Skip to content

Off-site crew · experimental

Cloud sandboxes for AI coding agents, on your own account.

Foreman is a free, open-source desktop app for macOS and Windows that runs AI coding agents in parallel. Claude Code, Codex, Cursor and OpenCode each work in their own git worktree on their own branch, while you review diffs, answer questions and open pull requests from one window.

As an experiment, a workspace’s worktree and agent can run in a sandbox on your own E2B, Daytona, Vercel Sandbox or Docker account. Close the laptop. The crew keeps going.

  • macOS & Windows
  • Apache-2.0
  • No Foreman account
  • Your sandbox account

Try it · Illustrative

Send it off-site

Pick a workspace and a container, ship it, then close the laptop and see who keeps working.

New workspace · atlas

Workspace

Runs on

Sandbox
E2B
Size
2 vCPU
Starts from
A fresh clone, set up when it’s made
Sleeps after
20 min idle
Agent sign-in
Claude setup token

Remote workspaces run on E2B. Experimental.

This computer

Foreman · atlasZzz

Vault

  • Provider keystays here
  • GitHub tokenstays here
  • Agent sign-instays here
  1. Clone from GitHub The repository comes from its GitHub remote. GitHub’s token goes in as that one command’s environment.
  2. Install the agent host Foreman puts its small agent host in the sandbox, so the agent can run there without your computer.
  3. Set up The install script and the repository’s setup steps run, as they would in a local worktree.
  4. Run The agent takes the turn in the sandbox. Your computer only coordinates.

Session · not started

Turn · waiting to ship

  1. Pick a workspace and a container, then Create. Closing the laptop quits Foreman: remote turns go on in their sandboxes until they finish or reach the session limit, and their chats catch up when you open Foreman again.

This month · no sandbox time yet

Stencilled on the side

Can I run Claude Code in an E2B sandbox?

Yes, as an experiment. Turn on Remote workspaces, connect your E2B API key in Settings → Integrations, and New workspace offers Remote for the repository. Claude Code then runs in the sandbox with a setup token or an Anthropic API key.

  • E2B keeps no base: each workspace is cloned and set up from scratch, so it takes longer to start.
  • 2, 4 or 8 vCPUs. On E2B’s Hobby plan a session lasts an hour; Foreman continues the turn when you’re around.
  • Codex and OpenCode run there too. Cursor doesn’t yet.
A Foreman workspace: the agent's chat in the middle and its changes on the right
Same workspace Chat in the middle, changes on the right. A remote workspace keeps this and adds a sandbox pill to its header.

Which sandbox providers does Foreman support?

Four, each on your own account: E2B, Daytona, Vercel Sandbox and Docker, on this computer or another over SSH.

  • E2B

    Provider
    E2B
    Runs
    Hosted
    Sessions
    1-hour sessions on Hobby
    Size
    2, 4 or 8 vCPUs
    Base
    None: cloned and set up per workspace
  • DAYTONA

    Provider
    Daytona
    Runs
    Hosted
    Sessions
    24-hour sessions
    Size
    1, 2 or 4 vCPUs
    Base
    Built once, then each workspace starts from it
  • VERCEL

    Provider
    Vercel Sandbox
    Runs
    Hosted
    Sessions
    45-minute sessions on Hobby
    Size
    2, 4 or 8 vCPUs
    Base
    Built once, then each workspace starts from it
  • DOCKER

    Provider
    Docker
    Runs
    This computer, or another over SSH
    Sessions
    No session limit
    Size
    1 to 8 vCPUs
    Base
    Built once, then each workspace starts from it

Site office

Where do the keys live when an agent runs in the cloud?

On your computer. Provider keys stay in Foreman’s vault and never enter the sandbox; Foreman’s main process uses them from here. GitHub’s token reaches a sandbox only as one command’s environment.

  • Provider key

    E2B, Daytona or Vercel key · Docker context

    In the vault on this computer

    Never enters the sandbox. Foreman uses it from here to start, wake and sleep sandboxes.

  • GitHub token

    From gh or a personal access token

    In the vault on this computer

    Reaches the sandbox only as one command’s environment, for the clone, then it’s gone.

  • Agent sign-in

    Claude setup token or API key · Codex API key

    Stored encrypted on this computer

    Passed to the agent while it runs. Your Claude subscription sign-in can’t be copied into a sandbox.

After hours

What happens to a remote turn when you close the laptop?

It keeps going. Remote turns go on in their sandboxes after Foreman quits, until they finish or reach the provider’s session limit, and their chats catch up when you open Foreman again.

