Inter-office memo
- To
- Everyone choosing an app to run coding agents
- From
- Mo, Chief Executive
- Date
- November 16, 2026, 7:42 PM CST
- Re
- Emdash alternatives
Emdash alternatives in 2026: 8 apps for running coding agents in parallel
Emdash Classic still works and still gets fixes, so you don’t have to leave, but new development has moved to Emdash 2.0, which has no published price. Orca is the closest match, with GitHub and Linear tasks and SSH hosts, free; T3 Code, Paseo and Herdr are free too; Paradev adds Linear and cloud workspaces for teams on Macs; Enjoy runs every lab’s agent through usage limits.
Disclosure: Enjoy is our product. We checked every app below against its maker’s own pages on November 16, 2026, and we say where another app is the better pick, Emdash included.
Emdash alternatives compared
Emdash, from General Action, a company in Y Combinator’s W26 batch, is a free, open-source desktop app that runs coding agents side by side, each in its own Git worktree. On November 5, 2026, its makers wrote that “The current desktop app is now called Emdash Classic,” and that they’re building Emdash 2.0, “coding agents for your whole team.” Classic keeps working, so these are the apps to weigh if you’d rather move now.
| App | Best for | Price, checked November 16, 2026 | Runs on | Agents |
|---|---|---|---|---|
| Emdash Classic | Issues from your trackers, free and open source | Free | Mac, Windows, Linux | 35 in its docs |
| Orca | The closest match: tasks, SSH hosts and the most agents, free | Free | Mac, Windows, Linux | 40 in its docs, and any command-line agent |
| T3 Code | A simpler, free control plane | Free | Mac, Windows, Linux | Claude Code, Codex, Cursor, OpenCode, Grok Build, Antigravity, Kiro, Pi, Muse Code, and ACP agents |
| Paseo | Agents on several machines, with a full phone app | Free; hosted Hub from $0, Pro $15 a seat a month | Mac, Windows, Linux | Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity, Muse Code |
| Herdr | Agents in real terminals, across machines | Free | Mac (Apple silicon), Windows, Linux | Anything that runs in a terminal |
| Paradev, formerly Superset | Teams on Macs, with Linear and cloud workspaces | Free for one user; Pro $20 a user a month; Team $60; Ultra $200 | Mac; Linux experimental | Claude Code, Codex, OpenCode, and any command-line agent |
| Enjoy | Every lab’s agent, through usage limits | A monthly subscription, free for 7 days, with your phone and one computer (pricing) | Mac, Windows, Linux | Claude Code, Codex, Grok Build, Antigravity, Muse Code, OpenCode |
| Claude Code Desktop | Only Claude, with SSH and cloud sessions | Included in Claude Pro ($20 a month), Max ($100), Ultra ($200), Team and Enterprise | Mac, Windows; Linux in beta | Claude Code |
| The ChatGPT desktop app | Only Codex, with Linear issues | Included in every ChatGPT plan, from Free; Plus is $20 a month | Mac, Windows; Linux in preview | Codex |
Prices are per month as each maker lists them, before tax. The independent apps run your agents on your own Claude, ChatGPT or other plans and API keys, which those companies bill for separately. Claude Code Desktop and the ChatGPT app come with those plans.
Why people look for an Emdash alternative
Emdash Classic does a lot for free: it pulls tasks “from Linear, Jira, GitHub, Notion, Asana, and more,” connects “over SSH to your dev server, cloud VM, or GPU box,” and runs automations on a cron schedule. The reasons to look elsewhere are about where it’s going:
- New features go to 2.0. Emdash Classic “stays available and keeps getting fixes,” but “new development has moved to Emdash 2.0,” and its download page says “If you can, start with 2.0.” The latest Classic release, v1.2.10, came out on October 30.
- 2.0 isn’t out, and has no price. “Emdash 2.0 is on the way. Early access is open,” its makers wrote, adding “We’ll share more soon.” Its early-access page asks for a work email, and says agents will run “on your own infrastructure or Emdash cloud.” Its docs “are coming at launch.”
