Skip to content

Collect the whole crew · 32 cards

Claude Code vs Codex vs Cursor? Hire all of them.

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 agent wears its own hat, and you pick the right one per task instead of once and for all.

  • macOS & Windows
  • Apache-2.0
  • No account
  • Your own agent logins
  • Claude Code

    Full agent

    Agent · Anthropic

    The one Foreman lets work alone: schedules, flow code steps, AI employees and the assistant.

    • This computer: Yes
    • Sandbox: Yes
    • Unattended: Yes

    01/32

    Abilities Claude Code

    Read-only mode
    Yes, through plan mode
    Asks questions
    Yes
    Tool approvals
    Yes
    Runs unattended
    Yes
    Flow code steps
    Yes
    Flow review steps
    Yes
    Remote sandboxes
    Yes, with a setup token or API key
    Several accounts
    Yes
    Permissions by
    The agent

    Source: docs/agents.md §12

  • Codex

    Full agent

    Agent · OpenAI

    Read-only inside its own sandbox, with goals, and a reviewer a flow can call on.

    • This computer: Yes
    • Sandbox: Yes
    • Unattended: No

    02/32

    Abilities Codex

    Read-only mode
    Yes, through its sandbox
    Asks questions
    Yes
    Tool approvals
    Yes
    Runs unattended
    No
    Flow code steps
    No
    Flow review steps
    Yes, read-only and attended
    Remote sandboxes
    Yes, with an API key
    Several accounts
    Yes
    Permissions by
    The agent, by its sandbox

    Source: docs/agents.md §12

  • Cursor

    Full agent

    Agent · Anysphere

    An interactive pair in a worktree of its own. It never asks, so Foreman reviews what it does.

    • This computer: Yes
    • Sandbox: No
    • Unattended: No

    03/32

    Abilities Cursor

    Read-only mode
    No
    Asks questions
    No
    Tool approvals
    Never asks
    Runs unattended
    No
    Flow code steps
    No
    Flow review steps
    No
    Remote sandboxes
    No
    Several accounts
    Yes, an API key each
    Permissions by
    Foreman, by review

    Source: docs/agents.md §12

Tap a card to flip it

The rulebook

Which is better, Claude Code, Codex or Cursor?

None of them wins everywhere: they have different strengths, and Foreman lets you run them side by side and pick per task. Here is what each one can do inside Foreman, from its capability record, with no benchmarks.

  • Reach for Claude Code when…

    • work must run while you're away. It is the only agent Foreman runs unattended: schedules, flow steps that write code, and AI employees.
    • you want Foreman's assistant, the cost of each turn, or subagents you can stop one by one.
    • you want it read-only: it holds plan mode.
  • Reach for Codex when…

    • you want read-only held by its own sandbox, plan mode, or a long task as a /goal.
    • a flow needs a second opinion: review and decide steps can run on Codex, read-only and attended.
    • it should work in a remote sandbox, with an API key.
  • Reach for Cursor when…

    • you want an interactive pair in a worktree of its own, with several accounts if you need them.
    • you're happy to review: it never asks for approval, so Foreman holds its permissions by review.
    • it stays on this computer: no read-only or plan mode, and no remote sandboxes.

All three ship inside the app, sign in with your own account or key, can keep running after you quit if you opt in, and get a git worktree each. That's why the honest answer is “more than one”.

The binder

Who is on the crew?

Four full agents plus any ACP agent, ten flow personas, and an AI employee team: Priya, the program manager, and fifteen job templates. Flip any card for its abilities; drag or add agents to the compare tray under the binder.

Agents

  • Claude Code

    Full agent

    Agent · Anthropic

    The one Foreman lets work alone: schedules, flow code steps, AI employees and the assistant.

    • This computer: Yes
    • Sandbox: Yes
    • Unattended: Yes

    01/32

    Abilities Claude Code

    Read-only mode
    Yes, through plan mode
    Asks questions
    Yes
    Tool approvals
    Yes
    Runs unattended
    Yes
    Flow code steps
    Yes
    Flow review steps
    Yes
    Remote sandboxes
    Yes, with a setup token or API key
    Several accounts
    Yes
    Permissions by
    The agent

    Source: docs/agents.md §12

  • Codex

    Full agent

    Agent · OpenAI

    Read-only inside its own sandbox, with goals, and a reviewer a flow can call on.

