Skip to content

Run multiple AI coding agents on one well‑run site.

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.

  • Apache-2.0
  • No account
  • No telemetry
Four Foreman workspaces side by side in Tiles: a failed turn, a finished fix and two questions from AI employees waiting for an answer
Real appTiles: four workspaces in one window, each its own worktree and branch. Tap a hat to find its lane.

Site induction

How does Foreman work?

Add a git repository, then give each task a workspace: a new branch in its own git worktree, where an agent works without touching the others. Review the diff and open the pull request. For a team, make an organization and hire AI employees.

  1. Open a folder on your computer, clone one from GitHub or start a new project. Foreman remembers where it lives and writes nothing into it.

  2. Every task gets a workspace: a new branch in its own git worktree, with its own ports and terminal, so agents never collide.

  3. Start as many workspaces as you like with Claude Code, Codex, Cursor or OpenCode, then read each change as a diff and open the pull request.

  4. An organization is a space with its own repositories, AI employees and memory. Personal stays as it is.

  5. An AI employee is a standing member of an organization: a name, a role, a hard hat, instructions, memory and the access you approve.

An organization is a space with its own repositories, AI employees and memory. Personal stays as it is.

01Crew: Parallel agents

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 once without touching each other's files. Their changes still go through your review, and you merge.

  • Built for 10–12 at once
  • 1 worktree and branch each
  • 0 edits to your main checkout

Interactive demo · sample tasks

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

Away from the desk? Answer from your phone

Agents sharing a folder: none. Each agent works in its own git worktree.

02Team: AI employees

Can AI coding agents work as a team?

Yes: hire AI employees. Each one has a role in plain words, a hard hat and access you approve. They work in fresh workspaces, hand parts to each other, and remember through a private git repository with one commit per run.

Fifteen job templates · Priya, the built-in program manager, plans projects you tag her in

Open roles 15

Engineering

Design

Product

Data

Writing

Marketing

Customers

Hat rule A hat says who, never state. If a job's colour is taken, the new hire wears the least-worn colour instead.

Slack posts and Linear changes start held for you. Since v1.2.4 an employee pushes and opens draft pull requests on its own; this switch is the one-line rule that holds those too.

Your team 7

  • You

    The person · one of the team

    Approve each plan and each hire, and anything you've asked the team to hold.

  • Priya Lead

    Program manager

    Plans every project, proposes who it needs, reviews each part and accepts the result.

    Starts
    When you @Priya
    Access
    Writes project filesNo shellSlack · held
  • Ravi

    Staff software engineer

    Builds and fixes features, with tests, on its own branch.

    Starts
    When you askWhen assigned in Linear
    Access
    Write · atlasNo shellPush & PR · heldSlack & Linear · held
  • Uma

    Staff UX designer

    Reviews screens and flows, specifies what to build and draws it as mocks.

    Starts
    When you askWhen review is requested
    Access
    Write · atlasNo shellPush & PR · heldSlack & Linear · held
  • Quinn

    Staff QA engineer

    Reviews what others build and says what breaks.

    Starts
    When you askWhen review is requested
    Access
    Write · atlasNo shellPush & PR · heldSlack & Linear · held
  • Sofia

    Staff site reliability engineer

    Keeps builds, deploys and services healthy.

    Starts
    When you askWhen CI fails on a PR
    Access
    Write · atlasNo shellPush & PR · heldSlack & Linear · held
  • Theo

    Staff technical writer

    Writes the docs and keeps them up to date.

    Starts
    When you askWhen a PR merges
    Access
    Write · atlasNo shellPush & PR · heldSlack & Linear · held

03Shift: Automations

Can coding agents run on a schedule overnight?

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. Schedules run whenever Foreman is running, even with no window open.

Unattended runs (schedules, AI employees, flow steps that write code) use Claude Code · a sleeping computer isn't woken · a run more than 5 minutes late is skipped

The seven templates that ship 7

Saved prompts yours · blanks written out

Blanks fill in order: foreman run fix-a-bug "the login page loops". A scheduled run can't stop to ask, so only templates without {{blanks}} go on a schedule. Repository templates live in.foreman/templates and travel with the code.

