Deal me in.
The best AI coding agent setup is a whole crew. Deal yours.
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
The job
Loadout for fix flaky tests
- DeveloperClaude CodeAgent · Anthropic
Writes the fix. Flow steps that change code run on Claude Code, the one agent Foreman runs unattended.
- ReviewerCodexAgent · OpenAI
Reads the diff read-only, inside its own sandbox. A flow’s review steps can run on Codex.
- Review personaqa-engineerFlow persona · reviewer
What the reviewer wears: it finds what breaks, never fixes it, and ends with findings.
- At the gateYouThe foreman · one of one
Quarantine the test, keep the fix, or send it back with a note. Nothing ships before you look.
Plays as the built-in flow flaky-test-triage. Flows are experimental and off by default: Settings → Experimental.
Run them side by side in Foreman, each in its own worktree.
Loadout for try one task three ways
- Workspace osakaClaude CodeAgent · Anthropic
Takes the prompt in a worktree of its own, on its own branch.
- Workspace lisbonCodexAgent · OpenAI
Same prompt, its own worktree and branch, so nothing collides.
- Workspace kyotoCursorAgent · Anysphere
Same prompt again, as an interactive pair. Foreman reviews what it does.
- The judgeYouThe foreman · one of one
Read the three diffs side by side in Tiles and keep the one you like. Nothing merges by itself.
No flow needed: three workspaces, one prompt.
Run them side by side in Foreman, each in its own worktree.
Loadout for security pass before a release
- DeveloperClaude CodeAgent · Anthropic
Builds, then fixes until the checks pass, round after round, within the loop’s bounds.
- First reviewqa-engineerFlow persona · reviewer
Reads the tree first: does the change do what was asked?
- Second reviewsecurity-reviewerFlow persona · reviewer
Reads the same tree for injection, secrets and unsafe defaults. Any finding goes back.
- 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.
Loadout for plan a whole feature
- Program managerPriyaEmployee · Program manager
Tag @Priya in Channels. She asks her questions first, then draws the plan as a workflow.
- Design partUmaEmployee · Staff UX designer
Specifies the screens and draws two HTML mock options for each design part.
- Build partRaviEmployee · Staff software engineer
Builds it with tests on its own branch, and opens a draft PR without waiting.
- Approves the planYouThe foreman · one of one
Nothing starts until you approve the plan. Slack posts and Linear changes wait for you.
Plays as a project in Channels, on Claude Code.
Priya runs the parts that don’t depend on each other side by side, in one shared workspace.
Agents · the crew board
Where does an agent card go to work?
To its own lane. Foreman gives every agent a git worktree on its own branch, so Claude Code, Codex, Cursor and OpenCode work one repository at the same time without stepping on each other's files.
- Built and load-tested for 10 to 12 agents at once
- Every lane ends as a diff you read before it ships
- Checkpoints rewind any turn, untracked files included

Tap a hat or a work order. Each agent gets its own lane: a git worktree on its own branch.
- 01osaka
Open lane · waiting for a hat
fix-login-redirectClaude Code+12 −3 · ready for review
- 02lisbon
Open lane · waiting for a hat
add-rate-limitCodex+10 −1 · ready for review
- 03kyoto
Open lane · waiting for a hat
write-testsCursor+48 −0 · ready for review
- 04lima
Open lane · waiting for a hat
update-docsOpenCode+6 −2 · ready for review
4 worktrees open · 4 signed off
Away from the desk? You still hold the gateAgents sharing a folder: none. Each agent works in its own git worktree.
Personas · the drafting desk
What does a persona card play as?
A step in a flow. A flow is a graph of agent steps with loops that stop on facts, like the checks passing or a review coming back clean, and gates where you decide. Personas say who does each step and what it may write.
- 11 built-in flows, 10 personas
- What a persona may write is enforced by Foreman, not the prompt
- Experimental and off by default: Settings → Experimental
Skip the plan, the developer builds, the checks run until green, at most 4 rounds, the QA engineer reviews until clean, and I approve before it ships.
Tap any underlined part to change it.
Who plans?
Who builds?
How many rounds may the checks take?
Who reviews?
Where do you step in?
Matches the built-in flow fix-until-green.
Ready · 4 rooms · 2 loops · 1 gate
.foreman/flows/fix-until-green.tomlSimplified for this page# .foreman/flows/fix-until-green.toml · simplified for this page
name = "Fix until green"
description = "Skip the plan, the developer builds, the checks run until green, at most 4 rounds, the QA engineer reviews until clean, and I approve before it ships."
[inputs]
task = "What to build or fix"
[start]
step = "implement"
[steps.implement]
kind = "turn" # code steps run on Claude Code
persona = "developer"
loadout = 1
prompt = "{{task}}"
[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.ship-check]
kind = "gate" # you: Continue, Send back or Stop
show = ["diff", "checks.results", "review.findings"]
ask = "Is this ready to ship?"
