Skip to content

You're the foreman now.

Run multiple AI coding agents without a pile‑up.

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.

  • macOS & Windows
  • Apache-2.0
  • No account
  • v1.2.4

Site board · repo atlas

Assign the crew

Tap a hat or a work order. Each agent gets its own lane: a git worktree on its own branch.

Work orders
  1. 01osaka

    Open lane · waiting for a hat

    fix-login-redirectClaude Code

    +12 −3 · ready for review

  2. 02lisbon

    Open lane · waiting for a hat

    add-rate-limitCodex

    +10 −1 · ready for review

  3. 03kyoto

    Open lane · waiting for a hat

    write-testsCursor

    +48 −0 · ready for review

  4. 04lima

    Open lane · waiting for a hat

    update-docsOpenCode

    +6 −2 · ready for review

4 worktrees open · 4 signed off

Off site? Answer the crew from your phone

Agents that stepped on each other today: zero

The crew

Which coding agents can join the crew?

Foreman runs Claude Code, Codex, Cursor and OpenCode, plus any agent that speaks the Agent Client Protocol. Each one signs in with your own subscription or API key, and each wears its own hat.

  • Claude CodeAnthropic
  • CodexOpenAI
  • CursorAnysphere
  • OpenCodeSST
  • Any ACP agentAgent Client Protocol

Blueprint

How do you run multiple AI coding agents at once?

Give each agent its own workspace. In Foreman a workspace is a git worktree on its own branch, so several agents edit the same repository at the same time without touching each other's files, and Tiles shows them side by side.

Four Foreman workspaces side by side in Tiles: a failed turn, a finished fix and two questions from AI employees waiting for an answer
On site Four workspaces in Tiles: one failed and needs a look, two have questions, one is done.
  1. One repo, four branches

    fix-login-redirectadd-rate-limitwrite-testsupdate-docsmain
  2. Watch them all at once

    Tiles shows several workspaces side by side so you can step in where you are needed. Built for 10 to 12 agents running at once.

  3. Why does every agent need its own worktree?

    A git worktree is a second checkout of the same repository on a different branch. With one each, agents never overwrite each other's files, every change lands on a branch you can review, and your main checkout stays untouched.

The night shift

Can the crew work the night shift?

Yes. Save a prompt as a template and Foreman runs it hourly, daily, weekly or monthly in your time zone, each run in a fresh worktree on Claude Code. Opt in, and failing CI goes back to your agent and a read-only reviewer reads each finished diff.

Shift board · repo atlas

Put nightly-triage on nights

Tonight at 02:00, and every night after.

Each run: a fresh worktree, Claude Code, stopped after 30 minutes. By breakfast it's a workspace with a diff, waiting to be signed off.

foreman schedules add nightly-triage --repo atlas --every daily --at 02:00

Runs while Foreman runs: with no window, or from login. A sleeping computer isn't woken, and a run more than 5 minutes late is skipped.

7 built-in templates, ready to run

  • Explain code
  • Fix a bug
  • Fix an issue
  • Write tests
  • Refactor
  • Review my changes
  • Set up this repo

Run one now, or schedule your own saved prompt. A template with blanks can't run at night: nobody's there to fill them in.

The Automations library of templates and commands, with schedules beside it
Automations Templates in the middle, schedules on the right.
  • Opt-in · per PR

    Auto-fix CI, on a budget

    When CI fails on a watched pull request, Foreman sends the failing log to the tab you picked: two fixes per commit, five per PR. It stops instead of looping.

    Failing CI only

  • Opt-in · per repo

    Auto-review, read-only

    When a turn ends and the workspace goes quiet, a read-only reviewer, Claude Code or Codex, reads the diff once. Its findings reach the agent only when you click.

    Six reviews a day

  • Experimental

    Flows that loop until green

    1. implement
    2. checks
    3. fix ↺
    4. review
    5. gate: you

    Fix until green: implement, run the checks, fix what fails, review, then stop at a gate where you decide whether it ships. Every loop has a limit.

    11 built-in flows

Site radio

Can you run the site from your phone?

Yes. Pair a phone with a QR code to answer approvals, plans and flow gates, steer agents and comment on diffs, live. On the same Wi‑Fi it connects directly, and anywhere else over your own Tailscale network.

  • WatchSees everything, changes nothing.
  • OperateDefaultAnswers approvals, plans, questions and gates. Steers, comments on diffs, reads terminals; typing stays on the computer.
  • Full controlAlso settings, repositories and keys. Meant for a browser at /app.
Same Wi‑Fi
Straight to your computer.
Away
Over your own Tailscale network, with tailscale serve. No Foreman relay.
Another computer
The whole app in a browser at /app.
No window
Run headless, or at login with foreman service install.

