Skip to content

SheetG-001

TitleCover sheet

Scale1 agent = 1 git worktree

SetForeman · 9 sheets

A drawing set for your repo. Checked by you.

AI agent orchestration, drawn to scale.

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.

Every sheet below is one part of it, and every sheet works. Use one and watch the set get revised.

  • macOS & Windows
  • Apache-2.0
  • No account
  • v1.2.4
Tiles · 4 workspaces · 4 branches · 2 need you
Four Foreman workspaces side by side in Tiles: a failed turn, a finished fix and two questions from AI employees waiting for an answerThe 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. G-1Tiles: four workspaces side by side, each in its own worktree, two of them waiting on you.
Project
your repo
Drawn by
the assistant
Checked by
you
Rev
A
Date
Licence
Apache-2.0

G-002 Drawing index

What's in the drawing set?

Eight sheets, one for each part of Foreman: the site plan of parallel agents, staffing, schedules, integrations, cloud sandboxes, flows, crew assignment and your phone. Every sheet is a working model.

Sheet list: every sheet in the set, what it shows, its caveat and its current revision
SheetTitleShowsNoteRev
A-101Site planParallel agents, one worktree eachIllustrativeA issued
A-102StaffingAI employees and their accessUnattended: Claude CodeA issued
A-201ScheduleTemplates and schedulesRuns while Foreman runsA issued
A-301Services and utilitiesGitHub, Linear, Slack, Langfuse, MCPSlack: outbound onlyA issued
A-401Off-site worksE2B, Daytona, Vercel, Docker sandboxesExperimentalA issued
A-501ProcessFlows that loop until green, with your gateExperimentalA issued
A-601Crew assignmentWhich agent takes which jobIllustrativeA issued
A-701Remote supervisionYour phone, and the apps comingiOS & Android: coming soonA issued

General notes, whole set

  1. Every sheet is illustrative. Templates, jobs, limits and flow names are the app's own.
  2. Flows and remote sandboxes are experimental and off by default.
  3. Unattended work (schedules, AI employees, flow steps that write code) runs on Claude Code.
  4. Use any sheet and the set is revised. Watch the Rev column.

SheetA-101

TitleSite plan

Scale1 lane = 1 git worktree

Rev Aissued for review

Tap a hat or a work order. Each agent walks into its own lane.

What is AI agent orchestration?

AI agent orchestration is running several coding agents on one codebase at the same time, each on its own task, without them colliding. Foreman does it with git: every agent gets its own worktree on its own branch, and you assign, watch and review the work from one window.

General notes

  1. One lane is one git worktree on its own branch. Your main checkout stays clean.
  2. Built and load-tested for 10 to 12 agents at once.
  3. Claude Code, Codex, Cursor, OpenCode or any ACP agent, each on your own login or key.
  4. Board is illustrative; the branch names are made up.
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

Off site? Supervise from your phone: sheet A-701

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

SheetA-102

TitleStaffing

Scale1 hat = 1 employee

Rev Aissued for review

Hire from the fifteen job templates. Remove anyone with the ×.

Can AI agents work as a team?

Yes, as AI employees. Give an organization employees with a role in plain words, a hard hat and access you approve. They work in fresh workspaces, remember through a git memory repository and hand work to each other. Priya, the program manager, plans each project and you approve it.

General notes

  1. 15 job templates, from software engineer to SEO specialist, each with its own hat.
  2. Memory is a private git repository per organization, with a commit for each run.
  3. Since 1.2.4 employees push and open pull requests without waiting. Slack posts and Linear changes are held for you.
  4. Unattended runs use Claude Code.

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 5

  • 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

SheetA-201

TitleSchedule

Scale1 slip = 1 schedule

Rev Aissued for review

Pin a template to the slip, say when it runs, file it.

Can you schedule AI coding agents?

Yes. Save a prompt as a template and Foreman runs it hourly, daily, weekly or monthly, in your time zone. It runs while Foreman runs, and Foreman can run with no window, or start at login with foreman service install.

General notes

  1. Schedules run while Foreman runs. A sleeping computer isn't woken.
  2. A run more than 5 minutes late is skipped, never replayed.
  3. Templates with {{blanks}} can't be scheduled: a scheduled run can't stop to ask.
  4. Scheduled runs use Claude Code. Edit the text and the schedule pauses until you approve it again.

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

SheetA-301

TitleServices and utilities

Scale1 tag = 1 access level

Rev Aissued for review

Hang a tool on the belt, then read its tag: what the agent may do with it.

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.

General notes

  1. Slack is outbound only: notifications and posts. You can't approve from Slack.
  2. Langfuse is read-only. GitLab sends fewer pull request events than GitHub.
  3. Auto-fix CI is opt-in and answers failing CI only, not review comments: 2 fixes per commit, 5 per PR.
  4. Every agent also gets a foreman-app MCP server to check its status and run checks.
  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

SheetA-401

TitleOff-site works

Scale1 container = 1 sandbox

Rev Aissued for review

Pick a workspace and a container, ship it, then close the laptop.

Can coding agents run in a cloud sandbox?

