hob vs Conductor
Conductor and hob both run several coding agents at once on your own Claude Code and Codex accounts, and both can give each task its own git worktree. The first difference is where they run. Conductor's desktop app is macOS only, with an optional paid cloud. hob runs on macOS, Windows, and Linux, and headless on a server you control.
The larger difference is what the agents do. Conductor runs agents side by side. In hob, agents also work with each other and with you in the same workspace.
At a glance
| Topic | hob | Conductor |
|---|---|---|
| Platforms | macOS, Windows, and Linux desktop; headless on your own VM or server, with access from a browser or phone. | macOS desktop app. Windows and Linux are not available yet. Optional Conductor Cloud runs agents in hosted VMs. |
| Agents | Claude Code, Codex, OpenCode, and Grok Build. | Claude Code, Codex, Cursor, and OpenCode. |
| Accounts and inference | Your own subscriptions and keys. hob does not resell inference. | Your own subscriptions and keys. Conductor does not resell inference. |
| Isolation | Worktree workspaces for separate branches, or several agents in one checkout when they should share it. | One git worktree and branch per workspace. |
| Agents working together | Agents open panes and previews, start a delegate with a task, message another agent pane, and file issues. | Agents run in parallel workspaces; Multiplayer lets people share cloud workspaces. |
| Record of the work | Conversations saved in a local database. Commits and issues link back to the turn that produced them. Search past conversations from History, and agents search the same history themselves. | Local chats stay on the Mac; cloud chats are stored on Conductor's servers. Reverting a checkpoint deletes the later messages. |
| Automation | Automations combine commands and agent steps, run manually or on a schedule on your machine or server, and keep a record of every run. | Routines run agents on a schedule or from a GitHub Action, in Conductor Cloud. |
| Price | Pro $50/mo, Pro+ $75/mo with remote access and headless, billed annually. First month free. | Free for local use. Pro at $50/mo adds Cloud, Multiplayer, and the API. |
Why pay for hob?
Most tools in this category are free, or come with a model subscription. Here is what a hob subscription buys.
Always use the best. No tooling changes.
Agent tools change every month. A new model takes the lead, a harness ships a feature, a new practice spreads. hob brings the best of the whole agent stack into one app, so each improvement reaches you where you already work.
hob builds the workspace once, for all your agents. Agents fork, queue, and schedule the same way in Claude Code, Codex, and OpenCode. Your agents open live previews, point you at the element they changed, take your markup on an image, PDF, or web page, and ask each other for reviews. Every commit made through hob links to the conversation behind it, recorded on your machine, not in your repository. One setting gives every agent the same personality.
Every harness wants to keep you inside its own ecosystem. hob keeps each one optional. Use whichever agent is best this month, and keep your workspace, history, and automations exactly as they are.
You never leave hob
Code, web pages, PDFs, images, documents, and spreadsheets (beta) open in hob beside the work. Mark up any of them for an agent. Agents annotate them for you just as easily.
Agents that know hob
Every agent starts with hob's instructions. From its first turn, it opens panes, previews, and diffs, points you at a detail, and coordinates with other agents.
The subscriptions you already pay for
hob runs Claude Code, Codex, OpenCode, and Grok Build on your own accounts. You pay hob for the workspace, never for tokens.
No reason to sell you tokens
hob does not resell inference, so it earns nothing when you spend more. Every change we ship aims to make your work faster and easier.
Change models, keep the workspace
Switch model or account from the pane. For another provider, or a local model through OpenCode, open a new agent beside it; it can read the recorded task. Your workspace, history, and automations stay the same.
Your data stays yours
Conversations and history live in a local database on your machine. hob's servers never hold your code or your sessions.
Support from the people who build it
You work with the hob team directly. You are a name to us, not an issue number, and your feedback reaches the people who decide what ships next.
Fitted to your team
For teams, we help adapt hob to how you work, from onboarding to the workflows and automations your projects need.
Orchestration or collaboration
Most tools in this category orchestrate agents. They start sessions, isolate them, and show you their state. hob does that too. Its larger aim is collaboration: people and agents operate the same workspace.
In hob, an agent opens the preview, diff, or file beside its conversation. It reads and operates a live web page while you watch, annotates an image or PDF at the detail you need to judge, and asks you a question in place. It starts a second agent for a bounded task, such as a review, messages another agent pane, and files the issue it found. When it commits through hob, the commit links to the turn that produced it, so the reasoning is one click away months later.
It works in the other direction too. Mark up an image, PDF, web page, or spreadsheet to show an agent exactly what you mean, and send the markup with your request.
You choose how involved you are. Stay hands-on and review every step. Or go hands-off: give a task to a team of agents, let them divide and review the work, and run the repeatable parts as a scheduled automation. hob keeps the record either way.
Windows and Linux
Conductor's install page says it is not available for Windows or Linux yet. hob runs natively on both, so the whole team can use one workspace, whatever the operating system.
hob also runs headless on a Linux VM. Your agents, terminals, and history stay on that machine, and you continue from a browser or your phone. Conductor's answer is its hosted cloud, which runs your agents on Conductor's infrastructure and supports only GitHub repositories.
Review and the record of the work
Both tools show diffs and send line comments back to the agent. hob also keeps the reasoning attached to the result. When an agent commits through hob, the commit links to the turn that produced it, and you can open that conversation from History months later. Issues that agents file link back the same way.
hob saves the whole workspace continuously: panes, layout, and conversations. After a restart, you return to the same arrangement with the context still in view.
Choose hob if
- You work on Windows or Linux, or across several operating systems.
- You want agents to coordinate with each other and bring results to you for review.
- You want each commit and issue linked to the conversation that produced it.
- You want your agents and history on machines you control.
Questions
- Is there a Conductor alternative for Windows or Linux?
- Yes. hob runs on macOS, Windows, and Linux, with Claude Code, Codex, OpenCode, and Grok Build. Like Conductor, it gives each task its own worktree when you want isolation. It adds agent collaboration, a linked record of the work, and automations.
- Can I use my Claude Pro or Max and ChatGPT subscriptions with hob?
- Yes. hob runs the official agent CLIs with your own accounts. It stays out of the inference path, so your usage goes directly to Anthropic, OpenAI, or the provider you choose.
- Does hob have a cloud like Conductor Cloud?
- No hosted cloud. With Pro+, hob runs headless on a VM or server you control, and you connect from a browser or phone. Your code and conversations stay on that machine.
Try hob with the agents you already use. Your first month is free.