[edges]
implement = "checks"
checks = { passed = "review", failed = "fix" }
fix = "checks"
review = { clean = "ship-check", findings = "address" }
address = "checks"
ship-check = { continued = "done", sent-back = "address", stopped = "done" }
[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 }
[after]
workspace = "keep" # keep | archive | delete-unchanged- Project
- atlas
- Flow
fix-until-green- Drawn by
- the assistant
- Checked by
- you
- Revisions
- A first drawn
Scale: 1 step = 1 room · persona hats drawn for this page
Site log fix-login-redirect
- 00:08developer: moved the redirect after setSession() · +12 −3
- 00:45checks: ✕ auth/redirect.test.ts › keeps returnTo after sign-in
- 01:22developer (fix, same tab): kept returnTo on the refresh path · +4 −1
- 01:59checks: ✓ 214 tests · types · lint
- 02:36qa-engineer: clean, no findings
- 03:13ship-check: waiting for you · ready to ship?
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
Employees · the roster
Can you keep an AI employee on the team?
Yes. Hire from 15 job templates. Each employee gets a role in plain words, a hard hat and access you approve, works in a fresh workspace each run, and remembers through the organization's own git memory repository.
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 3
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.
Quinn
Staff QA engineer
Reviews what others build and says what breaks.
Ravi
Staff software engineer
Builds and fixes features, with tests, on its own branch.
Mei
Staff frontend engineer
Builds screens and components and keeps them accessible.
Omar
Staff security engineer
Reviews changes and dependencies for security risks.
Sofia
Staff site reliability engineer
Keeps builds, deploys and services healthy.
Kenji
Staff software architect
Shapes the system and reviews big changes before they start.
Uma
Staff UX designer
Reviews screens and flows, specifies what to build and draws it as mocks.
Leo
Staff web designer
Designs and builds marketing and content sites.
Nia
Staff product manager
Recommends what to build next and writes the requirements.
Dara
Staff data analyst
Answers questions with data and specifies dashboards.
Theo
Staff technical writer
Writes the docs and keeps them up to date.
Ines
Staff copywriter
Writes release notes, launch posts and site copy.
Sam
Staff SEO specialist
Audits the site for search and suggests fixes.
Ana
Staff marketing manager
Plans launches and the messages around them.
Jonah
Staff support engineer
Triages issues and traces what users report in the code.
Since 1.2.4 employees push and open draft pull requests without waiting; Slack posts and Linear changes are still held for you. Unattended runs use Claude Code.
You · the gate
Can you play your hand 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: directly on the same Wi‑Fi, and anywhere else over your own Tailscale network. There is no Foreman relay.
- WatchSees everything, changes nothing.
- OperateAnswers approvals, plans, questions and gates; steers and comments on diffs. Terminals are read-only.
- Full controlAlso settings, repositories and keys. Meant for a browser on another computer.
Native iPhone and Android apps are on the way.
- iOS appComing soon
- Android appComing soon
- Watch the repo for the release
Today: pair your phone with a QR code and add the phone view to your Home Screen.
lisbon · two-reviewers
Both reviews came back clean. Ship it?
Send backContinue
Same Wi‑Fi · Operate
Illustrative A flow waits at your gate. Nothing ships before you look.
The table
What else is on the table?
Four more cards: the tools your crew carries, sandboxes it can work off-site in, a night shift, and the real app as built. Play one to lay it down.
Play: Tool belt Card 1 of 4
Which tools can the crew carry?
GitHub, GitLab, Linear, Slack, Langfuse and MCP. Each connection gets the agent access you choose: nothing, read, or read and write.
- Slack is outbound only
- Langfuse is read-only
- Auto-fix answers failing CI, within a budget
- GitHub
- Linear
- Slack
- Langfuse
- MCP
- Sandboxes
- 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. Change a setting and the run below changes too.
Still on the board
Example run: ENG-123, start to finish
8 of 8 steps work with this belt. Missing tools grey out their steps.
Linear
Starts from ENG-123, “Login loops after sign-in”. The agent reads the issue and its comments.Starts from ENG-123. Foreman reads the issue in; the agent gets no Linear tools.Starts from ENG-123. The agent reads it and comments its plan on the issue.
foreman run issue ENG-123Hang Linear on the belt to start from an issue. Without it, you type the task.
Workspace
Workspace osaka: its own git worktree on
eng-123-login-loop.Workspace osaka runs in a E2B sandbox, oneng-123-login-loop. Provider keys stay on your computer.Workspace osaka runs in a Daytona sandbox, oneng-123-login-loop. Provider keys stay on your computer.Workspace osaka runs in a Vercel Sandbox sandbox, oneng-123-login-loop. Provider keys stay on your computer.Workspace osaka runs in a Docker sandbox, oneng-123-login-loop. Provider keys stay on your computer.Langfuse
Reads the trace of the failing
POST /login: the redirect fires before the session is saved.Hang Langfuse to let the agent read your app's traces.Langfuse access is Nothing, so no traces for this agent.