Schedule slipNo. 0042

nightly-triage on atlas

Every
in Europe/London
Runs on
Claude Code, a Sonnet by default
Max
30 minutes5 to 480
After
Approved
its text, the repo's setup, checks and MCP servers

Runs every day at 00:30 (Europe/London) · stops after 30 minutes · keeps the workspace

foreman schedules add nightly-triage --repo atlas --every daily --at 00:30 --tz Europe/London

  • Auto-fix CI, on a budget

    Opt in, and a failing CI log goes back to your agent: two fixes per commit, five per PR. Failing CI only, not review comments.

  • Auto-review, read-only

    Opt in per repository, and a read-only reviewer reads each finished diff. Its findings reach the agent when you click.

04Tools: Integrations

Which tools and integrations can the agents use?

GitHub, GitLab, Linear, Slack, Langfuse and MCP, plus your own sandboxes. Each connection gets the agent access you choose: nothing, read, or read and write. Slack is outbound only and Langfuse is read-only.

  1. GitHub
  2. Linear
  3. Slack
  4. Langfuse
  5. MCP
  6. Sandboxes
  7. GitLab

Connections belong to the repository, so every new workspace in atlas starts with this belt.

7 of 7 tools on the belt

The tags on the belt

Each tool's tag says what the agent can do with it and what stays held for you.

  • Wrench · gh or a token

    GitHub

    Auto-fix CI

    Commit, push and open draft PRs. Merge, or auto-merge when checks pass. Watch CI and reviews. Start from an issue or PR link. Open PRs in GitHub or Graphite.

    A failing CI run waits on Home with Fix CI in… for you to press.

    Auto-fix sends the failing log to the tab you picked: 2 fixes a commit, 5 a PR. Never for review comments.

    Agents in repositories that use it get GH_TOKEN. Turn approvals on to see each push first.

  • Level · an API key

    Linear

    What agents may do

    Agents get no Linear tools. Foreman still reads issues for New workspace.

    Agents can search and read issues, projects and comments.

    Agents can also create and update issues and comment.

    Nothing goes to Linear from an agent.

    They can't create, edit or comment.

    Issue text is written by others, so treat this like any tool that changes things.

    Foreman doesn't change issue status itself.

  • Megaphone · a bot token

    Slack

    What agents may do
    Rule: PR ready → message the reviewer

    Foreman sends your notification rules. Agents can't post.

    Agents may also post to #launches, the channel you allowed.

    Messages to anyone but you wait for your Send.

    This rule has your consent; change any part of it and it asks again.

    Outbound only. Never pings @here or @channel.

  • Magnifier · a key pair

    Langfuse

    What agents may do

    Agents get no Langfuse tools.

    Agents get search_observations, get_trace and get_observation.

    They can't change anything in Langfuse.

    Langfuse Cloud EU, US or HIPAA, or your own host over HTTPS.

  • Power strip · built in

    MCP

    Let agents start workspaces

    Every workspace agent gets foreman-app: its status, its checks, a preview, its own chat history.

    No agent can start a workspace or queue a message.

    Agents can hand tasks to other workspaces in atlas and read the replies. Other repositories are refused.

    MCP servers a repository proposes start only after you approve them.

  • Toolbox · experimental

    Sandboxes

    Where the workspace runs

    E2B · Hosted · 1-hour sessions on Hobby · 2, 4 or 8 vCPUs.

    Daytona · Hosted · 24-hour sessions · 1, 2 or 4 vCPUs.

    Vercel Sandbox · Hosted · 45-minute sessions on Hobby · 2, 4 or 8 vCPUs.

    Docker · This computer, or another over SSH · No session limit · 1 to 8 vCPUs.

    Off by default. Provider keys never enter the sandbox. Needs a GitHub remote. Claude Code, Codex and OpenCode, not Cursor.

    Turns keep going after you quit, up to the provider's session limit.

  • Pliers · an access token

    GitLab

    gitlab.com or self-managed

    Merge requests and issue links work like GitHub's, on your own GitLab host.

    Fewer events: employee triggers don't see failed pipelines, approvals or requested changes.

    foreman gitlab add https://gitlab.example.com

05Off-site: Cloud sandboxes. Experimental · off by default

Can agents keep working after you close the laptop?

Yes, in a sandbox on your own E2B, Daytona, Vercel Sandbox or Docker account. Turns keep going after Foreman quits, until they finish or reach the provider's session limit, and provider keys never enter the sandbox.