ForemanNeeds you · 1

lisbon · Claude Code

Plan ready: rate-limit the login

  1. Add a limiter to /api/login
  2. Answer 429 with Retry-After
  3. Test the sixth try in a minute

Same Wi‑Fi · Operate

02lisbon

add-rate-limit

waiting for you: plan

Illustrative Tap Approve on the phone and watch lane 02 on your desk.

Native apps for iPhone and Android are on the way.

Today: pair your phone with a QR code and add the phone view to your Home Screen.

Off-site crews Experimental

Can the crew work off-site, in a cloud sandbox?

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. Provider keys stay on your computer and never enter the sandbox.

  • Trailer 01

    E2B

    Hosted

    1-hour sessions on Hobby2, 4 or 8 vCPUs

  • Trailer 02

    Daytona

    Hosted

    24-hour sessions1, 2 or 4 vCPUs

  • Trailer 03

    Vercel Sandbox

    Hosted

    45-minute sessions on Hobby2, 4 or 8 vCPUs

  • Trailer 04

    Docker

    This computer, or another over SSH

    No session limit1 to 8 vCPUs

  • Off twice by default: once in Settings, once per repository.
  • Claude Code, Codex and OpenCode go off-site; Cursor stays home. The repository needs a GitHub remote.
  • Quit Foreman and the turn keeps going until it finishes or meets the provider's session limit.

What's on the tool belt?

GitHub, GitLab, Linear, Slack, Langfuse and MCP. Each connection gets the agent access you choose: nothing, read, or read and write.

  • GitHubOpen, merge and auto-merge PRs. Watch CI and reviews.
  • GitLabMerge requests and issues, self-managed hosts too.
  • LinearStart a workspace from an issue.
  • SlackNotifications and posts. Outbound only.
  • LangfuseAgents read traces. Read only.
  • MCPA foreman-app server for every agent.

Site rules

What are the rules on a Foreman site?

Four rules hold on every Foreman site: your code stays on your computer, approvals spell out anything that leaves it, every change is read as a diff, and every agent works in its own worktree.

  • Prohibited

    No account. No telemetry upload.

    Local-first. No account.

    Foreman runs on your computer. There is no Foreman account, no cloud service and no telemetry upload. Agents use your own logins and API keys.

  • Caution

    See what leaves your computer.

    Approvals that spell it out

    An approval breaks a command down part by part, marks anything that leaves your computer, and says exactly what Always allow adds.

  • Mandatory

    Read the diff before it ships.

    Review every change

    Read each change as a diff before you commit, push or open a pull request. Checkpoints let you rewind a workspace to any turn.

  • Safe condition

    Every agent gets its own lane.

    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.

Inspection

Nothing ships until you've looked.

Every workspace keeps its changes on the right: file by file, as a diff, against main. Commit, push or open a pull request when you're happy. Checkpoints rewind a workspace to any turn when you're not.

▲ Leaves this computer is how an approval marks a push, a pull request or a Slack post. You see the whole command, part by part, before you say yes.

A Foreman workspace: the agent's chat in the middle and its changes on the right
Inspection The agent's chat in the middle, its three changed files on the right.

On the truck

What else can the crew do?

Take on standing hires: AI employees with a role, a hard hat and a git-backed memory, who start on a schedule or an event. And almost everything in the window works from a terminal too.

Job 01 · Hiring

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.

15 job templates12 hat coloursgit-backed memory

Job 02 · A real command line

Every command takes --json, and exit codes are the same for every command.

foreman approvals
foreman pr create atlas --draft
An organization's Team page: its employees, what each needs from you, and a memory change waiting for approval
Team Each employee, what they need from you, and a memory change waiting for approval.

Other sites

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. Next to T3 Code, Foreman adds flows that loop until checks pass, AI employees with git-backed memory 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.

Induction

Get started in a minute

Download the app, point it at a git repository, and give each task its own workspace.

  1. Download Foreman

    Free for macOS (Apple Silicon, signed and notarized) 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 is a fresh worktree on its own branch. Watch them in Tiles, then review and open the PR.

Prefer a terminal? Same thing, one line.
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. CLI reference

Toolbox talk

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.

Twelve hats. One of them is yours.

Foreman is three weeks old and has shipped 31 releases since 1.0.0 on 27 October. It's built in the open under Apache-2.0. Star it so you hear about the next one, fork it, or pick up a first issue and join the crew.