MCP
Checks itself with
foreman-app. Delegation is off, so it writes the regression test too.Hands “add a regression test” to lisbon withstart_task, then reads the reply.Hang MCP to see what an agent can do with Foreman's own tools.
Pull request
Pushes the branch and opens draft PR #42 on GitHub.Pushes the branch and opens draft MR !42 on your GitLab.
foreman pr create atlas --draftHang GitHub or GitLab to push and open the pull request.
CI
CI fails: Tests, 1 failing. Foreman saw it, so you don't have to refresh.The pipeline fails, and Foreman tells you.
Hang a code host to watch CI.
Back to green
Auto-fix is off: Home shows CI failed and you press Fix CI in…. Checks pass.Auto-fix sends the failing log to the tab: fix 1 of 2 for this commit. Checks pass.
Hang GitHub to watch CI and fix it.This demo draws the CI loop on GitHub. Hang the wrench to see it.
Slack
Drafts “PR #42 is ready for review” to @maya, the reviewer. It waits for your Send.Sends “PR #42 is ready for review” to @maya. The rule has your consent.The agent also posts the fix to #launches.
Hang Slack to tell the reviewer.Slack rules fire on pull request events. Hang a code host first.
Merging stays with you: press Merge, or foreman pr merge atlas --auto to merge when the checks pass. Linear’s own GitHub integration moves ENG-123 along. Illustrative run; the names are made up.
Play: Off-site Card 2 of 4
Can a card keep playing after you close the laptop?
Yes, as an experiment. A workspace can run in a sandbox on your own E2B, Daytona, Vercel Sandbox or Docker account, and its turn goes on after you quit, until it finishes or meets the provider's session limit.
- Provider keys never enter the sandbox
- Claude Code, Codex, OpenCode; not Cursor
- Needs a GitHub remote. Off by default
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
Cursor can’t run in a sandbox yet. Pick This computer, or Claude Code, Codex or OpenCode.
Codex needs an API key in a sandbox. ChatGPT sign-in is off there for now.
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.
Runs here, in a git worktree on this computer. Close the laptop and the agent stops with it.
Remote workspaces run on E2B. Experimental.
This computer
Vault
- Provider keystays here
- GitHub tokenstays here
- Agent sign-instays here
- Clone from GitHub The repository comes from its GitHub remote. GitHub’s token goes in as that one command’s environment.
- Install the agent host Foreman puts its small agent host in the sandbox, so the agent can run there without your computer.
- Set up The install script and the repository’s setup steps run, as they would in a local worktree.
- Run The agent takes the turn in the sandbox. Your computer only coordinates.
Session · not started
Turn · waiting to ship
- 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
Play: Night shift Card 3 of 4
Can the crew play while you sleep?
Yes, on Claude Code. Save a prompt as a template and Foreman runs it hourly, daily, weekly or monthly in your time zone, while Foreman runs: with a window, without one, or from login.
- A sleeping computer isn't woken
- A run 5 minutes late is skipped
- Seven templates ship
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 · your zone
- Runs on
- Claude Code, a Sonnet by default
- Max
- 5 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/LondonThe CLI has no flag for AFTER: set it in the app's Schedule dialog.
Runs on Claude Code while Foreman is running.
Play: As built Card 4 of 4
What does a flow look like in the real app?
Like this: the real flow studio, with a built-in flow's steps, loops and gate drawn as a graph and the assistant under it. Click the stamp; hover the crew.
The 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.
Other tables
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
| Feature | Foreman | Conductor | T3 Code |
|---|---|---|---|
| Open source | Apache-2.0 | No | MIT |
| macOS | Yes | Yes | Yes |
| Windows | Yes | Mac only | Yes |
| One git worktree per agent | Yes | Yes | Yes |
| Agents | Claude Code, Codex, Cursor, OpenCode, any ACP agent | Claude Code, Codex, Cursor | Claude Code, Codex and more |
| Flows that loop until checks pass, with human gates | Yes | — | — |
| AI employees with git-backed memory | Yes | — | — |
| Scheduled automations and auto-fix CI | Yes | — | — |
| Your own cloud sandboxes (E2B, Daytona, Vercel, Docker) | Experimental | — | — |
| Scriptable CLI, --json on every command | Yes | — | — |
| Approve from your phone | Yes | — | Yes |
| No account, no telemetry upload | Yes | — | — |
Cut, deal, play
Get started in a minute
Download the app, point it at a git repository, and give each task its own workspace.
Download Foreman
Free for macOS (Apple Silicon, signed and notarized) and Windows. You need Git on your PATH.
Download ForemanAdd a repo, sign in an agent
Any git repository. Sign in Claude Code, Codex, Cursor or OpenCode in Settings → Agents, with your own login or key.
Create workspaces
One per task, each a fresh worktree on its own branch. Deal the hand, then read every diff before it ships.
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
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.
Pull up a chair. The game is open source.
Foreman is three weeks old: 31 releases since 1.0.0 on 27 October, built in the open under Apache-2.0. Star it to hear about the next one, fork it, or pick up a good first issue and take a seat at the table.