Add passkey sign-in to atlas
About a minute. Touch anything and it stops; you take over.
Scroll down: each chapter is something you can try.
ENG-142 One project, start to ship
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.
About a minute. Touch anything and it stops; you take over.
Scroll down: each chapter is something you can try.
The route
In Foreman it takes seven moves: draw the way of working as a flow, staff it, give the agents the Linear issue, build each part in its own git worktree, send the slow tests to a sandbox, put upkeep on a schedule, and have reviewers read the result before a draft pull request opens.
This page follows one made-up issue, ENG-142, through all seven. Every module below is live. Use them in order and the docket fills in; skip around and it still keeps count.
The drawing's stamp. Press to stamp it again.01 Draw it Experimental
Draw it as a flow: a graph of agent steps with loops that run until the checks pass and a gate where you decide. issue-to-draft-pr is one of 11 flows that ship with Foreman: it resolves the issue until the checks pass and QA is clean, waits for you, then opens a draft PR itself.
Try it: tap an underlined word to redraw the plan, or press Run it and answer the gate.
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 a draft PR.
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 issue-to-draft-pr.
Ready · 6 rooms · 3 loops · 1 gate
.foreman/flows/issue-to-draft-pr.tomlSimplified for this page# .foreman/flows/issue-to-draft-pr.toml · simplified for this page
name = "Issue to draft pull request"
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 a draft PR."
[inputs]
task = "The issue to resolve: its link or its words"
[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.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]
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-unchangedissue-to-draft-prScale: 1 step = 1 room · persona hats drawn for this page
Site log fix-login-redirect
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
02 Staff it
Hire from the fifteen job templates Foreman ships. Ravi builds and Uma specs the screens; sign-in code also wants a QA engineer and a security engineer, and whoever you hire here shows up at the review in chapter 7.
Try it: hire Quinn (QA engineer) and Omar (security engineer) from Open roles.
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.
The person · one of the team
Approve each plan and each hire, and anything you've asked the team to hold.
Program manager
Plans every project, proposes who it needs, reviews each part and accepts the result.
Staff software engineer
Builds and fixes features, with tests, on its own branch.
Staff UX designer
Reviews screens and flows, specifies what to build and draws it as mocks.
Staff frontend engineer
Builds screens and components and keeps them accessible.
Staff QA engineer
Reviews what others build and says what breaks.
Staff security engineer
Reviews changes and dependencies for security risks.
Staff site reliability engineer
Keeps builds, deploys and services healthy.
Staff software architect
Shapes the system and reviews big changes before they start.
Staff web designer
Designs and builds marketing and content sites.
Staff product manager
Recommends what to build next and writes the requirements.
Staff data analyst
Answers questions with data and specifies dashboards.
Staff technical writer
Writes the docs and keeps them up to date.
Staff copywriter
Writes release notes, launch posts and site copy.
Staff SEO specialist
Audits the site for search and suggests fixes.
Staff marketing manager
Plans launches and the messages around them.
Staff support engineer
Triages issues and traces what users report in the code.
03 Tool up
Connect Linear and Foreman reads its issues for New workspace, so foreman run issue ENG-142starts a workspace from one. What the agents themselves may do in Linear is up to you: nothing, read, or read and write.
Try it: tap the Linear level on the pegboard to hang it on the belt.
Connections belong to the repository, so every new workspace in atlas starts with this belt.
7 of 7 tools on the belt
Pulled ENG-142: “Add passkey sign-in to atlas”, with its description and comments.Hang Linear on the belt and ENG-142 comes in from Linear.
foreman run issue ENG-14204 Build it
Give each part its own agent in its own git worktree on its own branch. They edit the same repository at the same time without touching each other's files, and you sign off each diff.
apiWebAuthn register and verify endpointssign-inThe "Sign in with a passkey" buttone2eEnd-to-end tests in three browsersdocsThe sign-in docs and the changelogTry it: tap a hat, then Sign off each lane when it says ready for review.
Open lane · waiting for a hat
passkey-apiClaude Code
+86 −12 · ready for review
Open lane · waiting for a hat
passkey-buttonCodex
+41 −6 · ready for review
Open lane · waiting for a hat
passkey-e2eCursor
+120 −0 · ready for review
Open lane · waiting for a hat
passkey-docsOpenCode
+18 −2 · ready for review
4 worktrees open · 4 signed off
Away from the desk? Answer from your phoneAgents sharing a folder: none. Each agent works in its own git worktree.
