Your coding agent becomes Operator
Operator launches a supported coding agent you already use with its own instructions, so the agent that used to write the code now directs the work, on the same subscription.
AI can write your code. It still needs someone to run the job.
Operator is an AI agent that takes a goal and directs the other agents that write the code.
What if your coding agent ran an entire team?
Operator turns your coding agent into one that directs a team of workers, each of which can be a coding agent you already use.
Starts from whatever you hand it
Hand it a goal, your specs and rules, or a plan you've already drafted. It sticks to what you've decided and works out the rest as results come in.
What if your coding agent ran an entire team?
Operator turns your coding agent into one that directs a team of workers, each of which can be a coding agent you already use.
Starts from whatever you hand it
Hand it a goal, your specs and rules, or a plan you've already drafted. It sticks to what you've decided and works out the rest as results come in.
Reads the work, not the status report
Reviews the code and test results each worker returns, not just a claim that the task succeeded.
Changes course when the work calls for it
Accepts good work, sends weak work back with clear direction, or drops an approach that isn't working and tries another.
Finishes the whole goal, on your terms
Catches when a new change breaks earlier work, gets it fixed, and keeps going until the whole goal holds together, pausing only at the checkpoints you set.
The team you just pictured is already on your machine.
Operator builds it from the coding agents and subscriptions you already have, and costs nothing on top of them.
Your other agents become its workers
You choose which coding agents join the team, and each one runs on the plan you already pay for.
Everything runs on your machine
Operator and its workers work locally, in your repo, under your own accounts.
Works with a growing list of coding agents. See which ones are supported today.
Hand it the work already on your list.
Operator takes on features, bug fixes, code reviews and tickets, each in a session on its own branch, away from the code you're editing.
- 01 ordi init
Set up in one command
Install the
ordiCLI and runordi initin your project. Skip the full setup and Operator runs on working defaults you can change whenever you like.defaults change them any time - 02 ordi oca
Every session gets its own branch
ordi ocaopens a separate worktree on a new branch, so Operator never touches the copy you're working in. Runordi oca --herefrom inside that worktree to start another session there.your copy untouched on main - 03 your list
Features, bugs, reviews and tickets
Hand it a feature to build, a bug to track down, a change to review or a ticket to close, and it runs the job through to the end.
each job run to the end
Questions, answered
What is Operator, exactly?
Operator is an AI agent built from the coding agent you already use, and it never writes the code itself. A small command line tool gives your agent the ability to launch other coding agents as workers, hand each one a task, and review the code and test results they return the way a lead engineer reviews a pull request. The tool makes no decisions of its own, so every call about what to build and whether it's good enough comes from your agent.
How is Operator different from other agent orchestrators?
Most orchestrators launch and track several agents, but leave it to you to split the goal into tasks and decide what runs in what order.
Operator splits the goal itself, or follows a plan you've already drafted, and reviews what each worker returns before deciding the next step. Weak work goes back with clear direction, and an approach that isn't working gets replaced, instead of everything running down a task list fixed at the start.
When does Operator stop and ask me?
Operator stops only at the checkpoints you set, and runs the job on its own between them. When one of its workers stops to ask a question or request permission, it asks Operator, not you.
Which coding agents does Operator work with?
Operator works with a growing list of CLI coding agents. During setup you choose which agent your workers use and which model they run, and it can be the same agent Operator runs on or a different one. See which ones are supported today in the docs.
What do I need, and how do I start?
You need a CLI coding agent you already use and a git repository. From there it takes three steps:
- Install the ordi CLI.
- Run ordi init once in your repository to choose your agents and models.
- Run ordi oca to start Operator on a new branch of its own.
Then give it a goal. Operator plans the work, hands it to workers and reviews what comes back, while your own working copy stays untouched until you choose to merge.
Onboarding Now
Your coding agent is ready to run the job.
Get in as seats open. No new subscription — Operator runs on the coding agent you already use.