Compare hob
hob is the independent workspace where people and agents work together. It supports every way of working with agents: in parallel, in the background, as scheduled automations, and in panes you can see, on web pages, documents, data, and code, where you can take over at any time. Claude Code, Codex, OpenCode, and Grok Build run in it on your own accounts, and every result stays linked to the conversation behind it. See how hob compares.
- hob vs ConductorA Conductor alternative for macOS, Windows, and Linux. Run Claude Code, Codex, and OpenCode in parallel worktrees, and let agents work with you and each other.
- hob vs OrcaAn Orca alternative where Claude Code, Codex, and OpenCode agents work with you and with each other, and every commit links back to the conversation behind it.
- hob vs PaseoA Paseo alternative for Claude Code, Codex, and OpenCode. Reach your agents from desktop, browser, or phone, and let them work with you in one shared workspace.
- hob vs T3 CodeA T3 Code alternative for Claude Code, Codex, and OpenCode. Agents work side by side with previews and documents, and every result links to its conversation.
- hob vs Claude Code desktopWork with Claude Code in view, beside Codex, OpenCode, and Grok Build, on macOS, Windows, Linux, or a headless server, with the record of every task in one workspace.
- hob vs the Codex appWork with Codex and Claude Code in view in one app. hob puts the Codex CLI beside Claude Code, OpenCode, and Grok Build, with one history and one review flow.
- hob vs CursorA Cursor alternative where you work with your agents in view. Run Claude Code, Codex, and OpenCode on the subscriptions you already pay for, and let agents take you straight to the code.
Orchestration or collaboration
An orchestrator starts agent sessions, isolates them, shows you their state, and returns a result. hob does that too, but it is built for collaboration: people and agents operate the same workspace, and the agent works where you can see it.
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.