Orca ADE Tutorial: Every Feature Explained (2026)

If you want an orca ade tutorial that actually covers every feature rather than the first five minutes, this is the one.

Orca is a free, open-source agentic development environment.

I have been running it as my main build surface for parallel coding agents, and there are far more features in it than the download page suggests.

So this post is a reference.

Feature by feature, what it does, how to switch it on, and when it is worth using.

The Whole Feature Set At A Glance

Before the detail, here is everything Orca gives you in one table.

Feature	What it does	Why it matters
Split terminals	Runs several agents on one project	Parallel work instead of one slow queue
Live browser preview	Renders your localhost inside Orca	You see the build as it happens
Element select	Sends one exact element to the agent	Precise feedback, fewer misunderstandings
Annotations	Queues many changes and sends them together	Batch edits in a single pass
Mobile emulator	Xcode or Android Studio preview	Build and check mobile apps properly
Orca Mobile	Connects your phone by QR code	Drive your projects away from the desk
Automations	Schedules recurring agent tasks	Work carries on in the background
Computer use skill	Agents control any app on your machine	Agents stop being trapped in the editor
Orchestration skill	Agents coordinate with each other	Several agents without the collisions
Voice	Speak to your agents	Useful for some, I do not use it

Now the detail on each one.

🔥 Want the full agent stack, not just the IDE? Inside the AI Profit Boardroom I hand members the Agent OS zip, 1,000+ done-for-you agent workflows, and daily tutorials on exactly this kind of build. Weekly live coaching calls, 2,800+ members. → Get access here

Feature 1: The Environment Itself

Orca is an agentic development environment rather than a code editor with an assistant bolted on.

You get it from the Orca GitHub repo and download the app.

Once it is open, you are looking at terminals, a live preview and an automation panel.

The framing matters, because it explains every design decision that follows.

This is a control room for agents, not a place you are expected to type code yourself.

It is free and open source, which means the environment adds zero cost to whatever agents you already run.

Feature 2: Project Loading (Three Routes In)

You get three ways to open a project, and all of them take seconds.

You can browse to an existing folder already on your machine.

You can clone directly from a GitHub URL.

You can create a brand-new project from scratch.

I default to the GitHub clone because the agents then start with the whole repo structure and history in front of them.

Feature 3: Agent Selection

You pick which coding agent runs in each terminal.

Claude Code, Codex, Hermes, Kimi, OpenClaw and Antigravity all work, among others.

You add, enable and disable agents in the settings, which is what makes the tool genuinely agent-agnostic.

That is a bigger deal than it sounds, because it means you are never locked to one vendor's pricing or one model's weaknesses.

If your budget is the constraint, my write-up on running Claude Code for free is the fastest way to fill your first pane.

Feature 4: Split Terminals (The Feature That Changes Everything)

Right-click in the terminal and choose split terminal right, or split terminal down.

Do it a few times and you have four agents working the same project at once.

I have had Claude Code in one pane and Hermes in another, and you can add Kimi, Codex, OpenClaw or Antigravity to the remaining panes.

Each pane is its own agent, all pointed at the same codebase.

The practical effect is that your throughput stops being limited by one model's speed.

One agent can be building a page while another writes the backend and a third fixes something that broke.

This is the same logic behind running agent swarms with Kimi, just packaged into a desktop workspace.

Feature 5: The Two Free Routes

Orca being free is only half the story, because the agents inside it normally are not.

There are two honest routes to a zero-cost setup.

Route 1: Existing subscriptions

If you already pay for Codex, Claude Code or OpenClaw, connect them and you are done.

Orca itself is free and open source, so your bill does not move by a single pound.

Route 2: Free agent plus free API

No subscriptions at all? Use a free agent with a free API.

In my own run I used Hermes with a free API — Ling flash — and it genuinely cost nothing.

People always tell me it is not really free.

It is. Free agent, free API, free environment.

And the surprise is worth repeating.

I gave both setups the same prompt — create a beautiful website for an SEO agency — and on that run the free Ling 3.0 output looked a little nicer than the Claude Code version.

One test, one day, not a league table.

But it is a decent reason to stop assuming free means worse before you have tested it on your own project.

Feature 6: The Live Browser Preview

Writing code is half the job, and seeing it is where Orca earns its place.

First you need a localhost URL for your project.

If you do not have one, ask the agent you are coding with to give you one.

Then click the plus sign at the top and choose new browser tab.

Paste the localhost URL, and your project renders right there inside Orca.

You are now watching the real site while the agents keep working on it, which shortens your feedback loop to almost nothing.

Feature 7: The Mobile Emulator

If you are building a mobile app rather than a website, you open a mobile emulator instead of a browser tab.

That means an Xcode emulator or an Android Studio virtual device.

One of those two is required for mobile previews, so factor that in before you start a mobile project.

For a website, a game or a tool, the plain browser tab covers everything.

Feature 8: Element Select

This is the feature that saves me the most time in a week.