05 Send it off-site Experimental
In a sandbox, if you like: as an experiment, a workspace's worktree and agent can run on your own E2B, Daytona, Vercel Sandbox or Docker account. Close the laptop and the turn keeps going until it finishes or reaches the provider's session limit.
Try it: OpenCode has the tests. Press Create on E2B, then Close the laptop.
Workspace
Runs on
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
Session · not started
Turn · waiting to ship
This month · no sandbox time yet
06 Keep it fresh overnight
Put a saved prompt on a schedule. Passkeys lean on a WebAuthn library, so weekly-deps updates the dependencies and runs the tests every Monday at 02:00, on Claude Code, in a fresh worktree. With Flows on, a schedule can run the keep-branch-fresh flow instead.
Try it: pin weekly-deps, set it to weekly at 02:00 and file the slip.
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
weekly-deps on atlasRuns every Monday at 02:00 (Europe/London) · stops after 30 minutes · keeps the workspace
foreman schedules add weekly-deps --repo atlas --every weekly --on mon --at 02:00 --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.
07 Review it
Two reviewers who must agree. A QA reviewer reads the change against what was asked, a security reviewer reads the same tree for injection, secrets and unsafe defaults, any finding goes back, and you look last. That is the built-in two-reviewers flow.
Omar, your security engineer, is on the team, so the table deals the security pass.
No security engineer on the team, so the table deals a one-reviewer hand. Hire Omar in chapter 2 and it deals the security pass.
Quinn, your QA engineer, takes review requests on this branch too.
The job
Loadout for security pass before a release
Builds, then fixes until the checks pass, round after round, within the loop’s bounds.
Reads the tree first: does the change do what was asked?
Reads the same tree for injection, secrets and unsafe defaults. Any finding goes back.
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 fix flaky tests
Writes the fix. Flow steps that change code run on Claude Code, the one agent Foreman runs unattended.
Reads the diff read-only, inside its own sandbox. A flow’s review steps can run on Codex.
What the reviewer wears: it finds what breaks, never fixes it, and ends with findings.
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
Takes the prompt in a worktree of its own, on its own branch.
Same prompt, its own worktree and branch, so nothing collides.
Same prompt again, as an interactive pair. Foreman reviews what it does.
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.
08 Ship it
A draft pull request on its own branch, with every change read as a diff, the checks run and both reviews clean. In issue-to-draft-pr Foreman opens the draft itself after your gate, and sends CI failures back to the developer until green. Merging stays with you.
foreman pr create atlas --draft
foreman pr merge atlas --auto --yes# Open a draft by hand, or auto-merge when the checks pass.
eng-142-passkeys → main · opened by Foreman after your gate
Waiting on the chapters above.
Also on site
Yes. Pair a phone with a QR code and 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, with no Foreman relay.
Phone · today
Watch, Operate or Full control for each device. The phone answers gates and picks; it 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.
AI employees
Every organization remembers in its own private git repository. Each run's notes land as one commit saying who wrote them, and your code repositories stay clean.
On a budget
Opt in and a failing CI log goes back to the agent: two fixes per commit, five per PR. A read-only reviewer can read each finished diff.
Command line
Almost everything in the window works from a terminal with the foreman command. Every command takes --json and exit codes are stable, so scripts and CI can rely on them.
foreman flow run fix-until-green --input task="make the tests pass" --waitOther sites
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 the parts of this page past chapter 4: flows that loop until checks pass, AI employees, schedules and your own sandboxes.
—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 | — | — |
Your own project
Download the app, point it at a git repository, and give each task its own workspace.
Free for macOS (Apple Silicon, signed and notarized) and Windows. You need Git on your PATH.
Download ForemanPick any git repository. Sign in Claude Code, Codex, Cursor or OpenCode in Settings → Agents with your own login or key.
One per task, each a fresh worktree on its own branch. Review the diffs, then open the pull request.
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
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Foreman is three weeks old and has shipped 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 it from start to ship yourself.