Conductor

Conductor is a Mac app for running Claude Code, Codex, and Cursor agents in parallel inside isolated workspaces. It helps developers delegate separate tasks, review the resulting diffs, and merge work locally on their machine.

AI Agent Development AI Developer Tools Programming Agent

Visit Website

What Conductor does

Conductor is a Mac app for running multiple coding agents in parallel across isolated workspaces. It is designed for people who want to delegate separate tasks to Claude Code, Codex, and Cursor while keeping each task’s files, terminal, diff, and review path separated.

The product’s core workflow is straightforward: add a repository, let Conductor create a workspace for each task, watch the agents work, and then review the resulting diff before merging or archiving the workspace. The site positions Conductor as an interface for managing your coding agents rather than as another standalone model provider.

Features

Isolated task workspaces

Create isolated workspaces for coding agents so each task can run in its own git worktree without interfering with others.

Parallel agent execution

Run Claude Code, Codex, and Cursor in parallel to split up work across multiple agents.

Workspace status overview

See what each agent is doing at a glance, including which workspace needs attention and which changes are ready to review.

Review and merge workflow

Review changes, open a pull request, merge, and archive completed work from the same workflow described in the docs.

Local Mac-based workflow

Keep work on your Mac while Conductor clones the repo and operates locally on your machine.

Enterprise privacy controls

Use enterprise privacy mode to disable external AI features at the user or repo level when needed.

Use cases

Parallel feature work
Split a repository into separate tasks and let multiple agents work at once without sharing a workspace.
Isolated agent task execution
Keep terminal output, diffs, and file changes contained while an agent handles a focused bug fix or refactor.
Code review and merge preparation
Review each agent’s changes before merging, so a human can check the diff and decide what ships.
Team and enterprise workflows
Adopt the tool in an organization that needs local control over code and the option to disable external AI features.

Pros and Cons

Pros

Runs coding agents in isolated workspaces so parallel work stays separated.
Supports three named coding agents: Claude Code, Codex, and Cursor.
Keeps the workflow local on your Mac rather than moving the repo to a remote service.
Includes a review-oriented flow for checking diffs, opening pull requests, merging, and archiving work.
Offers enterprise privacy mode for organizations that need to disable external AI features.

Cons

The pricing page currently returns a 404, so pricing details are not available from the public site.
The source only confirms support for Claude Code, Codex, and Cursor; broader integration coverage is not documented in the collected pages.

FAQ

Does Conductor use separate workspaces for each task?

Yes. The homepage says each workspace is a new git worktree, and the docs describe each task as having its own workspace, branch, files, terminal, diff, and review path.

Which coding agents does Conductor support?

Conductor supports Claude Code, Codex, and Cursor. The homepage says users can ask for other agents by email.

How does Conductor handle Claude Code authentication and billing?

Conductor uses Claude Code however you are already logged in. If you are logged into Claude Code with an API key, Conductor uses that; if you are signed in with Claude Pro or Max, it uses that too.

Can organizations restrict external AI features?

Yes. The enterprise page says you can enable enterprise privacy mode at the user level in Settings -> Privacy or at the repo level with `enterprise_data_privacy = true` in `.conductor/settings.toml`.

Is pricing available on the public site?

The pricing URL currently returns a 404 page, so the public site does not show pricing details on that page.