Skip to content
v1.2.4 · 31 releases since 1.0.0
Pick your agent

The Claude Code GUI for running agents in parallel

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 & WindowsApache-2.0No accountYour own agent logins

Four Foreman workspaces side by side in Tiles: a failed turn, a finished fix and two questions from AI employees waiting for an answer

Claude Codeatlas · lisbon · own worktree

Fix the login redirect and add a test for an expired token

foreman send atlas "Fix the login redirect and add a test for an expired token"
Tiles: four workspaces side by side, each its own agent session on its own branch.

The short answer

Is there a GUI for Claude Code?

Yes. Foreman is a free, open-source desktop GUI for Claude Code on macOS and Windows: it runs several Claude Code sessions in parallel, each in its own git worktree, and you review diffs, answer approvals and open pull requests from one window.

It isn't only for Claude Code. Every agent signs in with your own login or API key in Settings → Agents, and you can mix them in one repository.

Everything around the agent

What does Foreman add around Claude Code?

The parts a terminal session doesn't have: a worktree per session, a wall to watch them on, a review step, approvals that spell things out, loops that run until green, and a command line for the rest.

Watch them all at once

Run 8 Claude Code sessions side by side, each on its own branch. Step in where you're needed. Built and load-tested for 10 to 12 agents at once.

8
  • lisbonfix-login-redirectWorking
  • osakaadd-rate-limitWorking
  • kyotolaunch-2.4Needs you
  • limaflaky-session-testWorking
  • portocsv-exportWorking
  • oslodark-modeDone · +12 −3
  • quitoretry-webhooksWorking
  • hanoii18n-datesWorking

One worktree per agent

Every Claude Code session gets its own git worktree on its own branch. Agents never step on each other, and your main checkout stays clean.

mainclean
Aworktree · fix-login-redirectsrc/login.ts
Bworktree · add-rate-limitsrc/login.ts

Same file, different branches. Both changes land as reviewable diffs.

Approvals that spell it out

A command broken down part by part, with what leaves your computer marked.

Run it from anywhere

A live phone view for approvals away from your desk.

Review every change, rewind any turn

Read what Claude Code changed as a diff before you commit, push or open a pull request. Checkpoints let you rewind a workspace to any turn.

src/login.ts+2 −2

  password: string} - export async function login(credentials: Credentials) {-   return fetch('/api/login', { body: JSON.stringify(credentials) })+ export async function login(credentials: Credentials, returnTo = "/") {+   return fetch('/api/login', { body: JSON.stringify({ ...credentials, returnTo }) })}
  1. Turn 3
  2. Turn 4
  3. Turn 5 Restore

Flows that loop until green

Write a way of working down once: loops that run until the checks pass, and gates where you decide. 11 built-in flows to start from.

Flow steps run on Claude Code unattended: loops with bounds, and gates where you decide.

A flow's graph of steps, loops and a gate, with the assistant under it

A real command line

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

$ foreman approvals
kyoto  push      launch-2.4 → origin
               ▲ leaves this computer
lima   question  Which day is the launch?

$ echo $?
0
$ foreman approvals --json
[
  { "workspace": "kyoto",
    "kind": "push",
    "leavesComputer": true },
  { "workspace": "lima",
    "kind": "question" }
]

AI employees

A role in plain words, a hard hat and access you approve. 15 job templates to start from.

An organization's Team page: its employees, what each needs from you, and a memory change waiting for approval

Local-first. No account.

Foreman runs on your computer. Code leaves it only through the agents you choose.

  • No Foreman account
  • No cloud service
  • No telemetry upload
  • Claude Code uses your own login or key

Two Claude Code accounts, one window

Add a work account beside your personal one in Settings → Agents → Claude Code. Each keeps its own config folder (CLAUDE_CONFIG_DIR): login, settings, MCP servers and conversations.

  • PPersonal~/.claudedefault
  • WWorkCLAUDE_CONFIG_DIR=~/.claude-work

Remote sandboxes Experimental

A workspace can run in a remote sandbox on your own account.

  • Vercel Sandbox
  • Docker
  • E2B
  • Daytona

GitHub, GitLab, Linear, Slack, Langfuse

Pull requests, Linear issues and Slack posts, with anything outward-facing held for you.

  • GitHub
  • Linear
  • Slack

Mix and match

Can I run Claude Code and Codex at the same time?

Yes. Foreman runs Claude Code, Codex, Cursor and OpenCode side by side in the same repository, each in its own git worktree on its own branch, and each signed in with your own login or API key.

Save loadouts (an agent and its settings), then let a coordinator hand work between them: one researches, one plans, two implement in separate workspaces. Turn it on per repository in Repository settings → Actions.

  1. Loadout 1Claude CodeResearch
  2. Loadout 2CodexPlan
  3. Loadout 3OpenCodeImplement
  4. Loadout 4CursorImplement

Side by side

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. Foreman also drives OpenCode and any ACP agent, and adds flows, AI employees and a CLI with --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.

Three steps

Get started in a minute

  1. 01

    Download Foreman

    The .dmg for Apple Silicon or the Windows installer. No account, no Node.js.

  2. 02

    Add a git repo, sign in Claude Code

    Add a local repository, then sign in your agent in Settings → Agents with your own login or API key. Git must be on your PATH.

  3. 03

    Create workspaces

    One per task. Each is a git worktree on its own branch. Send a prompt and open Tiles.

Or from a terminalSettings → Advanced → foreman command

  • 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
  • foreman send atlas "also add a test for an expired token"# Follow up in the same workspace
  • foreman approvals# See what is waiting for you
  • foreman pr create atlas --draft# Open a draft pull request
  • foreman flow run fix-until-green --input task="make the tests pass" --wait# Loop until the checks pass

FAQ

Questions developers ask

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.

Bring your agent. Or bring a pull request.

Foreman is three weeks old, Apache-2.0 and built in the open, with 31 releases since 1.0.0. If your agent speaks ACP, it already runs. If something's missing, the code is right there.