- There’s no phone app yet. Classic’s docs describe none. Handing off work “from Slack, Linear, GitHub or your phone” is on the 2.0 page.
- Schedules need a machine that’s on. “A stopped machine cannot execute a scheduled run,” its automations page says.
Orca
Best for: the closest thing to Emdash Classic, still adding features, free.
Orca, from Stably, says “Run Claude Code, Codex, and any other coding agent in parallel, each in its own worktree.” Its README covers both of Emdash’s signature features: “See your GitHub and Linear tasks in one place, and start a workspace for each when you’re ready to build,” and “Pair a Remote Orca Server, work on any SSH host, or give a worktree its own cloud VM.” Its docs list 40 agents set up out of the box, and “Orca works with any CLI agent.” Automations “run a prompt on a schedule from the CLI,” and a mobile companion for iOS and Android, in beta, lets you “reply to prompts, review source control, and switch agent accounts.”
Price: free. “Orca is free and open source under the MIT License,” on macOS, Windows and Linux.
Watch for: its README names GitHub and Linear tasks, not Jira, Notion or Asana, and remote machines are yours to run: “Orca does not sell managed VPS hosting,” says Ways to run. And “Orca pre-fills each supported CLI’s permission-bypass flag for new launches,” so agents don’t ask first unless you switch to Manual under Settings → Agents → Agent Permissions. See Orca alternatives.
T3 Code
Best for: a simpler, free app for running agents side by side, on a server or from your phone.
T3 Code calls itself “the open-source control plane for coding agents,” and “If an agent is set up on your computer, T3 Code can control it.” Its README lists Claude Code, Codex, Cursor, OpenCode, Grok Build, Antigravity, Kiro, Pi, Muse Code, fx, “and any ACP agent.” Each thread “can work in its own worktree,” and you can “Change models in the middle of a thread.” For remote work, its FAQ says “Your agents run wherever T3 Code runs: your desktop, a server, a VPS,” with apps for iOS and Android and a web app.
Price: “Nothing. There’s no way to pay us to use T3 Code,” under the MIT license. Its remote service, T3 Connect, “is free too, for now,” for up to three machines.
Watch for: its README and FAQ don’t mention taking issues from trackers, and it runs no local models: “Locally runnable models are not capable of meaningful engineering work,” its FAQ says. On T3 Connect’s cost, it adds “if the bill gets unacceptable we may have to change course.”
Paseo
Best for: running agents on several machines, with a full app on your phone.
Paseo is “an open source agentic development environment for desktop, mobile, web, and CLI,” its README says: “Run many agents at once, each in its own worktree, on one machine or several. The mobile app is the full app, native on iOS and Android.” It runs “Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity, and Muse Code through the same interface,” and it downloads for macOS, Windows, Linux, iOS and Android, with a web app and a server you can run anywhere.
Price: free, under the Apache 2.0 license. Paseo Hub, the nearest thing here to taking work from a tracker, starts agents on your machines from GitHub, Slack and Discord. Hosted, it’s free for 50 agent runs a month and one seat, or $15 a seat a month for unlimited runs, and you can host it yourself for free.
Watch for: Hub is in beta, and “access to the beta stays small and trusted.” Its triggers are GitHub, Slack and Discord, not Linear or Jira, and agents run on machines you keep running.
Herdr
Best for: people who want their agents in real terminals, across several machines.
“Herdr is an app for running coding agents that you shape by asking,” and its agents “run on your machines, not in a window.” You can “Add any machine you can reach over SSH, like a server, a VM or a cloud sandbox,” whose “agents keep running there while your laptop sleeps or the app is closed.” It works with “Anything that runs in a terminal,” on “macOS (Apple silicon), Linux (x86_64 and arm64) and Windows (x86_64),” with apps for “iPhone, iPad and Android.”
Price: free. “The app, herdr-core and Herdr TUI are open source under Apache 2.0.”