Instead of describing a change in words and hoping the agent finds the right part of the page, you point at it.

You do not like the logo, so you select it, paste it into your coding agent, and give feedback on that one element.

There is no ambiguity about which thing you mean.

Most wasted agent turns come from the agent editing the wrong component, and this removes that failure mode entirely.

Feature 9: Annotations And Intent

Right-click anywhere on the preview and describe the change you want.

"Make the headline bright yellow" is enough.

Then you choose your intent, and this is the bit people miss.

A command means change this now.

A question means what would work better here?

That difference matters more than it sounds, because sometimes you want action and sometimes you want the agent's opinion before anything gets touched.

I use questions far more than I expected to, especially on design work where I do not have a fixed answer in mind.

Feature 10: The Annotation Queue

Adding an annotation does not fire it off immediately.

That is a deliberate design choice and it is the right one.

You can mark up ten things across the page, then hit send once, and the agent works through the whole list.

No waiting for one change at a time before you can request the next.

In practice this turns a twenty-minute back-and-forth into a single pass.

🔥 Want to see this workflow run end to end? Inside the AI Profit Boardroom I record the full builds — agent setup, free API configuration, and the annotate-and-batch loop — as step-by-step tutorials. Plus 5 live coaching calls a week. → Get the free agent build stack here

Feature 11: Orca Mobile

You scan a QR code with your phone and you can then run your terminals and projects from it.

I have not put this through its paces properly yet, so I am not going to oversell it.

What I will say is that I have tried remote coding through other tools and found it consistently underwhelming.

Being able to drive several agents across several projects from a phone is a better shape of idea than the single-chat remote apps I have used.

Feature 12: The Automation Panel

The automation panel lets you schedule recurring agent tasks.

You can have an agent iterate and improve a project every day.

You can have it research a topic and draft a post on a schedule.

The honest catch is that your computer needs to be running for scheduled work to fire.

This is local scheduling, not a cloud cron job, so treat it as a desk-hours automation rather than a server.

Feature 13: Installable Skills

Two skills are worth enabling straight away, and you install them from the terminal by pressing enter.

Computer use lets agents control any app on your machine, which is the one that turns a coding agent into something closer to a full assistant.

Orchestration lets agents coordinate rather than duplicate each other's work, which matters a lot once you are running four panes.

There is voice in there as well, though I do not personally use it.

If computer use is new to you, my breakdown of OpenClaw's computer use covers what that capability looks like in practice.

Where Orca Stops And An Agent OS Starts

Orca is excellent at being an environment for parallel coding agents.

It is not trying to run your whole business, and I would not want it to.

That is the job of an Agent OS — the wider agentic operating system where Hermes runs with shared memory, a mission-control dashboard, and skills for content, SEO, research and publishing.

Use Orca when the work is building software.

Use the Agent OS when the work is running the business around it.

They complement each other rather than overlapping, which is why I run both.

Frequently Asked Questions

Is Orca really free?

Yes. Orca is free and open source. You either plug in subscriptions you already have, or run a free agent with a free API such as Hermes with Ling flash. Neither route adds cost to what you were already spending.

Which agents does this orca ade tutorial cover?

Claude Code, Codex, Hermes, Kimi, OpenClaw and Antigravity among others. You add, enable and disable them in settings, and you can run several at once in split terminals.

What does element select actually do?

It lets you grab one specific element on the live preview and send it straight to your coding agent, so your feedback applies to exactly that element and nothing else.

What is the difference between a command and a question annotation?

A command tells the agent to make the change. A question asks the agent what would work better instead. You pick the intent when you create the annotation.

Do I need Xcode or Android Studio?

Only for mobile app previews, where one of the two is required. Websites, games and tools preview in a normal browser tab inside Orca.

Do Orca automations need my computer switched on?

Yes. Scheduled agent tasks only run while your machine is running, which is the main limitation of the automation panel.

About Julian

I'm Julian Goldie — AI entrepreneur, SEO expert, and founder of the AI Profit Boardroom (2,800+ members). I help business owners scale with AI agents, automation, and SEO.

400K+ YouTube subscribers
7-figure AI agency (Goldie Agency)
Daily training inside the Boardroom
Author of multiple AI automation playbooks

→ Get my best AI training inside the AI Profit Boardroom

Also On Our Network

The Verdict

Every feature in this orca ade tutorial points at the same idea: you direct, the agents type, and you correct them visually instead of in prose.

Split terminals give you parallel output.

The preview plus element select plus the annotation queue give you precise, batched control.

Orca Mobile, automations and the installable skills extend that beyond your desk.

Run it on subscriptions you already have, or run it completely free with Hermes and a free API, and this orca ade tutorial costs you nothing but the afternoon it takes to learn.

📺 Video notes + links to the tools 👉

🎥 Learn how I make these videos 👉

🆓 Get a FREE AI Course + Community + 1,000 AI Agents 👉