Needs a GitHub remote · Claude Code, Codex and OpenCode; Cursor stays home

New workspace · atlas

Workspace

Runs on

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

Your Claude subscription sign-in stays on this computer. In a sandbox Claude uses a setup token from claude setup-token, or an API key.

On E2B a session ends after 60 minutes. Foreman continues the turn when you’re around; with Foreman closed, the agent stops at the limit and the workspace sleeps.

Remote workspaces run on E2B. Experimental.

This computer

Foreman · atlasZzz

Vault

  • Provider keystays here
  • GitHub tokenstays here
  • Agent sign-instays here
Property line · provider keys stop 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

06Plans: Flows. Experimental · off by default

How do you make agents loop until the tests pass?

Draw it as a flow: a graph of agent steps with loops that run until the checks pass or a review comes back clean, and gates where you decide. Foreman ships 11 built-in flows, and every loop has a limit.

research-then-implement · 7 steps · 2 loops · 1 gate
A flow's graph of steps, loops and a gate, with the assistant under itThe drawing's stamp. Press to stamp it again.
  • I plan the change. I never touch the files.
  • I build it, then fix it until the checks pass.
  • I find problems. Fixing them isn't my job.
  • Nothing ships until I open the gate.
Fig. 1The real flow studio: a built-in flow's steps, loops and gate, with the assistant under it.
Start from a built-in flow

⁠, ⁠, ⁠, ⁠, ⁠.

Tap any underlined part to change it.

A flow of your own. Closest built-in: research-then-implement. Ask the assistant and it drafts this file for you.

Ready · 7 rooms · 3 loops · 1 gate

IN · {{task}}OUT · done01planarchitect · read-onlyTURN · CLAUDE CODE02implementdeveloper · edits the worktreeTURN · CLAUDE CODE03checksnpm test · tsc · lintCHECKS · NO AGENT04reviewqa-engineer · read-onlyREVIEW · CLAUDE OR CODEX05pr-checkyou · open a draft PR?GATE · YOU06prdraft · Foreman pushes and opens itPR · NO AGENT07ciwaits for CI: green or failedWAIT · ON = "CI"≤ 4 roundson failed · 45 min≤ 2 roundson findings≤ 2 roundson failed CIsent backJOB
IN · {{task}}OUT · done01planarchitectTURN · CLAUDE CODE02implementdeveloperTURN · CLAUDE CODE03checksnpm test · lintCHECKS · NO AGENT04reviewqa-engineerREVIEW · CLAUDE OR CODEX05pr-checkyou decideGATE · YOU06prdraft · no agentPR · NO AGENT07ciwaits for CIWAIT · ON = "CI"≤ 4 roundson failed≤ 2 roundson findings≤ 2 roundson failed CIsent backJOB
.foreman/flows/my-blueprint.tomlSimplified for this page
# .foreman/flows/my-blueprint.toml · simplified for this page
name = "My blueprint"
description = "The architect plans, the developer builds, the checks run until green, at most 4 rounds, the QA engineer reviews until clean, and I approve before a draft PR."

[inputs]
task = "The issue to resolve: its link or its words"

[start]
step = "plan"

[steps.plan]
kind = "turn"
persona = "architect"          # read-only: plans, never edits
prompt = "Research how to do this and write a plan. Don't change any files yet. {{task}}"
context = ["task", "tree"]

[steps.implement]
kind = "turn"                  # code steps run on Claude Code
persona = "developer"
loadout = 1
prompt = "Implement the plan."
context = ["plan.answer"]

[steps.checks]
kind = "checks"                # the repo's approved check commands, never an agent

[steps.fix]
kind = "turn"
same_tab = "implement"
prompt = "Address what failed or what you were sent back for, and run the checks again."
context = ["checks.results"]

[steps.review]
kind = "review"                # read-only: Claude Code or Codex
persona = "qa-engineer"
                               # its default loadout 3 is Codex
context = ["diff"]

[steps.address]
kind = "turn"
same_tab = "implement"
context = ["review.findings"]

[steps.pr-check]
kind = "gate"                  # you: Continue, Send back or Stop
show = ["diff", "checks.results", "review.findings"]
ask = "Open a draft PR?"

[steps.pr]
kind = "pr"                    # Foreman pushes and opens it, no agent
draft = true
body = "{{ledger}}"

[steps.ci]
kind = "wait"
on = "ci"

[steps.fix-ci]
kind = "turn"
same_tab = "implement"
prompt = "CI failed on the pull request. Fix it, commit and push."

