Port42 for Business

Your team pays for AI. Your people are still the glue.

Port42 is a Mac desktop where your team and its AI companions work on the same live work. Bring the Claude Code and Codex seats you already pay for, and stop carrying pieces between windows.

The problem

Every AI tool is one more window.

Every AI tool your team adopts opens another window, and every app an AI companion builds opens one more. A dashboard in one tab, a terminal in another, the answer in a chat somewhere else. Your people carry the pieces between them by hand.

244
window switches an hour

On a normal working day, heavy on AI, I counted 244 window switches an hour.

More AI, more windows

Each new tool is one more place to check, sign in to, and paste into.

Apps that cannot talk

What one app knows, the next never sees, unless someone copies it across.

Work nobody can see

AI runs in terminals and tabs on one person's screen, so the rest of the team finds out afterwards.

What Port42 does

Port42 puts your people and your AI companions on the same live work.

Everything your team and its AI companions make lives on one desktop as a port, a live surface you can see, click, and share. A pricing model, a deploy log, a launch review. People and AI companions work on the same port at the same time, and every port shows who is driving it.

pricing model · web portdriver: you
tier B · $48 → $52
lead margin check passes
deploy log · terminal portdriver: eng2 · codex
● build 412 green
staging updated
launch review · web portdriver: lead · claude code
lead 3 of 4 items done
you copy approved
Faster

A team of AI companions on one task, in the open.

Give one AI companion the lead. It splits the work, briefs the others in the port's own chat, and they build in parallel on the same live port. You watch it happen, and step in whenever you want.

Lead: "Lead here, to settle the direction so there is one brief." A real run with one Claude Code lead, a Claude Code engineer, and a Codex engineer.
Better

The lead checks the work, and you review the running thing.

The lead reads the port's console and checks each piece before it accepts it. At the end you review the thing itself, running, with everyone's changes in it.

Most multi-agent tools hand each agent an isolated task and send you diffs to review afterwards. Here your AI companions work one live surface together, in a chat you are part of.

History you can roll back

Every port keeps its versions. Restore any one of them.

Step in any time

Click the port and you are driving. Your AI companions pick up from your change.

Cheaper

Bring the seats you already pay for.

Claude Code and Codex become your AI companions out of the box, and other CLIs and agent frameworks can join too, with integration still deepening. Each uses your team's own Claude or ChatGPT accounts, under the plans and terms you already have. Port42 runs no model and holds no key.

No new AI vendor

Nothing new to approve. Your team keeps the AI seats it already has.

No keys to hand out

Port42 never reads a provider credential.

Swap any seat

Replace Claude Code with Codex on any seat and nothing else changes.

Fewer tools to buy

Your AI companions build what the team needs as ports, on the desktop it already has, and you share the live thing. So there is less to add:

  • No new AI vendor or model subscription
  • No agent orchestration platform
  • No internal-tool builder for a dashboard you need this week
  • No hosting or deploy just to show a client a prototype
  • No screen share to walk someone through it
  • No sharing service to buy. Start on Port42's hosted relay, and run your own when sharing has to stay inside your network

More than 100 things your team could build instead of buy, one line each: the periodic table of software →

In control

Every change is named, and access is per port.

Every driver is named

Each port shows who is driving it right now, you, a colleague, or an AI companion, and every version records who made it.

Nobody overwrites anybody

If someone changed a port first, a later write is refused and picks up from their change.

Any caller, one grant at a time

Grant access to an AI companion, a person, or any outside process, like a script, a service, or a CI job, through its own bearer token. Revoke one grant and every other grant stays as it is.

Your work stays on your computer

Your ports, their chats, and their history stay on your machine. A port reaches someone else only when you invite them to it.

Your model traffic, your provider

Each CLI talks to its own provider under your team's terms. Port42 is not in that path, and adds no new vendor or data processor for your prompts.

In control

Run your own relay.

Sharing a port goes through a relay. Start on Port42's hosted relay, with nothing to set up. When sharing has to stay inside your network, run your own. The relay is open source. Run it on your own domain, under your own logging policy, and point your team's Port42 at it in Settings. Sharing then never depends on Port42's servers.

Traffic is encrypted end to end either way. The relay forwards what it cannot read, so whoever runs it sees who connected to whom and when, never the work.

Security status. Sharing in Port42 v1 (invites, the relay, and the browser guest) is new code and has not been independently audited. Connections between machines are encrypted end to end with the Noise protocol, the relay forwards bytes it cannot read, and a guest reaches only the port you invited them to. Those are design properties, not audited guarantees. Until an audit is done, treat a shared port like a screen share: don't share credentials, personal or customer data, or anything covered by regulation. Running your own relay keeps sharing traffic inside your network; it does not replace an audit.

Your relay, your domain

One static binary or a Docker image, with no database. It needs a domain with TLS and WebSockets, nothing else.

Your logs policy

The relay keeps its state in memory and stores nothing. What you log around it is your call.

Start hosted, move when ready

Port42's hosted relay works from day one. Add your relay in Settings and new invites use it, with Port42's relay out of the path.

How to self-host the relay →

Share live work

Share live work with clients.

Send a port. Not a screenshot, a file, or a doc. One invite to one web port, for a colleague, a client, or a reviewer. It is live on both computers with one chat for it, a change on either side shows up on the other, and your AI companions and theirs can work on it together. They reach that port and nothing else you have.

your computer
launch review · portdriver: you
your AI companions keep working on it
one invite
the same port, live on both
their computer
launch review · portdriver: you
your client drives it too
no Port42?The same invite opens in a browser, with nothing to install. Same live port, same door.

Not yet audited. Sharing is new in v1 and has not had an independent security audit. It is encrypted end to end, but until it is audited, don't share ports that hold passwords, customer data, or anything regulated.

One invite grants one port, and it works once. You stay in control. Stop sharing any time, and they lose that one port and nothing else.

Why this matters now

The advantage is the harness.

Everyone runs the same models now, and they get cheaper every month. What sets a team apart is the harness around them.

A thousand years ago the horse collar moved the load off a horse's throat and onto its shoulders, and one horse did the work of a team. Same horse, better harness. Today the throat strap is the window. Your people are the wire between the AI and the work, and the more powerful the AI, the more that costs.

Port42 is the collar. Your AI companions and your people work on the same live surface, so the power reaches the work.

Yours

It stays on your machines.

Port42 runs on your computer. Your ports, their chats, and their history stay there. Your AI companions use your own accounts, and you decide who reaches which port. Leave whenever you like, and your work stays with you.

Your people stop being the glue.

The copying stops. The apps stop being separate places to visit. The window switching falls toward zero, because the work is all in one place.

244

I clocked myself at 244 an hour. Zero is the target. We are not there yet, and we are building straight at it.