  1. 17:58You quitForeman closes. The sandbox doesn’t.
  2. 18:30The turn runs onIn the sandbox, on your account, with nobody watching.
  3. 19:05It finishes, or stops at the limitA short session ends at its limit, the files are kept and the workspace sleeps.
  4. 08:40You come backForeman reattaches the turn and the chat catches up. Continue picks up a capped one.
  • Sleeps after 20 idle minutesFiles and chats are kept; running processes stop.
  • Wakes when you open itOr when an agent starts, or with foreman cloud wake.
  • Base buildsClone and install once per repository, except on E2B.
  • Usage per providerThis month’s sandbox time, counted from this computer.

Bill of lading

How do you turn on remote sandboxes?

Twice, on purpose. Remote workspaces are off by default in Settings and off in every repository’s Remote tab. Turn on both and New workspace offers This computer or Remote.

Experimental. It works, it’s new, and the switch says so. Expect rough edges and tell us about them.

Bill of ladingNo. FMN-1.2.4

  • A GitHub remote. The sandbox clones from it.
  • Claude Code, Codex or OpenCode. Cursor isn’t supported in sandboxes yet.
  • Claude: a setup token or an API key. The subscription sign-in stays on your computer.
  • Codex: an API key. ChatGPT sign-in is off in sandboxes for now.
  • A provider connection. E2B, Daytona or Vercel key, or a Docker context, in Settings → Integrations.
  • Not in sandboxes yet: the foreman-app MCP tools. A remote chat uses the agent’s default account.

Received in good order · you

Also on the yard

What else does Foreman do?

Sandboxes are one crate. The rest of the yard: one git worktree per agent, schedules and auto-fix, flows, integrations, AI employees, and remote control from your phone.

  • Phone · coming to iOS and Android

    Run it from anywhere

    Pair your phone with a QR code to approve, steer and comment on diffs, live. Away from home it connects over your own Tailscale network, with no Foreman relay. A browser on another computer can open the whole app.

  • The core

    One worktree per agent

    Every workspace is its own git worktree on its own branch. Agents never step on each other, and your main checkout stays clean.

  • Runs on Claude Code

    Automations and schedules

    Save prompts as templates and run them on demand or on a schedule: hourly, daily, weekly or monthly, in your time zone. Run Foreman without a window, or at login, and schedules keep going.

  • Opt-in · within a budget

    Auto-fix CI and auto-review

    Opt in and Foreman sends a failing CI log to your agent within a budget you set, and a read-only reviewer reads each finished diff. Checks can run after every turn, and a chat that hits a usage limit resumes by itself.

  • 11 built in · experimental

    Flows that loop until green

    Write a way of working down once as a graph of agent steps: loops that run until the checks pass or a review comes back clean, and gates where you decide.

  • Nothing · read · read and write

    GitHub, GitLab, Linear, Slack, Langfuse

    Open, merge and auto-merge pull requests, watch CI and reviews, start work from a Linear issue, send Slack notifications and read Langfuse traces. Each connection gets the agent access you choose: nothing, read, or read and write.

  • 15 job templates

    AI employees

    Give an organization employees with a role in plain words, a hard hat and access you approve. They work in fresh workspaces, remember through a git memory repository and hand work to each other.

  • foreman-app MCP server

    Agents that use Foreman too

    Every workspace agent gets a foreman-app MCP server to check its status, run checks and, if you allow it, hand tasks to other agents. A Claude Code or Codex session you run yourself can sign in to Foreman over MCP.

  • --json on every command

    A real command line

    Almost everything in the window works from a terminal with the foreman command. Every command takes --json and exit codes are stable, so scripts and CI can rely on them.

Other yards

How is Foreman different from Conductor and T3 Code?

Foreman is open source under Apache-2.0 and runs on Windows as well as macOS, while Conductor is a closed-source Mac app. Of the three, only Foreman lists sandboxes on your own E2B, Daytona, Vercel or Docker account, plus flows, AI employees and a CLI where every command takes --json.

A dash means not listed on their site

Foreman compared with Conductor and T3 Code
FeatureForemanConductorT3 Code
Open sourceApache-2.0NoMIT
macOSYesYesYes
WindowsYesMac onlyYes
One git worktree per agentYesYesYes
AgentsClaude Code, Codex, Cursor, OpenCode, any ACP agentClaude Code, Codex, CursorClaude Code, Codex and more
Flows that loop until checks pass, with human gatesYes——
AI employees with git-backed memoryYes——
Scheduled automations and auto-fix CIYes——
Your own cloud sandboxes (E2B, Daytona, Vercel, Docker)Experimental——
Scriptable CLI, --json on every commandYes——
Approve from your phoneYes—Yes
No account, no telemetry uploadYes——
From each project's own site as of November 2026. “—” means it isn't listed there, not that it's missing. Spot a mistake? Tell us.

Delivery

Get started in a minute

Download the app, add a repository, give each task a workspace. Ship one off-site when you’re ready.