Watch for: its site doesn’t describe taking issues from trackers or running agents on a schedule. And “If the machine reboots or herdr-core stops, the programs stop too,” and “Herdr doesn’t restart an agent or resume its work in progress.”
Paradev, formerly Superset
Best for: teams on Macs who want what Emdash 2.0 promises today: Linear, Slack and cloud workspaces.
“Superset is now Paradev,” its homepage says, “The open-source workspace for Claude Code, Codex, and any coding agent.” It says “Paradev is MIT licensed,” each agent “runs in its own Git worktree and branch,” and an iPhone and iPad app “lets you check on agents and review their diffs away from your desk.”
Price: the free plan is “For individuals getting started,” with local workspaces, the desktop app and its command line. Pro, $20 a user a month or $16 billed yearly, adds remote access, automations, the mobile app, and the Linear and Slack integrations. Team, $60 or $54 billed yearly, adds cloud workspaces with 150 hours per seat each month; Ultra is $200, with 500 hours.
Watch for: “The desktop app runs on macOS, with an experimental Linux AppImage; Windows is not yet available.” Paradev also publishes its own Emdash alternatives page, which recommends Paradev.
Enjoy
Best for: keeping work going when an agent or a plan runs out, across all your projects.
Enjoy runs Claude Code, Codex, Grok Build, Antigravity, Muse Code, and local models through OpenCode, on Mac, Windows and Linux, on the AI plans you already have. Each conversation runs its own agent, and an agent can work in a worktree, as it would in Emdash. What it adds:
- Switch agents mid-conversation. When one lab’s agent is the wrong fit or out of usage, another picks up the same conversation: “The new agent gets the conversation so far, including replies from other agents, before it works on your message.”
- Keep going through limits. When an agent runs out of usage, Enjoy switches to another of your accounts that still has usage, or waits for the limit to reset, then continues.
- A superagent over everything. JOY keeps an eye on all your projects: ask it what needs you, catch up on what your agents did, or start work in any project.
- Your phone and any browser. Pair your phone with a code, and use the iPhone app or any browser, end-to-end encrypted.
- More than code. Projects don’t have to be Git repositories, and workflows can run on a schedule.
Price: Enjoy is one monthly subscription, and the first seven days are free, with a card to start. It includes your phone and any browser and one computer; each other computer costs extra each month, and each teammate you invite needs a subscription of their own. See pricing.
Watch for: Enjoy isn’t open source, and it’s a monthly subscription on top of your AI plans once the free week ends, where Emdash Classic is free. It doesn’t take issues from trackers, and it doesn’t open projects over SSH: agents run on a computer where Enjoy is installed. It runs six agents, where Emdash lists 35. Scheduled workflows run only while your computer is awake with Enjoy open. And it doesn’t stop two conversations from editing the same files: overlapping work needs a worktree, which you ask for.
Claude Code Desktop
Best for: people who only use Claude, with sessions on their own servers or in Anthropic’s cloud.
Claude Code is the Code tab of Anthropic’s Claude desktop app, where you can open new sessions “to work on multiple tasks in parallel.” Its docs list SSH sessions, which run “on a remote machine you connect to over SSH, such as your own servers, cloud VMs, or dev containers,” and cloud sessions, which “run on Anthropic-managed infrastructure by default and continue even if you close the app or shut down your computer.” It runs on Mac and Windows, with Linux in beta.
Price: “Claude Code is included in all paid plans,” Anthropic’s pricing page says: Pro at $20 a month, or $17 billed yearly, Max at $100, Ultra at $200, Team and Enterprise.
Watch for: it runs only Claude, and “By default, Worktree is off and Claude works in the project folder itself,” so local sessions share one folder unless you turn it on.
The ChatGPT desktop app, for Codex
Best for: people who only use OpenAI, and assign work from Linear.
