Skip to content

Preview — not open to the public yet. Accounts are created on request.

Drawing № 02 — agents that run without you · Switzerland

AI agents that keep working after you close the tab.

A ZeroLog agent runs in your own Linux container, on the server, not in your browser. You give it a condition that means “done”, and a separate model reads each round and decides whether that condition is met. Every command can wait for your approval, and every run leaves a log with its state and its cost.

Request access └─ how it knows it is done

Sheet 01 — the stopping rule

The agent does not decide when it is finished.

Type /goal and the condition, for example “pytest reports 0 failed”. After every answer a second, smaller model reads the conversation and rules on one question: is the condition true? If not, it says what is missing, and the agent is called again with that reason. The loop runs on the server, so closing the tab does not stop the next round. In the chat, /goal is limited by rounds, not by the clock.

Write a condition the checker can see in the chat: a test count, a build without errors, a file that has to match. “Make it better” never becomes true.

/goal in the docs

FIG 1.1 — one round, and the four ways out
  1. agent works in the container
  2. checker reads the conversation since the goal was set
  3. not met the reason goes back to the agent

stops when

  • met the condition is true
  • impossible a blocker only you can clear, such as access you have to grant
  • stalled the same gap four rounds in a row
  • capped 25 rounds by default
├ condition up to 4000 characters ┤ not available in anonymous chats

Sheet 02 — more than one agent

Split the work, then let two reviewers try to break it.

Switch a chat to /ultracode and the model may hand a large task to several agents in your container when that is faster than doing it alone. It decides when; a short question still gets a short answer. After an agent finishes its part, two reviewers go through the files it changed, one looking for what is wrong and one for what is missing. A part they reject goes back for a fix before you see it.

Several agents on one task means several model bills. Use it where a wrong answer is expensive: an audit, a migration, a review before a release.

/ultracode in the docs

Sheet 03 — what it may do without asking

You decide which commands run unattended.

Approve each command

Every command the agent wants to run appears in full and waits. Approve runs it once, Deny tells the model you said no, and you can edit the command before it runs. Leave a request for 5 minutes and it expires; the agent stops there and sums up what is left.

Approvals in the docs

Standing permissions

Grant routine actions once and they run without asking; anything outside a grant waits in a queue for you. Grants are explicit and can be revoked. Moving money is not a permission you can give: it is refused every time.

Automation in the docs

A report afterwards

Each long run shows up under Jobs with its state and its log. Follow it live or read it the next morning, and see what that particular run cost.

Jobs in the docs

On a schedule

Give an agent a task and a time: a nightly build, a daily check, a weekly summary. Schedules follow your timezone, and every run leaves a log.

Scheduled tasks in the docs

Sheet 04 — where it runs

A container you have root on, not a sandbox that forgets.

The agent works in the same Linux container you use yourself: installed packages stay, files stay, and from Mini upwards a service it starts keeps answering on a subdomain you pick. Containers run isolated from every other account. A plan sets how big the machine is and how long one background job may run.

Containers · Isolation · Plans

FIG 4.1 — run time for one background job

per plan

  • Free · CHF 01 hour
  • Mini · CHF 4.504 hours
  • Pro · CHF 13.5012 hours
  • Max · CHF 45.00no limit
└─ prices a month, prepaid models are paid from credit

Sheet 05 — what a run costs

The plan pays for the machine. Each model call is paid from credit.

Model tokens cost the provider’s rate plus 2 %, taken from your ZeroLog credit, and the figure under each reply is the figure you are charged. When the credit reaches zero, paid models stop; nothing is billed afterwards. Set a spending limit if you want an agent to stop earlier.

Cost per reply · Credit and top-ups · Spend limits

Sheet 06 — the details

Everything on this page, one topic at a time.

Hand it the job, and read the log in the morning.

Free needs no card and includes background jobs of up to one hour. Accounts are created on request while ZeroLog is in preview.

Request access └─ compare plans