    • This computer: Yes
    • Sandbox: Yes
    • Unattended: No

    02/32

    Abilities Codex

    Read-only mode
    Yes, through its sandbox
    Asks questions
    Yes
    Tool approvals
    Yes
    Runs unattended
    No
    Flow code steps
    No
    Flow review steps
    Yes, read-only and attended
    Remote sandboxes
    Yes, with an API key
    Several accounts
    Yes
    Permissions by
    The agent, by its sandbox

    Source: docs/agents.md §12

  • Cursor

    Full agent

    Agent · Anysphere

    An interactive pair in a worktree of its own. It never asks, so Foreman reviews what it does.

    • This computer: Yes
    • Sandbox: No
    • Unattended: No

    03/32

    Abilities Cursor

    Read-only mode
    No
    Asks questions
    No
    Tool approvals
    Never asks
    Runs unattended
    No
    Flow code steps
    No
    Flow review steps
    No
    Remote sandboxes
    No
    Several accounts
    Yes, an API key each
    Permissions by
    Foreman, by review

    Source: docs/agents.md §12

  • OpenCode

    Full agent

    Agent · SST

    Asks before it runs a tool, answers to Foreman, and reports what each turn cost.

    • This computer: Yes
    • Sandbox: Yes
    • Unattended: No

    04/32

    Abilities OpenCode

    Read-only mode
    No
    Asks questions
    Yes
    Tool approvals
    Yes
    Runs unattended
    No
    Flow code steps
    No
    Flow review steps
    No
    Remote sandboxes
    Yes
    Several accounts
    —
    Permissions by
    Foreman

    Source: docs/agents.md §12

  • Any ACP agent

    Wildcard

    Agent · Agent Client Protocol

    Gemini CLI, Qwen Code, Goose and eight more, through one protocol. Off until you enable them.

    • This computer: Yes
    • Sandbox: Yes
    • Unattended: No

    05/32

    Abilities Any ACP agent

    Read-only mode
    No
    Asks questions
    Yes
    Tool approvals
    Yes
    Runs unattended
    No
    Flow code steps
    No
    Flow review steps
    No
    Remote sandboxes
    Yes
    Several accounts
    —
    Permissions by
    Foreman

    Source: docs/agents.md §12

Personas

  • architect

    Starter

    Flow persona · turn

    Plans the change without making it, from the task and the tree.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    06/32

    Abilities architect

    May write
    Nothing: read-only
    Is shown
    task, tree
    Ends with
    a plan
    Runs as
    A turn step: Claude Code
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • developer

    Starter

    Flow persona · turn

    Makes the change and gets the checks passing.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    07/32

    Abilities developer

    May write
    The worktree
    Is shown
    task, check results
    Ends with
    done
    Runs as
    A turn step: Claude Code
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • qa-engineer

    Starter

    Flow persona · reviewer

    Reviews the change against what was asked; finds problems, never fixes them.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    08/32

    Abilities qa-engineer

    May write
    Nothing: read-only
    Is shown
    diff, check results
    Ends with
    findings
    Runs as
    A review step: Claude Code or Codex
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • designer

    Starter

    Flow persona · reviewer

    Reviews what the change looks like, from the diff and before-and-after screens.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    09/32

    Abilities designer

    May write
    Nothing: read-only
    Is shown
    diff, workspace note
    Ends with
    findings
    Runs as
    A review step: Claude Code or Codex
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • product-manager

    Starter

    Flow persona · turn

    Decides whether and what to build, never how; writes the requirements.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    10/32

    Abilities product-manager

    May write
    docs/features/** only
    Is shown
    task, tree, note
    Ends with
    done
    Runs as
    A turn step: Claude Code
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • ux-designer

    Starter

    Flow persona · turn

    Turns requirements into a design specification; writes no code.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    11/32

    Abilities ux-designer

    May write
    docs/features/** only
    Is shown
    task, tree
    Ends with
    done
    Runs as
    A turn step: Claude Code
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • security-reviewer

    Starter

    Flow persona · reviewer

    Reviews the change for security problems; never fixes them.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    12/32

    Abilities security-reviewer

    May write
    Nothing: read-only
    Is shown
    diff, check results
    Ends with
    findings
    Runs as
    A review step: Claude Code or Codex
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • docs-writer

    Starter

    Flow persona · turn

    Updates the documentation for what the diff changed; never code.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    13/32

    Abilities docs-writer

    May write
    docs/** only
    Is shown
    diff, task
    Ends with
    done
    Runs as
    A turn step: Claude Code
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • researcher

    Starter

    Flow persona · turn

    Structures and writes a research report on an idea, and revises it in place.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    14/32

    Abilities researcher

    May write
    docs/research/** only
    Is shown
    task, tree
    Ends with
    done
    Runs as
    A turn step: Claude Code
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

  • research-reviewer

    Starter

    Flow persona · reviewer

    Reviews a research report for soundness, alone.

