Our desktop and mobile apps are open sourceOpen source

Agents scale. Your attention doesn't.

Everything you'd expect: parallel worktrees, scheduled runs, shared skills, memory, MCPs, mobile, and more. All running on your existing subscriptions, and all optimized to keep you in flow.

100% free and open source, no card required. Also for Windows
Bring your own subscription with

What it takes to run agents at scale

Every agent, on your subscription

Run Claude Code, Codex, and Cursor on the plans you already pay for. Pick the agent for each task without changing tools.

As many as you need, in parallel

Each task gets its own worktree, terminal, and browser, grouped by repo. Quit or reboot and the list comes back.

Pipelines on a schedule

Chain prompts and scripts across agents, and start them on a schedule or a hook.

Quiet until it's your turn

Agents work in the background and the app stays muted. When one needs an approval, an answer, or a review, it lights up so you know where to look.

Google Drive and Gmail are trademarks of Google LLC. Jira and the Jira logo are trademarks of Atlassian. Integration doesn't imply endorsement.

Less to keep in your head

Chat or terminal, your call

Prefer the TUI? Switch any Claude chat to terminal mode and keep your hooks, status line, CLAUDE.md, and skills. Prefer a chat view? Switch back. It's the same session either way.

100% free and open source, no card required. Also for Windows

A second opinion before it ships

Have Claude and Codex each review a change before it ships, and Autopilot fix what they find.

100% free and open source, no card required. Also for Windows

Bring your setup with you

Import your projects, chats, and memory from Claude Code and Codex. The skills and plugins you already use with Claude Code, Codex, and Cursor work as they are.

100% free and open source, no card required. Also for Windows

Embedded tools for every agent

Agents can open the built-in browser, take screenshots, run commands, and use the plugins you have connected. Chain those into a workflow, or let the agent reach for them as it works.

100% free and open source, no card required. Also for Windows

Respond on the go

Step away without wondering what's stuck. Remote Control brings your workspace to the web and your chats to your phone, so you can answer an agent from anywhere. Turn on activity sharing to get a push when one needs you. Your computer needs to stay on.

Download on the App StoreGet it on Google Play

Private by default

We don't collect your code or conversations by default, and we don't sell your personal information. Activity sharing is optional and off by default.

An app shaped around how you work

Tell the built-in assistant how you handle triage, planning, and reviews. It builds the skills, pipelines, and schedules to match.

100% free and open source, no card required. Also for Windows

Don’t like something? Fork it.

Our desktop and mobile apps are open source. Read every line that runs on your machine, change what you want, and build it yourself.

  • Audit it. See exactly what runs on your machine and what it sends.
  • Change it. Restyle the UI or wire in your own agents and tools.
  • Build it. Run your own build from source. It connects to our services out of the box, and the config is yours to change.
Commands to fork, install, build, and start the desktop app from source.
gh repo fork unstoppableweb/unstoppable-code --clone
cd unstoppable-code/clients/desktop
pnpm install --frozen-lockfile --ignore-scripts
pnpm run build:public
pnpm run setup:public
pnpm run start:public

Compare Unstoppable to other leading AI coding orchestrators

Feature comparison between Unstoppable, Cursor, Orca, Conductor
CapabilityUnstoppableCursorOrcaConductor
Deterministic workflows orchestrating Codex and ClaudeYes
Unknown. Cursor documents automations, but a deterministic workflow across external Codex and Claude CLIs was not verified.
Partial. Experimental task dependencies, supervised workers, and decision gates; not a confirmed equivalent workflow builder.
Partial. Multiple provider tabs and API orchestration; a deterministic cross-provider workflow builder was not verified.
Plugin, skill, & memory sync across providersYes
Partial. Imports third-party configuration; ongoing bidirectional sync across providers was not verified.
Partial. Supports skills, MCP, and provider memory files; cross-provider memory sync was not verified.
Partial. Reuses skills and configures MCP per provider; automatic cross-provider memory sync was not verified.
Multi-repo PR supportYes
Yes. Multi-repo cloud environments can open PRs in each changed repository.
Partial. Groups repositories into folder workspaces with one selected task-source repository; coordinated PR handling across the group was not verified.
Partial. Links workspaces for cross-repository edits; a coordinated multi-repo PR workflow was not verified.
Remote control and mobile appYes
Yes. Native iOS app controls local and cloud agents; Android is planned.
Yes. Mobile companion connects to local or remote Orca runtimes.
Yes. The current homepage links a published iOS app for monitoring and managing workspaces; no Android app was verified.
Team cost and usage dashboardYes
Yes. Team and Enterprise usage analytics with spending controls.
Partial. Per-account usage and rate-limit tracking; a centralized team spending dashboard was not verified.
Partial. Centralized team billing; a per-agent team cost and usage dashboard was not verified.
Bring your own subscriptionYes
Unknown. Bring-your-own API keys are documented; Claude Code or Codex subscription authentication was not publicly verified.
YesYes
macOS and WindowsYesYesYes
No. The desktop download and local setup target macOS; cloud access is browser-based.
Cloud agentsYesYes
Partial. Runs on SSH machines, self-hosted servers, or cloud accounts you control; not vendor-hosted compute.
Yes. Hosted cloud workspaces on eligible paid plans.
Native chat interfaceYesYes
Partial. Experimental structured native chat for eligible local Claude and Codex sessions; remote sessions remain terminal-backed.
Yes

