conductor - run parallel coding agents on your mac
About Conductor
macOS app for running Claude Code, Codex, Cursor, and OpenCode side by side, each in its own isolated workspace, without wrangling git worktrees by hand. You bring your own agent subscriptions and keys. The paid Conductor Cloud tier moves those workspaces into Vercel sandboxes so agents keep running after you shut the laptop, and adds shared multiplayer workspaces plus an API.
Key Capabilities
Runs Claude Code, Codex, Cursor, and OpenCode in parallel from one Mac app
Every workspace is an isolated copy of your repo, so agents never collide
Free tier covers unlimited local workspaces with your own subscriptions and keys
Conductor Cloud keeps agents running in Vercel sandboxes after you close the laptop
Multiplayer workspaces let teammates watch and prompt the same agent live
Conductor API drives workspaces and prompts from your own scripts and integrations
Standout Features
Isolated Workspaces
Each task gets its own copy of the repo and its own branch, so parallel agents never overwrite each other's work.
Conductor Cloud
Pro and above run workspaces in Vercel sandboxes (8 vCPUs, 16 GB RAM, 32 GB NVMe) so agents keep working after you close the app.
Multiplayer Workspaces
Share a workspace link, see who is active, and prompt the same agent together in real time.
Bring Your Own Keys
Uses the Claude, OpenAI, and Cursor plans you already pay for, with traffic going straight to the model provider on local workspaces.
Conductor API
Create workspaces, send prompts, and pull transcripts from your own scripts, CI, or phone.
Perfect for
Pricing
How much does Conductor cost?
Free for local workspaces on macOS (bring your own agent subscriptions and keys). Pro $50/mo adds Conductor Cloud, multiplayer, and the API. Teams $60/mo per user adds admin portal, central billing, and SSO. Enterprise is custom priced.
Community Buzz
I’ve been using conductor only for the past 6 months, but I don’t like their new version Why would I pay for their cloud while other solutions can do the same for free, in my own server/laptop?
yes conductor is very good if you ask the agent to everything (setup/run scripts, etc)
I use conductor cause I like the way it has workspaces and native agent views (don’t need to use the cli tuis) But I really like the direction of t3 code. The only thing it’s missing for me is workspaces. Each conversation is a separate thread with no way to group threads that…
I've been loving @conductor_build but... It's time for me to check out some new stuf. Their cloud setup is pretty steeply priced. And it just confused me as I need to basically set up my whole dev workflow again? Their new API doesn't work locally only on cloud. Also, I don't…
A week ago I asked how developers were running agents in parallel and more than a hundred people replied. Many people said that they weren't, but of those that were running agents in parallel often, several recommended @conductor_build. I want to recommend you all give it a… p...
Similar Tools to Conductor
Orca
Open-source Agent Development Environment for running a fleet of AI coding agents at once. Every task gets its own git worktree, its own agent terminal, and its own browser tab, so you can fan one prompt across several agents, compare the diffs, and merge the winner. It drives roughly 30 CLI agents you already pay for, including Claude Code, Codex, OpenCode, Cursor and Copilot, and ships on macOS, Windows, Linux, iOS and Android.
Parallel Code
Free, open-source desktop app that dispatches AI coding agents in parallel, each in its own git worktree. It runs the real CLI agents you already trust (Claude Code, Codex, Gemini) side by side, then lets you review the diffs, merge the wins, and toss the rest.
Vibe Kanban
Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.
Google AntiGravity
Google's agentic development platform, now split across four surfaces: the Antigravity IDE (VS Code fork), Antigravity 2.0 standalone desktop, the Go-based Antigravity CLI, and a Python SDK for custom agents.
Hermes Agent
Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.
Vibe80
Apache-2.0 web workspace that orchestrates Codex and Claude Code over your Git repositories in sandboxed parallel worktrees, with a PTY web terminal and a mobile companion app that picks up a session by QR code.
Related Articles
Browse vetted vibe coding agencies for MVP builds, cleanups, and audits.
ready to try conductor?
go to the official site and judge Conductor yourself.
try conductor now