Your agents, on subscriptions you already pay.

We set up your own always-on agents with you. Each one gets its own account and its own job, and its tokens come from the Claude, SuperGrok or ChatGPT plan you already own. Never a metered API key.

Book 15 minutes See the live fleet
Runs on the plans you already pay for. ClaudeChatGPTSuperGrok

Every agent worth hiring wants to be paid by the token.

The agent products winning right now meter the work: credits, compute units, token overage on top of the subscription, and a usage window that parks your agents when you need them most.

So you get two ways to lose. Pay the meter. Or watch your agents stand in line, hands out, while the window counts down.

Five small robots queue with open hands at a pay window where a tiny agent sits, while the owner beside it turns out empty pockets

The usage window

Wait 5 more hours.

Can you really afford $1,000 a day for agents? No one can.

That number is not drama, it is list price. An always-on agent carries a big working context on every turn. At today's published prices for a top-tier model ($5 per million tokens in, $25 out), a working turn runs $0.55 to $2.05, and an agent doing 30 to 90 turns a day costs $17 to $185 a day on a metered key. Put five or six of them to work and the fleet can cross $1,000 a day.

On a subscription you already pay, Claude Max from $100 a month, SuperGrok $30, ChatGPT plans from $20, the same turns cost nothing extra on top of the plan's flat price. The plan is the ceiling.

$5,500

a busy agent-month, metered at list

$100

the flat plan it runs on instead

The same turns, two ways to pay

PerMetered API at list priceA subscription you already own
List price, per 1M tokens$5 in / $25 outincluded in the flat plan
A working turn$0.55 to $2.05$0 extra
An agent-day, 30 to 90 turns$17 to $185$0 extra
A month, per agent$500 to $5,500the plan's flat price: Claude Max from $100, SuperGrok $30, ChatGPT from $20

Sources: claude.com/pricing, x.ai/pricing, help.openai.com. Prices as of August 2026.

KM BOT itself is a flat price, quoted on the 15-minute call. Never per token.

The meter is an API-list-price equivalent of tokens actually run, not money withdrawn from anyone's account. Subscriptions have their own fair-use windows.

What did your last API invoice say?

Three things you get here and nowhere else.

1 of 3

Connect as many subscriptions as you like.

Claude, ChatGPT, SuperGrok. One of each, or three Claude plans and a SuperGrok. Every plan you add is more fuel in the pool, and one plan fuels several agents at once.

Three subscription tanks, Claude, OpenAI and xAI, piping fuel down to five robots working at their own desks
2 of 3

Two ways to run it: Agents mode and Board mode.

Define roles and talk to your people in Agents mode, or watch the projects move across a board in Board mode. Same fleet, two views, switch any time.

Agents modeTalk to your people

Agents mode: the roster on the left, a conversation with an agent in the middle, what needs you on the right

Your agents by team on the left, one conversation in the middle.

Board modeWatch the work move

Board mode in the light theme: the same fleet, organised by project and task instead of by agent

The same fleet by project and task, with who holds each one.

3 of 3

Every agent gets its own account. And can drive your browser.

They share one server the way a team shares an office: each agent works under its own account, with its own memory, its own files, its own browser. Not one shared login for everybody. One mistake stays in one room. And when a job lives in your own logged-in session, the agent can drive your browser while you watch.

Seven killer features.

Keep scrolling. Each one takes over the whole screen.

1 / 7

Pick the subscription each agent runs on.

The pool holds your flat plans. You decide which plan fuels which agent, move them any time, and spread the load with one click.

The pool: flat plans in, agents assigned out.

2 / 7

Pick the model, and how hard it thinks.

Per agent: the model tier and the thinking effort. Your researcher can think at max while your inbox sorter stays quick and light. On a voice call it can use a faster model.

Model, model on calls and thinking effort, set per agent.

3 / 7

Talk to the whole fleet, or just the top.

Filter the roster to Everyone, Leads or Top. Ask one agent about one job, ask a team lead about their whole team, or ask your top management how the week went.

One roster, three filters: Everyone, Leads, Top.

4 / 7

Talk to KM BOT. Out loud.

Press Talk and speak to Doni, your COO agent, the way you would on a phone call. Ask about any open ticket, give instructions, and keep talking while the work runs.

What you agree on the call is handed to the right agent.

5 / 7

The fleet proposes its own fixes.

When an agent spots something in KM BOT that could work better, it files the fix in plain words: what goes wrong today, and what changes. You say Do it, or Not now.

Fixes written by the fleet, for the fleet.

6 / 7

The meter shows the bill you are not paying.

Every turn is priced at what it would have cost on the metered API, at public list prices, and shown on a meter: by day, by subscription, by agent.

The meter: what today's turns would have cost at list.

7 / 7

By the month, not by the token.

Your agents can work every day of the month and the bill does not move. You pay the flat plans you already own, and the plan is the ceiling.

A busy month. The same flat bill.

A living room with three doorways shaped like a phone, an app window and a browser, all opening onto the same robot at its desk

Every door leads to the same agent.

Ask on WhatsApp from the car. Open the app at your desk. Pick the thread up in the browser at night. It is the same agent, the same session, the same memory, mid-thought.

There is no "let me catch you up". It was there.

Nothing leaves without your yes.

An MFA code, a purchase, a login wall. The turn ends with a ticket at your door and the reason in plain words. Nothing fails quietly, and nothing guesses a password.

  • No agent spends, refunds or moves a dollar. Every email, post and quote is a draft until you approve it.
  • Your bank, Google, GitHub, Stripe and registrar logins stay yours. An agent that hits one of them stops and tells you.
  • It will not run on a metered key, even if you paste one. The runner refuses to start without a subscription session.

Pick an agent and switch on only what it may reach. Anything outside its list stops and asks you.

Five small robots working late in a lit glass office seen from a dark lounge, passing files and a bundle of notes down the line, each lit by its own colour

We run our own company on it, every day.

The console on this page is the one we run our own company on, every day. Yours can start with one agent and grow to any size, one flat plan at a time.

Want to see your own ticket run through it?

Bring one real task to the call. We hand it to an agent while you watch, on a plan you already pay.

Book 15 minutes

The three ways to run agents.

A chat window

One thread, one voice, flat price, but you still assign every task.

A shared computer

A weekly allowance, with overage billed by the token, and every agent on one machine with one set of logins. Its own docs tell you not to treat the agents as a security boundary.

KM BOT

Your agents, separate accounts each, running on flat subscriptions pooled behind a router. A blocked task waits at your door instead of failing quietly, and the meter shows what those turns would have cost at public API list prices.

Want to meet Ziv and see it installed in your business?

Tell us what is breaking. When the note arrives, the calendar opens.

On the call we do the whole first setup together:

  1. 01Connect a plan you already pay
  2. 02Name your first agent
  3. 03Hand over its first job

As you want Shay to address you.

Replies come here.

One line is enough.

For the call itself, not for follow-ups.

One task you would hand over this week. Up to 2000 characters.