hob vs T3 Code
T3 Code, from T3 Tools, is a free, open-source (MIT) control plane for coding agents, with desktop, web, and iOS apps. It runs agent threads with optional worktrees, a terminal, a preview browser, and diff and pull request review. Its README calls it very early and tells you to expect bugs.
hob is a workspace for the same agents, built for people and agents working together. Conversations, previews, documents, and terminals tile side by side. Agents coordinate with each other, and every result stays linked to the conversation that produced it.
At a glance
| Topic | hob | T3 Code |
|---|---|---|
| License and price | Pro $50/mo, Pro+ $75/mo with remote access and headless, billed annually. First month free. | Free and open source (MIT). Remote access uses T3 Connect, a hosted relay with sign-in. |
| Maturity | Stable releases since April 2026, with new features tested first in a beta channel. | Version 0.0.44. The README says the project is very early and to expect bugs. |
| Platforms | macOS, Windows, and Linux desktop; browser and phone access to the same Host. | macOS, Windows, and Linux desktop; a web app; an iOS companion app. |
| Agents | Claude Code, Codex, OpenCode, and Grok Build. | Claude Code, Codex, Cursor, Grok Build, OpenCode, and Google Antigravity. |
| Workspace layout | Conversations, terminals, previews, diffs, and documents tile side by side in each workspace. | One thread at a time in the main view; a request for split view was closed. |
| Agents working together | Built in: agents open panes and previews, point at details for you, start a delegate, message another agent pane, and file issues. | Shows subagent activity within a thread. |
| Record of the work | Conversations 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. | A command palette searches messages across threads. |
| Beyond code | Render panes for documents, PDFs, images, and spreadsheets (beta), with markup and annotations between you and your agents. | Image, video, and file attachments in the composer. |
| Automation | Automations combine commands and agent steps, run manually or on a schedule, and keep a record of every run. | No scheduled automations in the current release. |
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.
A workspace, not a thread list
T3 Code organizes work as a list of agent threads. hob organizes it as workspaces: the agent's conversation, the preview it built, the diff, the terminal running the checks, and the issue that defined the task, side by side. You see the evidence and the result together, without switching views.
Agents arrange that context themselves. An agent opens the preview, points at the element it changed, and asks a second agent for a review. You step in where your judgment matters.
Built to rely on every day
hob ships stable releases, with new features tested first in a beta channel. Your conversations, workspaces, and history save continuously in a local database, so after a restart you return to the same panes and context. When something goes wrong, you work with the hob team directly.
Choose hob if
- You want conversations, previews, documents, and terminals side by side.
- You want agents to coordinate and review each other as a standard part of the work.
- You want scheduled automations with a record of every run.
- You want commits and issues linked to the conversations that produced them.
- You want a stable product with support from the team that builds it.
Questions
- Is there a T3 Code alternative with split panes?
- Yes. In hob, agent conversations, terminals, browser previews, diffs, and documents tile side by side in each workspace, and agents can open the panes they need beside their conversation.
- Can I use my Claude 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.
- Can I reach hob from my phone, like T3 Code?
- Yes, with Pro+. hob roam connects to the same hob Host from iOS, Android, or a browser, so you can answer an agent, follow a command's output, or review a result. Remote traffic is end-to-end encrypted before it reaches the relay.
Try hob with the agents you already use. Your first month is free.