  1. Download Foreman

    Free for macOS (Apple Silicon) and Windows. You need Git on your PATH.

    Download Foreman
  2. Add a repo, sign in an agent

    Pick any git repository. Sign in Claude Code, Codex, Cursor or OpenCode in Settings → Agents with your own login or key.

  3. Create workspaces

    One per task, each a worktree on its own branch. With Remote on, choose This computer or Remote as you create one.

Or from a terminal
foreman run fix-a-bug "the login page loops after sign-in" --repo atlas --wait

# Start a workspace from a template and wait for the turn. Add --cloud to put the worktree in a sandbox; the repository’s Remote settings apply. CLI reference

Yard office

Questions developers ask

Something missing? Open an issue or read the guide.

What is Foreman?

Foreman is a free, open-source desktop app for macOS and Windows that runs AI coding agents in parallel. Claude Code, Codex, Cursor and OpenCode each work in their own git worktree on their own branch, while you review diffs, answer questions and open pull requests from one window.

Is Foreman free and open source?

Yes. Foreman is free and licensed under Apache-2.0, with the full source on GitHub at github.com/elite-build/foreman. There is no paid tier, no account and no Foreman cloud service.

Which coding agents does Foreman support?

Foreman runs Claude Code, Codex, Cursor and OpenCode, plus any agent that speaks the Agent Client Protocol (ACP). Each agent signs in with your own subscription or API key, set in Settings → Agents.

How do I run multiple Claude Code agents in parallel?

Add a git repository to Foreman and create one workspace per task. Each workspace is a separate git worktree on its own branch, so several Claude Code sessions edit the same repository at once without conflicts. Tiles shows them side by side.

Why does each agent need its own git worktree?

A git worktree is a second checkout of the same repository on a different branch. Giving each agent its own worktree means agents never overwrite each other's files, every change lands on a reviewable branch, and your main checkout stays untouched.

Does my code leave my computer?

Only through the agents you choose. Foreman runs locally with no account and no telemetry upload; your agents talk to their own model providers. In your own workspaces, an approval marks any command that leaves your computer before it runs, and AI employees hold Slack posts and Linear changes for you.

Do coding agents need my approval for every command?

Only if you want them to. Approvals are a setting: with Claude Code tool approvals on (Settings → Account), each command is spelled out part by part before it runs, anything that leaves your computer is marked, and Always allow shows exactly what it adds. Every agent still works in its own worktree, and checkpoints rewind any turn.

Which operating systems does Foreman run on?

Foreman runs on macOS (Apple Silicon, signed and notarized) and Windows. You need Git on your PATH and a login or API key for at least one agent.

Can Foreman run coding agents on a schedule?

Yes. Any saved prompt template can run hourly, daily, weekly or monthly in your time zone, and opt-in auto-fix sends failing CI logs to your agent. Scheduled runs use Claude Code and happen while Foreman is running, which can be without a window or from login.

Can I control Foreman from my phone?

Yes. Pair a phone with a QR code to answer approvals, steer agents, comment on diffs and read terminals, live. On the same Wi-Fi it connects directly, and anywhere else through your own Tailscale network. Native iOS and Android apps are coming soon.

Can coding agents run in a cloud sandbox like E2B?

Yes, as an experiment. A workspace's worktree and agent can run in a sandbox on your own E2B, Daytona, Vercel Sandbox or Docker account, for Claude Code, Codex and OpenCode. Provider keys stay on your computer and never go into the sandbox.

Which integrations does Foreman have?

GitHub (pull requests, merges, CI and reviews), GitLab, Linear, Slack and Langfuse, plus MCP. Each connection has a default per service, each repository can pick its own, and you choose what agents may do with it: nothing, read, or read and write.

How is Foreman different from Conductor?

Foreman is open source under Apache-2.0 and runs on Windows as well as macOS, while Conductor is a closed-source Mac app. Foreman also drives OpenCode and any ACP agent, and adds flows that loop until checks pass, AI employees and a scriptable command line.

How is Foreman different from T3 Code?

Both are open-source GUIs for coding agents. Foreman adds flows (agent graphs that loop until tests pass, with human gates), AI employees with a git-backed memory, a foreman CLI where every command takes --json, phone approvals and remote sandboxes.

Can I script Foreman or use it in CI?

Yes. The foreman command starts workspaces, sends messages, answers approvals, opens and merges pull requests and runs flows. Every command takes --json and exit codes are the same for every command.

Ship one upstream.

Foreman is three weeks old: 31 releases since 1.0.0 on 27 October, built in the open under Apache-2.0. Remote sandboxes are the newest crate on the yard. Star it to hear what lands next, fork it, or pick up a good first issue.