    • This computer: Yes
    • Sandbox: —
    • Unattended: On Claude Code

    15/32

    Abilities research-reviewer

    May write
    Nothing: read-only
    Is shown
    task
    Ends with
    findings
    Runs as
    A review step: Claude Code or Codex
    Writes enforced
    Yes, by Foreman, not the prompt
    Ships with
    Foreman 1.2.4, read-only; copy to change

    Source: src/shared/personaStarters.ts

Employees

  • Priya

    Program manager

    Employee · Program manager

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

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    16/32

    Abilities Priya

    Starts
    When you tag @Priya in Channels
    Asks first
    1–4 questions small, 4–10 large
    Plans
    Up to 3 parts small, 8 large, in plan.md
    Proposes
    Up to 4 new employees when nobody fits
    Replans
    3 times at most, if a part can’t finish
    Design parts
    HTML mocks, two options each
    Writes
    Only the project’s own files

    Source: CHANGELOG.md §1.2.0–1.2.4

  • Ravi

    Specialist

    Employee · Staff software engineer

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

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    17/32

    Abilities Ravi

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Mei

    Specialist

    Employee · Staff frontend engineer

    Builds screens and components and keeps them accessible.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    18/32

    Abilities Mei

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Quinn

    Specialist

    Employee · Staff QA engineer

    Reviews what others build and says what breaks.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    19/32

    Abilities Quinn

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Omar

    Specialist

    Employee · Staff security engineer

    Reviews changes and dependencies for security risks.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    20/32

    Abilities Omar

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Sofia

    Specialist

    Employee · Staff site reliability engineer

    Keeps builds, deploys and services healthy.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    21/32

    Abilities Sofia

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Kenji

    Specialist

    Employee · Staff software architect

    Shapes the system and reviews big changes before they start.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    22/32

    Abilities Kenji

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Uma

    Specialist

    Employee · Staff UX designer

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

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    23/32

    Abilities Uma

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Leo

    Specialist

    Employee · Staff web designer

    Designs and builds marketing and content sites.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    24/32

    Abilities Leo

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Nia

    Specialist

    Employee · Staff product manager

    Recommends what to build next and writes the requirements.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    25/32

    Abilities Nia

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Dara

    Specialist

    Employee · Staff data analyst

    Answers questions with data and specifies dashboards.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    26/32

    Abilities Dara

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Theo

    Specialist

    Employee · Staff technical writer

    Writes the docs and keeps them up to date.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    27/32

    Abilities Theo

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Ines

    Specialist

    Employee · Staff copywriter

    Writes release notes, launch posts and site copy.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    28/32

    Abilities Ines

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Sam

    Specialist

    Employee · Staff SEO specialist

    Audits the site for search and suggests fixes.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    29/32

    Abilities Sam

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Ana

    Specialist

    Employee · Staff marketing manager

    Plans launches and the messages around them.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    30/32

    Abilities Ana

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

  • Jonah

    Specialist

    Employee · Staff support engineer

    Triages issues and traces what users report in the code.

    • This computer: Yes
    • Sandbox: Not yet
    • Unattended: On Claude Code

    31/32

    Abilities Jonah

    Starts
    When asked, or on triggers you add
    Each run
    A fresh workspace and chat
    Push and draft PR
    Yes, without waiting (1.2.4)
    Slack and Linear
    Held for you
    Shell
    No, unless you allow one
    Remembers
    In the org’s git memory repo
    Hands off
    To colleagues you allow

    Source: src/shared/employeeTemplates.ts

✓ yes✕ no– not stated, or a notePersona hat colours are this page's; personas don't wear one in the app.

Compare tray 3 of 3

  1. Claude Code
  2. Codex
  3. Cursor
Agents

Drag an agent card here, or tap the chips. The tray holds three.

The compare tray

How do Claude Code, Codex and Cursor compare, ability by ability?

In Foreman, Claude Code is the only one that runs unattended, Codex holds read-only through its sandbox and can review in a flow, and Cursor is an interactive pair that Foreman reviews. The table follows the compare tray above; with no JavaScript it shows all five.

