Inter-office memo
- To
- Everyone running coding agents in Claude Squad
- From
- Mo, Chief Executive
- Date
- November 19, 2026, 1:47 AM CST
- Re
- Claude Squad alternatives
Claude Squad alternatives in 2026: 8 apps for running coding agents in parallel
The best Claude Squad alternative depends on why you’re leaving: Claude Code’s own agent view if you only use Claude, Agent Deck to stay in tmux with more features, Herdr, Orca, T3 Code or Paseo for a free app on Windows and your phone, Paradev for teams on Macs, and Enjoy to run every lab’s agent through usage limits. Claude Squad is still right if its tmux app does the job.
Disclosure: Enjoy is our product. We checked every app below against its maker’s own pages and GitHub repository on November 19, 2026, and we say where another app is the better pick, Claude Squad included.
Claude Squad alternatives compared
Claude Squad, from smtg-ai, is a free, open-source terminal app that runs several coding agents at once, each in its own tmux session and Git worktree. “Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp,” says its GitHub page, where it has more than 8,800 stars. If you only use Claude, Claude Code’s own agent view now does much of the same job; if you want to stay in tmux with more features, look at Agent Deck; for a desktop app that also works on Windows and your phone, Herdr, Orca, T3 Code and Paseo are free. These are the apps people weigh against it, side by side.
| App | Best for | Price, checked November 19, 2026 | Runs on | Agents | How you use it |
|---|---|---|---|---|---|
| Claude Squad | Agents in tmux, free | Free | Mac, Linux | Claude Code by default, or any command you give it | Terminal |
| Claude Code’s agent view | Only Claude, in the terminal | Included in Claude Pro ($20 a month), Max ($100), Ultra ($200), Team and Enterprise | Mac, Windows, Linux | Claude Code | Terminal |
| Agent Deck | Staying in tmux, with more features | Free | Mac, Linux; Windows through WSL | Claude Code, Codex, Gemini CLI, OpenCode and more | Terminal, with a web mode |
| Herdr | Agents in real terminals, on any machine | Free | Mac (Apple silicon), Windows, Linux | Anything that runs in a terminal | Desktop and phone apps, or a terminal app |
| Orca | The most agents, free | Free | Mac, Windows, Linux | 41 in its docs, and any command-line agent | Desktop app with terminals, and a phone app |
| T3 Code | A simple, free control plane | Free | Mac, Windows, Linux | Claude Code, Codex, Cursor, OpenCode, Grok Build, Antigravity, Kiro, Pi, Muse Code, and ACP agents | Desktop, web and phone apps, and a command line |
| 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 | Desktop, web and phone apps, and a command line |
| Paradev, formerly Superset | Teams on Macs, with 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 | Desktop app, and an iPhone and iPad app |
| 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 | Desktop, web and iPhone apps |
Prices are per month as each maker lists them, before tax. Every app here runs your agents on your own Claude, ChatGPT or other plans and API keys, which those companies bill for separately; Claude Code’s agent view comes with a paid Claude plan.
Why people look for a Claude Squad alternative
Claude Squad does one thing simply, and for free: its README says it uses “tmux to create isolated terminal sessions for each agent” and “git worktrees to isolate codebases so each session works on its own branch.” Its license is AGPL-3.0, and its latest release, v1.0.20, came out on August 20, 2026. People look elsewhere for five reasons:
- It’s terminal only. It needs tmux and GitHub’s
ghcommand line, and you drive it with keys such asnfor a new session andtabto switch between its preview and diff. - It doesn’t run on Windows itself. Its releases include Windows builds, but an issue opened against v1.0.17 in April 2026, and still open, reports that “creating any new session fails instantly” with “error starting tmux session: unsupported,” and lists “Workarounds for other Windows users finding this” as “Currently none.” None of the three releases since mentions a fix.
- One repository at a time. An open request from April 2025 notes that “new instances are automatically tied to the repository of the active folder.”
- Nothing for your phone. Its README describes no phone or web app, so checking on agents away from your desk means SSH and tmux.
- Auto-accept is limited. Its
--autoyesflag is “[experimental]” and accepts prompts “for claude code & aider.”
Claude Code’s agent view
Best for: people who only use Claude and want to stay in the terminal.
Claude Code now has much of Claude Squad built in. “Agent view, opened with claude agents, is one screen for all your background sessions: what’s running, what needs your input, and what’s done,” say Anthropic’s docs. Each row shows whether a session is working, needs input or has finished, and you can peek, reply or attach. “Before editing files, Claude moves the session into an isolated git worktree under .claude/worktrees/, so parallel sessions can read the same checkout but each writes to its own.” Sessions keep running with no terminal open, and its changelog covers macOS, Windows, Linux and WSL. For one-off parallel work, claude --worktree feature-auth in a second terminal starts “an isolated parallel session,” and the desktop app has a Worktree switch for each session.