[edges]
plan      = "implement"
implement = "checks"
checks    = { passed = "review", failed = "fix" }
fix       = "checks"
review    = { clean = "pr-check", findings = "address" }
address   = "checks"
pr-check  = { continued = "pr", sent-back = "address", stopped = "done" }
pr        = { opened = "ci" }
ci        = { green = "done", none = "done", failed = "fix-ci" }
fix-ci    = "ci"

[loops.fix-until-green]
over = ["checks", "fix"]
at_most = { iterations = 4, minutes = 45 }
iteration = "same-tab"         # or "compact-when-full" or "fresh-with-summary"

[loops.review-until-clean]
over = ["review", "address", "checks"]
at_most = { iterations = 2 }

[loops.ci-until-green]
over = ["ci", "fix-ci"]
at_most = { iterations = 2 }

[after]
workspace = "keep"             # keep | archive | delete-unchanged
Project
atlas
Flow
my-blueprint
Drawn by
the assistant
Checked by
you
Revisions
  1. A first drawn

Scale: 1 step = 1 room · persona hats drawn for this page

Site log fix-login-redirect

  1. 00:08architect: a 3-step plan · the cookie is set after the redirect in src/auth/session.ts
  2. 00:45developer: moved the redirect after setSession() · +12 −3
  3. 01:22checks: ✕ auth/redirect.test.ts › keeps returnTo after sign-in
  4. 01:59developer (fix, same tab): kept returnTo on the refresh path · +4 −1
  5. 02:36checks: ✓ 214 tests · types · lint
  6. 03:13qa-engineer: clean, no findings
  7. 03:50pr-check: waiting for you · open a draft PR?

Illustrative run of the sentence above. In Foreman the Flow tab draws it live and the gate waits in Needs you. Flows are experimental: turn them on in Settings → Experimental → Flows.

Legend

  • A room is a step: a turn, checks, a review, a gate or a PR
  • A loop, with its bound and the fact that sends it round
  • Sent back from your gate, with your note
  • Your gate is a door: nothing passes until you open it
  • The job, walking from room to room on a run

07Loadout: Pick your agents

Which agent should you send for which job?

Claude Code writes the code. A second model reviews it read-only, and you keep the gate. Pick a job and the dealer hands out the crew, with the built-in flow it plays as.

The job

Loadout for security pass before a release

  1. DeveloperClaude CodeAgent · Anthropic

    Builds, then fixes until the checks pass, round after round, within the loop’s bounds.

  2. First reviewqa-engineerFlow persona · reviewer

    Reads the tree first: does the change do what was asked?

  3. Second reviewsecurity-reviewerFlow persona · reviewer

    Reads the same tree for injection, secrets and unsafe defaults. Any finding goes back.

  4. At the gateYouThe foreman · one of one

    Both reviews come back clean, then you look. Nothing leaves before that.

Plays as the built-in flow two-reviewers. Flows are experimental and off by default: Settings → Experimental.

Run them side by side in Foreman, each in its own worktree.

Phone: Remote control

Can you run Foreman 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; anywhere else, over your own Tailscale network. There is no Foreman relay.

  • WatchSees everything, changes nothing.
  • OperateDefaultAnswers approvals, plans, questions and flow gates. Steers, comments on diffs, reads terminals.
  • Full controlAlso settings, repositories and keys. Meant for a browser at /app.

A browser on another computer opens the whole app at /app. Run Foreman with no window, or from login with foreman service install. The phone reads terminals but can't type into them.

Native iPhone and Android apps are on the way.

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

ForemanNeeds you · 1

  • lisbon · Codex

    Plan ready: rate-limit the login

    1. Add a limiter to /api/login
    2. Answer 429 with Retry-After

Same Wi‑Fi · Operate

Illustrative Finish a lane on the board at station 01, or run the flow at station 06 to its gate, and the card lands here.

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 a fresh worktree on its own branch. Watch them in Tiles, review the diff, open the PR.

Prefer a terminal? Every command takes --json.
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 approvals
# See what is waiting for you

CLI reference · exit codes are the same for every command

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.

The site is open source. Pick up a shovel.

31 releases since 1.0.0 on 27 October, and every station on this page is code you can read under Apache-2.0. Star it to bookmark Foreman, watch releases for updates, fork it, or take a first issue and join the crew.