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. Turns keep going after Foreman quits, until they finish or reach the provider's session limit.

General notes

  1. Experimental and off by default, in Settings and again per repository.
  2. The repository needs a GitHub remote.
  3. Claude Code, Codex and OpenCode go off-site; Cursor stays home.
  4. Provider keys never cross the property line into the sandbox.

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

SheetA-501

TitleProcess

Scale1 room = 1 step

Rev Aissued for review

Tap an underlined word to change the plan, then press Run it.

How do you orchestrate agents with a flow?

Write the way of working down once, as a graph of agent steps. Loops run until the checks pass or a review comes back clean, and gates stop the run where you decide. Describe who does what and the assistant drafts the flow; nothing runs until you click Run.

General notes

  1. Flows: experimental, off by default (Settings → Experimental → Flows).
  2. 11 built-in flows and 10 personas, from fix-until-green to idea-to-feature.
  3. Steps that write code run on Claude Code. Every loop has a bound.
  4. Flows never merge branches. That stays with you.
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

SheetA-601

TitleCrew assignment

Scale1 card = 1 seat

Rev Aissued for review

Pick a job and deal. You are always the fourth card.

Which agent should do which job?

Give the writing to one agent, the reading to another, and keep the gate for yourself. Foreman runs Claude Code, Codex, Cursor and OpenCode side by side, each in its own worktree, so one job can get a developer, a reviewer and a second opinion at once.

General notes

  1. The same prompt can go to three agents in three worktrees. You keep the diff you like.
  2. A flow's review steps can run on Codex, read-only; steps that change code run on Claude Code.
  3. Nothing merges by itself.

The job

Loadout for fix flaky tests

  1. DeveloperClaude CodeAgent · Anthropic

    Writes the fix. Flow steps that change code run on Claude Code, the one agent Foreman runs unattended.

  2. ReviewerCodexAgent · OpenAI

    Reads the diff read-only, inside its own sandbox. A flow’s review steps can run on Codex.

  3. Review personaqa-engineerFlow persona · reviewer

    What the reviewer wears: it finds what breaks, never fixes it, and ends with findings.

  4. 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.

SheetA-701

TitleRemote supervision

Scale1 phone = 1 paired device

Rev Aissued for review

Start the A-501 run from here, then answer its gate on the phone.

Can you supervise AI agents from your phone?

Yes. Pair a phone with a QR code to answer approvals and flow gates, steer agents, comment on diffs and read terminals, live. On the same Wi‑Fi it connects directly, and anywhere else over your own Tailscale network. A browser on another computer can open the whole app.

General notes

  1. No Foreman relay. Away from home it's your own Tailscale network (tailscale serve).
  2. Three access levels: Watch, Operate, Full control. A six-digit code pairs each device.
  3. The phone reads terminals but can't type into them, and can't answer AI employees' held actions.
  4. iOS and Android apps are coming soon. Today the phone view installs to your Home Screen.

Native apps, on the drawing board

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

ForemanNeeds you · 0

Operate · over Tailscale

osaka · fix-login-redirect

Nothing needs you

Start the run on sheet A-501 and its gate lands here.

  • lisbon · Codex working
  • kyoto · Cursor ready

Illustrative

  1. Scan the QR code in Foreman.
  2. Check the six-digit code matches.
  3. Pick Watch, Operate or Full control.

S-001 Specification

What else is in the specification?

Everything around the sheets: Foreman is local-first with no account, approvals spell a command out, every change is a diff you read first, Tiles holds 10 to 12 agents, and the command line takes --json everywhere.

A file diff with the list of changed files
Detail 1: review before you commit. A file diff, with every changed file to tick off as viewed.

Detail · Command line

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
  1. §01

    Local-first. No account.

    Foreman runs on your computer. There is no Foreman account, no cloud service and no telemetry upload. Agents use your own logins and API keys.

  2. §02

    Approvals that spell it out

    An approval breaks a command down part by part, marks anything that leaves your computer, and says exactly what Always allow adds.

  3. §03

    Review every change

    Read each change as a diff before you commit, push or open a pull request. Checkpoints let you rewind a workspace to any turn.

  4. §04

    Watch them all at once

    Tiles shows several workspaces side by side so you can step in where you are needed. Built for 10 to 12 agents running at once.

  5. §05

    A real 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.

  6. §06

    Agents that use Foreman too

    Every workspace agent gets a foreman-app MCP server to check its status, run checks and, if you allow it, hand tasks to other agents. A Claude Code or Codex session you run yourself can sign in to Foreman over MCP.

S-002 Schedule of alternatives

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, schedules 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.

C-001 Construction sequence

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.

Or from a terminal: one line, one workspace
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. Every command takes --json. CLI reference

RFI Requests for information

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.

Issue Approved for construction

Put your name in the title block.

Foreman is three weeks old and has shipped 31 releases since 1.0.0 on 27 October. It's drawn in the open under Apache-2.0. Star it to follow the revisions, fork it, or take a first issue and sign the drawings with us.

Revisions this visit: none yet

  1. AG-001Set issued for review