Skip to content

Your agents.
Your machine.
Your code.
The open-source Conductor alternative.

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 No telemetry upload

A file diff with the list of changed files
Plate I. Every change is a diff you read before you commit, push or open a pull request. Nothing here left the machine.

§ 1 Principles

Why should the tools that run your agents be open?

Because they hold your code, your keys and the decision to ship. A tool with that much reach should run on your machine, answer to you, and let you read every line of it.

Six principles follow. Each one comes with a receipt.

Principle I: Local-first

Your computer is the server.

Foreman runs on your computer, and so does your work: every workspace is a git worktree on your own disk, on its own branch. There is no Foreman cloud service for any of it to depend on.2

Show meHide the receipt

Receipt I

Plain git. Every workspace shows up in your repository’s own worktree list:

$ cd ~/code/atlas
$ git worktree list
~/code/atlas    a1c93e2 [main]
…/atlas/osaka   7f02b1d [fix-login-redirect]
…/atlas/lisbon  c44e0a9 [add-rate-limit]

Output is illustrative; your branches will differ.

Principle II: No account

Nothing to sign up for.

You download the app, open it and add a repository. No email, no trial, no seats. And no telemetry upload: what happens in Foreman stays on your machine.1

Show meHide the receipt

Receipt II

Foreman account
None
Foreman cloud service
None
Telemetry upload
None
Paid tier
None
Price
$0

Principle III: Open source

Apache-2.0. Every line.

The full source is on GitHub under Apache-2.0. Read how it works, change what you don’t like, and ship your own build if you want to. The license says you can.

Show meHide the receipt

Receipt III

Clone it and run the demo build:

$ git clone https://github.com/elite-build/foreman
$ cd foreman
$ npm install && npm run dev demo

Principle IV: Your keys

Your subscription, your API key, your bill.

Each agent signs in with your own login or API key with its provider. Foreman doesn’t resell model access or sit in the middle of it: your agents talk to their own model providers.1

Show meHide the receipt

Receipt IV

Where Settings Agents

  • Claude CodeAnthropicyour login or key
  • CodexOpenAIyour login or key
  • CursorAnysphereyour login or key
  • OpenCodeSSTyour login or key

Principle V: Approval before anything leaves

You see what leaves, before it leaves.

An approval breaks a command down part by part, marks anything that leaves your computer, and says exactly what Always allow adds. For AI employees, you decide what they may do on their own: Slack posts and Linear changes are held for you by default.

Show meHide the receipt

Receipt V

As it appears in the app, word for word:

Needs you · Max · Push

Push max/launch-2.4 to site

▲ Leaves this computer Pushes 1 commit of max/launch-2.4 to origin (github.com/acme/site) as @yatin. It leaves this computer and can’t be undone.

Principle VI: Bring any agent

No favourite model maker.

Claude Code, Codex, Cursor and OpenCode today, and any agent that speaks the Agent Client Protocol. Run them side by side, each in its own worktree. Your way of working doesn’t belong to one vendor.

Show meHide the receipt

Receipt VI

  • Claude CodeAnthropic
  • CodexOpenAI
  • CursorAnysphere
  • OpenCodeSST
  • Any ACP agentAgent Client Protocol
  1. Your agents do talk to their own model providers: that is how they work. Foreman adds no account and no upload of its own. ↩
  2. Run a workspace's worktree and agent in a sandbox on your own E2B, Daytona, Vercel Sandbox or Docker account. Provider keys never enter the sandbox, and turns keep going after you close the app. Experimental. That’s a choice you make per workspace, on your own account. ↩

§ 2 Side by side

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.

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.

We like both. The table says only what each project’s own site says, as of November 2026. Rows the other site doesn’t mention are marked “—”, which means not listed, not missing.

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.
An organization's Team page: its employees, what each needs from you, and a memory change waiting for approval
Plate II. An organization’s Team page. A push and a memory change wait for a yes; nothing was decided for you.

§ 3 The fine print

What does “open” mean here?

The license, the source, the build and the releases are all public. You can read it, build it, check what you downloaded, and leave with your fork any time.

License
Apache-2.0, with a NOTICE file. LICENSE · NOTICE
Source
Every line, on GitHub at github.com/elite-build/foreman.
Build it yourself
npm install && npm run dev demo
Releases
Built by GitHub Actions, in the open. Latest release
macOS
Apple Silicon. Signed and notarized.
Checksums
Each release ships a SHA256SUMS file. Check yours: shasum -a 256 -c SHA256SUMS
Account & telemetry
No account. No telemetry upload. docs/telemetry.md
Cadence
31 releases since 1.0.0 on . Changelog

§ 4 Get started

Get started in a minute

  1. Download Foreman. For macOS (Apple Silicon) or Windows. You need Git on your PATH.
  2. Add a git repo and sign in an agent. Claude Code, Codex, Cursor or OpenCode, with your own login or API key, in Settings → Agents.
  3. Create workspaces. One per task, each a fresh worktree on its own branch. Review the diffs when they’re done.
Or from a terminal
# Start a workspace from a template and wait for the turn
$ foreman run fix-a-bug "the login page loops after sign-in" --repo atlas --wait
# Follow up in the same workspace
$ foreman send atlas "also add a test for an expired token"
# Open a draft pull request
$ foreman pr create atlas --draft
Every foreman command takes --json. CLI reference

§ 5 Letters

Questions developers ask

Ask yours in the issues. Answers land in the docs.

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.

§ 6 Your move

Read the source. Fork it. Ship it.

Foreman is three weeks old and built in the open. The best time to shape it is now: star it to follow along, fork it to make it yours, and pick a good first issue for your first pull request.