Comparison as of October 1, 2026, based on each product’s publicly documented capabilities.

FAQs

Do I lose my terminal setup?

No. Use the chat view, or switch a Claude chat to terminal mode, which runs Claude Code's own TUI with your settings and hooks. Pick whichever suits how you work; you can also open a terminal in any worktree.

What happens to my sessions when I quit or restart?

Your chats and history come back when you reopen the app. A local agent that was mid-task stops when you quit; reopen the app and resume it with one click. Use web agents for work that has to keep going.

Do I have to use your agent or can I bring my own?

You can bring your own. Run Codex, Claude Code, Cursor, or another coding CLI side by side. Connect your existing agent subscription in the desktop app and choose the agent for each task; you don't have to replace the tools you already pay for.

Is Unstoppable open source?

Yes. The desktop and mobile apps are open source under the MIT license, and the code is on GitHub. Builds from source connect to our hosted services out of the box, and you can change that config when you build. Our hosted services aren't open source. You're free to fork it.

How do I keep multiple AI coding agents from overwriting each other's changes?

Give each agent its own isolated worktree instead of having them share one. Unstoppable runs every agent in its own worktree inside one workspace, so parallel agents can work on different parts of a project without colliding, and you review each plan before it merges back in.

How is Unstoppable different from a code editor or terminal?

Editors and terminals give you the tools and leave the keeping track to you. Unstoppable does the keeping track. Every task has its place, you can see what's working and what's done, and you step in only when an agent needs you.

Which platforms do you support?

The desktop app is available for macOS and Windows, with separate Apple Silicon and Intel Mac downloads. The mobile app is available for iOS and Android, and web agents run in your browser. Use the download menu for your platform and the release notes for updates.

Can agents keep working while I am away from my computer?

Yes. There are two modes. Remote Control lets you follow and unblock agents in your desktop app from your phone or browser; that computer must stay online. Web agents work in the cloud independently of your desktop, so choose that mode when you need hosted execution.

Can one task span multiple repositories and pull requests?

Yes. Use a multi-repo project when a change spans related repositories. Agents can work across those repositories while you track their separate GitHub pull requests, review the changes, and merge each PR when it is ready.

Can I bring my existing memory, plugins, and chat history?

Import your agent's memory, plugins, and history from Claude, Codex, and Cursor. Manage plugins and skills across agents in one place, keep useful context when you switch providers, and avoid starting from scratch.

Where do agents run, and what can they access?

Local agents work in the folders and worktrees you choose. Web agents run in hosted cloud environments. Model requests go to the selected provider, and connected plugins can access the accounts and tools you authorize. Review provider and plugin permissions before connecting sensitive data.

How much does Unstoppable cost?

Every app feature is free when you sign in, with no subscription required. Bring your own Claude or ChatGPT subscription to run agents on a plan you already have, or buy AI credits whenever you need them.

Can I track my token usage, spend, and other AI coding costs?

Yes. Unstoppable tracks token usage, spend, and activity across every session, model, and agent, then rolls it up into one dashboard so you can compare week to week, catch your most expensive runs, and right-size usage before it turns into a surprise bill.

Run more agents. Think about them less.

100% free and open source, no card required. Also for Windows

Cookie preferences

Optional cookies measure ads and improve the site with session recordings. Change anytime. Privacy policy