What Foreman can do with Claude Code, Codex, Cursor, OpenCode and any ACP agent
AbilityClaude CodeCodexCursorOpenCodeAny ACP agent
Made byAnthropicOpenAIAnysphereSSTAgent Client Protocol
Read-only modeYes, through plan modeYes, through its sandboxNoNoNo
Plan modeYesYes, since 1.0.22NoNo, until it lists oneWhen the agent lists one
Asks you questionsYesYesNoYesYes
Tool approvalsYesYesNever asksYesYes
Always allowYesYesNoOnce onlyKept by Foreman for the session
Steer a running turnNativeNativeInterrupt and restartInterrupt and restartInterrupt and restart
Fork and rewind the conversationNativeNativeFallbackFallbackFallback
Subagents as rows you can stopYesNoNoNoNo
Goals (/goal)NoYesNoNoNo
Reports costYesNoNoYesNo
Usage limit windows and reset timesYesYesNoNoNo
Unattended: schedules, flow code steps, AI employeesYesNoNoNoNo
Flow steps that write codeYesNoNoNoNo
Flow review and decide stepsYesYes, read-only and attendedNoNoNo
Runs the Foreman assistantYesNoNoNoNo
Remote sandboxes (E2B, Daytona, Vercel, Docker)Yes, with a setup token or API keyYes, with an API keyNoYesYes
Keeps running after you quit (opt-in)YesYesYesYes—
Several accountsYesYesYes, an API key each——
Who enforces its permissionsThe agentThe agent, by its sandboxForeman, by reviewForemanForeman
Tested againstRecorded traffic, 2.1.301Recorded traffic, 0.163.0Simulated fixturesSimulated fixturesSimulated fixtures

From Foreman's own capability records (docs/agents.md §12, v1.2.4). “Fallback” means Foreman does it another way; “—” means the docs don't say. Foreman also runs 18 terminal agents, such as Aider and Amp, as their own CLI in a terminal tab.

Deal a loadout

Which crew should you send for the job?

Pick a job and Foreman's dealer hands you a four-card team, with why each card fits. You are always the fourth card.

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.

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

On the table

Can you run Claude Code, Codex and Cursor at the same time?

Yes. Each task gets a workspace, a git worktree on its own branch, so the agents edit the same repository at once without touching each other's files. Tiles shows them side by side, and Foreman is built and load-tested for 10 to 12 agents at once.

  • Switch agents mid-chat. The hand-off is recorded, so you can see what the next agent received.
  • Hit a usage limit? The chat waits and resumes by itself, or continues on another account.
  • Review every change as a diff before you commit, push or open a pull request.
Four Foreman workspaces side by side in Tiles: a failed turn, a finished fix and two questions from AI employees waiting for an answer
The real Tiles layout: two workspaces side by side, each its own worktree.

Booster pack

What else comes in the box?

Flows that loop until the checks pass, automations and schedules, auto-fix for failing CI, remote control from your phone, integrations and remote sandboxes. All free, all in the same app.

  • 11 built-in · experimental

    Flows that loop until green

    Write a way of working down once as a graph of agent steps: loops that run until the checks pass or a review comes back clean, and gates where you decide.

  • Templates · schedules

    Automations and schedules

    Save prompts as templates and run them on demand or on a schedule: hourly, daily, weekly or monthly, in your time zone. Run Foreman without a window, or at login, and schedules keep going.

  • Opt-in · with a budget

    Auto-fix CI and auto-review

    Opt in and Foreman sends a failing CI log to your agent within a budget you set, and a read-only reviewer reads each finished diff. Checks can run after every turn, and a chat that hits a usage limit resumes by itself.

  • Agent access you choose

    GitHub, GitLab, Linear, Slack, Langfuse

    Open, merge and auto-merge pull requests, watch CI and reviews, start work from a Linear issue, send Slack notifications and read Langfuse traces. Each connection gets the agent access you choose: nothing, read, or read and write.

  • Experimental

    Remote sandboxes: E2B, Daytona, Vercel, Docker

    Run a workspace's worktree and agent in a sandbox on your own E2B, Daytona, Vercel Sandbox or Docker account. Provider keys never enter the sandbox, and turns keep going after you close the app. Experimental.

    • E2B
    • Daytona
    • Vercel Sandbox
    • Docker
  • Same Wi-Fi, or your own Tailscale

    Run it from your phone

    Pair a phone with a QR code to answer approvals and flow gates, steer agents and comment on diffs, live. Away from home it connects over your own Tailscale network, with no Foreman relay.

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

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. Foreman also drives OpenCode and any ACP agent, and adds flows, AI employees 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.

Starter deck

Get started in a minute

Download the app, add a git repository, sign in the agents you already pay for, and deal them a workspace each.

  1. Download Foreman

    Free for macOS (Apple Silicon) and Windows. You need Git on your PATH.

    Download Foreman
  2. Add 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.

  3. Create workspaces

    One per task, each a worktree on its own branch, each with the agent you pick. Watch them in Tiles.

Or deal from a terminal
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

House rules

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 rarest card is a contributor.

Foreman is three weeks old and has shipped 31 releases since 1.0.0 on 27 October, in the open under Apache-2.0. Star it to hear about the next one, fork it, or pick up a good first issue. Your hat colour is waiting.