Price: “Claude Code is included in all paid plans,” says Anthropic’s pricing page: 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 “Agent view is in research preview. The interface and keyboard shortcuts may change as the feature evolves.” Its limits say “running ten agents in parallel uses quota roughly ten times as fast as running one,” and “Claude-created worktrees are deleted with the session in agent view,” so commit first.
Agent Deck
Best for: staying in tmux, with more agents and more features than Claude Squad.
“Agent Deck runs all your AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode and more) in one terminal and shows which ones are working, waiting, or done,” says its README. Its own FAQ calls it “tmux plus AI awareness.” Like Claude Squad, it gives sessions their own worktrees, so “Multiple agents can work on the same repo without conflicts.” It goes further with sessions on “remote SSH servers from your local terminal,” a web mode in the browser, and conductors, “persistent agent sessions that monitor and orchestrate all your other sessions,” which can reach you through Telegram, Slack, Discord or Mattermost. Its latest release, v1.16.39, came out on November 14.
Price: free, under the MIT license.
Watch for: it “Works on macOS, Linux and Windows (WSL),” and its FAQ says “WSL2 is recommended for full feature support including MCP socket pooling,” so on Windows it’s still tmux in Linux. There’s no phone app: away from your desk, you reach it through a conductor’s chat bot or its browser mode, which listens only on your own computer until you set it up to be reached, through Tailscale for example.
Herdr
Best for: agents in real terminals, on your own machines, with apps for your phone and native Windows.
“Herdr is an app for running coding agents that you shape by asking,” says its site, and it works with “Anything that runs in a terminal.” It runs on “macOS (Apple silicon), Linux (x86_64 and arm64) and Windows (x86_64),” with apps for iPhone, iPad and Android, and you can “Add any machine you can reach over SSH, like a server, a VM or a cloud sandbox.” If you’d rather keep a terminal app, “Herdr TUI is the original Herdr: a terminal app with its own server,” though its agents don’t appear in the new app.
Price: free. “The app, herdr-core and Herdr TUI are open source under Apache 2.0.”
Watch for: its site doesn’t mention worktrees, so separating agents that touch the same files is up to you. 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.”
Orca
Best for: the widest choice of agents in a desktop app, free.
Orca, from Stably, says “Run Claude Code, Codex, and any other coding agent in parallel, each in its own worktree.” Its homepage lists a “GPU-rendered terminal with splits” and “Chat UI and terminal, switch any time,” so it suits people coming from tmux. Its docs list 41 agents set up out of the box, from Claude Code and Codex to Aider and Goose, and “Orca works with any CLI agent.” It runs on macOS, including Intel Macs, Windows and Linux, and a mobile companion for iOS and Android lets you “reply to prompts, review source control, and switch agent accounts.”
Price: free. Its homepage says “Free and open source,” under the MIT license.
Watch for: “The mobile companion is in beta,” and “Orca pre-fills each supported CLI’s permission-bypass flag for new launches,” much as Claude Squad’s --autoyes does, so agents don’t ask first unless you switch to Manual under Settings → Agents → Agent Permissions. An always-on machine is yours to run: “Orca does not sell managed VPS hosting,” says Ways to run.
T3 Code
Best for: a simple, free app for running agents side by side, from your desk or your phone.
T3 Code calls itself “The open-source control plane for coding agents.” Its README lists Claude Code, Codex, Cursor, OpenCode, Grok Build, Antigravity, Kiro, Pi, Muse Code, fx, “and any ACP agent,” and says “If an agent is set up on your computer, T3 Code can control it.” “Each thread can work in its own worktree,” you can “Change models in the middle of a thread,” and there are apps for macOS, Windows and Linux, iOS and Android, a web app, and a t3 command that starts its server.
Price: “Nothing. There’s no way to pay us to use T3 Code,” says its FAQ, under the MIT license. Its remote service, T3 Connect, “is free too, for now.”
Watch for: “Worktrees add up fast. One user cleared 500 GB,” its FAQ warns, so turn on its automatic cleanup. And it runs no local models: “Locally runnable models are not capable of meaningful engineering work.”
Paseo
Best for: running agents on several machines, with a full app on your phone and a command line.
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 its downloads cover macOS, Windows, Linux, iOS, Android, a web app and a command line from npm or Nix, so you can keep starting agents from a terminal.
Price: free, under the Apache 2.0 license. Paseo Hub, which starts agents on your machines when you mention it in GitHub, Slack or Discord, is free for 50 agent runs a month and one seat when Paseo hosts it, or $15 a seat a month, and free to host yourself.
