiple AI coding agents (Claude Code, Codex, and more) in parallel, each in its own isolated Git worktree, so you can compare approaches and merge what actually works.

🔗 Visit Emdash
📁 Editors, IDEs & Dev Tools🗣️ English📅 July 29, 2026

Description

Running one AI coding agent at a time means waiting for it to finish before trying a different approach to the same problem — and if the agent goes down a bad path, you've lost the time either way. Emdash runs several coding agents at once, each working in its own isolated Git worktree, so different fixes or features can be explored in parallel without one attempt blocking another or agents stepping on each other's changes.

It works with the CLI coding agents developers already use — Claude Code, Codex, OpenCode, Amp, and others — rather than locking users into a single provider, and supports both local projects and remote machines over SSH. Issues and tickets from Linear, GitHub, Jira, GitLab, Asana, and several other trackers can be sent directly into an agent to work on. It's free and fully open-source (YC W26), with optional Cloud and Enterprise tiers priced on request for teams that want managed infrastructure instead of running it themselves.

💬 Our review

The short version: Emdash's core mechanic — parallel agents in isolated Git worktrees — solves a real problem with today's coding agents: trying multiple approaches to the same task without one attempt interfering with another or having to babysit them sequentially.

Being free and open-source with no provider lock-in (works with Claude Code, Codex, OpenCode, Amp, and more) is a genuine advantage over agent tools tied to a single vendor's ecosystem, and the ticket-tracker integrations (Linear, GitHub, Jira, and others) mean work can flow in from where a team already tracks it rather than requiring a separate task list. The tradeoff is that running several coding agents in parallel means paying for API usage across all of them simultaneously, which the tool itself doesn't control — the cost scales with how many agents you run at once, not with Emdash's own (free) price tag.

💰 Pricing

Open-source gratuit + Cloud/Enterprise sur devisGratuit (self-hosted), Cloud/Enterprise sur demande

📊 Global score

53Average
🌐Availability15/100Faible

1 language · 0 platform

📄Profile90/100Excellent

Profile completeness

🤖 AI-enriched data

💰 Pricing model
🆓 Open-source gratuit + Cloud/Enterprise sur devis

Gratuit et open-source (self-hosted) ; Cloud et Enterprise sur demande pour infrastructure managée.

👥 Target audienceDéveloppeurs utilisant des agents de codage IA (Claude Code, Codex, Cursor) cherchant une gestion centralisée et l'exécution parallèle sans blocage de fournisseur
🗣️ Languagesen
🌍 Target countriesInternational
👍

Pros

Exécute plusieurs agents en parallèle dans des worktrees Git isolés

Agnostique au fournisseur d'agent (Claude Code, Codex, OpenCode, Amp)

Support SSH pour machines distantes en plus des projets locaux

Gratuit et open-source, intégrations trackers (Linear, GitHub, Jira)

👎

Cons

Coût d'utilisation API des agents non maîtrisé par l'outil lui-même

Nécessite de gérer plusieurs agents en parallèle, plus complexe qu'un seul agent séquentiel

Tiers Cloud/Enterprise sur devis uniquement, pas de tarif public

❓ Frequently asked questions

What is Emdash in one sentence?
How much does it cost?
Which coding agents does it support?
Can it work with remote servers, not just local projects?
Who is Emdash built for?
Is it worth the money compared to alternatives?
Which tool should you pick for your case?