OpenAI’s desktop app is where Codex runs on your computer: “Run projects in parallel, work with files, use your computer, and keep long-running work moving from one desktop workspace.” You can “Download ChatGPT for macOS, Windows, or Linux,” and on Linux it’s “available in preview.” Codex takes work from Linear too: “Assign an issue to Codex or mention @Codex in a comment,” and “Codex creates a cloud chat and replies with progress and results.”
Price: on every ChatGPT plan, from Free. Go is $8 a month, Plus $20, and Pro starts at $100. “Codex in Linear is available on paid plans.”
Watch for: it runs only Codex, and Free and Go get “GPT-6 Luna at Standard speed in the desktop app, subject to rollout,” not OpenAI’s top models.
When to stay with Emdash
If Emdash Classic does your work, you don’t have to move. It “stays open source and keeps getting fixes,” its latest release came out on October 30, and nothing else here takes issues from as many trackers: Linear, Jira, GitHub, Notion and Asana, where Orca takes GitHub and Linear and Paradev takes Linear. It’s free under Apache 2.0, and its docs list 35 agents.
If you’re a team that wants agents in the cloud, from Slack or from your phone, Emdash 2.0 is aimed at you: join its early access and judge it when it has a price. Until then, keep using Classic, and move when a fix you need doesn’t come.
How we compared
We read each maker’s homepage, pricing, install and docs pages, and their GitHub repositories, on November 16, 2026, and every one is linked below. We quote their own words for the limits, and we don’t count features a maker hasn’t documented. Emdash’s own pages give its agent count three ways, from “25+” to 35; we use its providers page, which says “Emdash supports 35 coding agent CLIs.” Roundups at Paradev, Munder Difflin, AlternativeTo and OpenAlternative list more apps, including Nimbalyst, Orchestrator.inc, Munder Difflin and Worktrunk, which we didn’t compare here. We left out Conductor, which runs only on Macs: “Conductor is not available for Windows or Linux yet,” says its installation page. Our Conductor guide compares it. This category changes weekly, so we recheck this guide against its sources at least once a month, and the date at the foot of the page says when we last did.
13.Questions.
What’s the best alternative to Emdash?
- It depends on what you use it for. Orca is the closest match, with GitHub and Linear tasks, SSH hosts and 40 agents set up, free; T3 Code is simpler; Paseo and Herdr suit agents on several machines; Paradev adds Linear and cloud workspaces for teams on Macs; Enjoy runs every lab’s agent through usage limits; and Claude’s or ChatGPT’s own app will do for one lab.
Is Emdash shutting down?
- No. On November 5, 2026, it renamed its desktop app Emdash Classic, which “stays open source and keeps getting fixes,” and its latest release, v1.2.10, came out October 30. “New development has moved to Emdash 2.0,” a cloud product for teams that’s in early access with no published price.
Which alternative takes issues from Linear or GitHub?
- Orca shows “your GitHub and Linear tasks in one place,” free. Paradev has a Linear integration from its Pro plan, $20 a user a month. Paseo Hub starts agents from GitHub, Slack and Discord, free for 50 runs a month. Codex takes Linear issues on paid ChatGPT plans. Enjoy doesn’t take issues from trackers.
Which alternative runs agents on a remote machine over SSH?
- Orca, Herdr and Claude Code Desktop connect to machines over SSH. T3 Code and Paseo run on the remote machine, and you connect to them from your laptop, phone or browser. Enjoy runs agents on a computer where Enjoy is installed, and each computer beyond the first costs extra each month.
What’s a free, open-source alternative to Emdash?
- Orca and T3 Code, under the MIT license, and Paseo and Herdr, under Apache 2.0, the same license as Emdash. All four are free on Mac, Windows and Linux, though Herdr runs only on Apple silicon Macs. Paradev is under the MIT license too, with a free plan for one user, on Mac with an experimental Linux build.
Do I still need a Claude or ChatGPT plan?
- Yes. Emdash and the independent apps here run agents on your own Claude, ChatGPT or other plans and API keys, which those companies bill for separately. Claude Code Desktop and the ChatGPT desktop app come with those plans.