Watch for: Hub is in beta, and “access to the beta stays small and trusted.” Agents run on machines you keep running.
Paradev, formerly Superset
Best for: teams on Macs who want a desktop app with cloud workspaces.
“Superset is now Paradev,” its homepage says. Its pitch is “Run an Army of Coding Agents,” where “Each task gets its own Git worktree and branch,” and “Paradev works with any CLI-based coding agent, including Claude Code, OpenCode, OpenAI Codex, and more.” It says “Paradev is MIT licensed, so you’re never locked in,” and an app for iPhone and iPad “lets you check on agents and review their diffs away from your desk.”
Price: its free plan is “For individuals getting started,” with local workspaces, the desktop app and its command line. Pro is $20 a user a month, or $16 billed yearly, and adds remote access, automations, the mobile app, and Linear and Slack. Team is $60, or $54 billed yearly, with cloud workspaces of 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 comparison with Claude Squad, which recommends Paradev.
Enjoy
Best for: running every lab’s agent across all your projects, without stopping when one plan runs out.
Enjoy runs Claude Code, Codex, Grok Build, Antigravity, Muse Code, and local models through OpenCode, on Mac, Windows and Linux, including projects inside WSL, 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 Claude Squad. 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.
- Every project at once. Its Inbox lists open conversations from all your projects, “with the ones waiting on you first,” where Claude Squad ties its sessions to the repository you start it in. JOY can catch you up on what your agents did.
- Your phone and any browser. Pair your phone with a code, and use the iPhone app or any browser.
- 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 Claude Squad is free. It’s a desktop app of conversations, not a terminal app, so if tmux is what you like about Claude Squad, Agent Deck or Claude Code’s agent view will feel closer. It runs six agents, where Claude Squad runs any command you give it. It doesn’t stop two conversations from editing the same files: overlapping work needs a worktree, which you ask for. And scheduled workflows run only while your computer is awake with Enjoy open.
When to stay with Claude Squad
If you work on a Mac or Linux, live in tmux, and run agents in one repository at a time, Claude Squad still does the job, for free. It’s light: one cs command, a list of sessions, a preview and a diff, and a key to commit and push. It runs any command-line agent through its -p flag or a profile in its config file, which several apps here can’t match. Its repository was still taking changes in November, and its latest release came out on August 20.
Move when one of its limits starts to cost you: you need Windows, your phone, more than one repository in view, or agents that keep going while you’re away from the terminal. If you only use Claude, try claude agents first, since it’s already on your machine.
How we compared
We read each maker’s homepage, pricing and docs pages and their GitHub repositories, including Claude Squad’s issues and releases, on November 19, 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. Roundups at aicoolies and Open Source Alternatives list more apps, including Emdash, Oh My ClaudeCode, Baton, Jean and Omnara, which we didn’t compare here; our Emdash guide covers Emdash. We left out Conductor, which runs only on Macs: 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 Claude Squad?
- It depends on why you’re leaving. Claude Code’s agent view does the job if you only use Claude; Agent Deck keeps you in tmux with more features; Herdr, Orca, T3 Code and Paseo are free apps that run natively on Windows and on your phone; Paradev suits teams on Macs; and Enjoy runs every lab’s agent across your projects through usage limits.
Does Claude Squad work on Windows?
- Not natively, by its own issue tracker. Its releases include Windows builds, but an issue opened in April 2026, still open on November 19, reports that creating a session “fails instantly” with “error starting tmux session: unsupported.” Agent Deck runs on Windows through WSL, and Herdr, Orca, T3 Code, Paseo and Enjoy run on Windows itself.
Is there a Claude Squad with a GUI?
- Yes, several. Orca, T3 Code, Paseo, Herdr, Paradev and Enjoy are desktop apps that run agents side by side, most of them each in its own Git worktree as Claude Squad does. Orca and Paseo keep terminals in the window, and Paseo and T3 Code have command lines too.
What’s a free, open-source alternative to Claude Squad?
- Agent Deck, Orca and T3 Code, under the MIT license, and Herdr and Paseo, under Apache 2.0. All are free. Paradev is MIT-licensed too, with a free plan for one user on Macs.
Does Claude Code do what Claude Squad does now?
- For Claude, mostly. `claude agents` opens agent view, “one screen for all your background sessions,” and each session moves into its own Git worktree before it edits files. It’s in research preview, runs only Claude, and is included in every paid Claude plan.
Do I still need a Claude or ChatGPT plan?
- Yes. Claude Squad and every app here run your agents on your own Claude, ChatGPT or other plans and API keys, which those companies bill for separately. Claude Code’s agent view comes with a paid Claude plan.