The AI-Native Accelerator: the first cohort starts later this month. Find out more

Rundock gives you an AI team,
with roles, a lead and a way of working.

Run it from one visual workspace. The team lives in files you own, and nothing it learns resets.

Free for macOS and Windows. All download options.

Rundock is free. Bring your own Claude Pro or Max subscription. Add a ChatGPT plan if you want specialists on Codex.

Rundock showing an example agent team as an org chart: a Chief of Staff at the top with the team reporting in below, Doc the Rundock Guide beneath a divider, and live team status in the sidebar.

You're doing the work of five people.

You run content, ops, sales, admin and research. When you started, there was nobody else, so the work fell to you. You're the CEO and the copywriter and the person who remembers to send the invoice. Your working week is full of work that isn't yours to be doing.

Existing AI tools haven't solved this. A single chatbot is a single assistant. You still have to hold the context, remember the process and redo the work each time. Agent platforms built for developers assume you can write code. You shouldn't have to. Rundock gives you a team you can actually manage.

Built for people who run things. If you've set up your own tools before, you can run a team.

What people are saying

Rundock removed the intimidation of Claude Code. You stop thinking in coding terms and start thinking in team terms. It's like having your own virtual team of highly paid experts, running in parallel. I've built my entire business DNA in the box.
James Compton
James Compton Founder, Limitless Coaching
My previous AI stack was advanced but not cohesive. Every tool had its own context. With Rundock the context is shared, but each agent keeps their skills. I think of an agent I need and I build, hire, create. I see this running my entire business. This is a true operating system.
Patrick Giwa
Patrick Giwa Founder, AI Impact

Your team.

A lead who delegates, specialists who deliver and a team that keeps what it learns.

Rundock conversation: the user asks Cos to make the landing hook shorter, Cos passes the work to Cleo, and Cleo joins and replies with two shorter options.
Rundock org chart turned on its side: Cos the Chief of Staff on the left, six leads in a column beside it, and the Content Analyst and Code Reviewer beside their leads.
Rundock agent profile for Dev, the Engineering Lead: a role description, a New conversation button, three attached skills, a nightly routine, and the model and runtime.
Rundock skill page for Code Reviewer: its description, the two agents who use it, and a button to schedule it as a routine.
Rundock routines: five scheduled skills across the team, each showing who runs it, when it last ran and when it runs next.

Your work.

Everything the team makes opens where you can read it, review it and find it again.

A markdown note open in Rundock: its properties as a panel with tags as chips, a callout, clickable wikilinks, and the workspace file tree beside it.
An HTML page open in Rundock as the finished page, with two numbered review comments beside it, one with a reply, each with Reply and Resolve buttons.
A Kanban board in Rundock with Backlog, In Progress and Done columns, tagged and dated cards, and three ticked-off cards under Done.
Rundock Map: the workspace drawn as a graph, with clusters of linked notes, unlinked files scattered around the edge, and recently changed files brightest.

Make it yours.

Add agents and new views from a link, and decide how much your team asks.

Rundock Pins: four pinned files in the sidebar, an investment dashboard first and open beside them, drawn by an extension with portfolio totals, an over-limit warning, an allocation chart and a risk control panel.
Rundock Settings open at Permissions: Code mode selected, agents kept inside the workspace by the macOS sandbox, and one extra folder they can also change.

Browse the Directory

The org chart shapes itself around your business.

Every team is different. Your org chart matches what you actually do, top-down or on its side for a deep team.

Rundock org chart for a consulting business: multi-level hierarchy with content, sales, delivery and research leads
A consulting business A multi-level team with content, sales, delivery and research leads, each with their own specialists.
Rundock org chart for a coaching business: eleven-agent team covering content, strategy, coaching, finance, sales, design and product
A coaching business An eleven-strong team covering content, strategy, coaching, finance, sales, design and product.
Rundock org chart for a school: school director with four specialists running curriculum, lesson creation and marketing
A school A school director and four specialists running curriculum, lesson creation and marketing.

Your work stays on your computer.

Rundock keeps your files, agents and history on your machine. Only the conversation you're in goes to your AI provider, under your own subscription.

Browser or app

Visual interface for your agent team. Org chart, conversations and workspace files.

Local server

Discovers agents, manages conversations, reads your workspace files.

Two runtimes

Claude Code or Codex, on your own subscription. Only the active conversation is sent.

Free. No account. Yours to keep.

Nothing to pay, no signup and no telemetry. Your agents and skills are plain markdown files you can take anywhere.

Free download

Want a pre-built team to get you started?

The Lean Agent Team gives you a Chief of Staff, an EA and a Content Lead: three agents ready to install today.

Download the Lean Agent Team

Free · No account required · Works in Rundock out of the box

"I was wearing every hat.
So I built a team that wears them with me."

Liam Darmody, founder of Rundock

Liam Darmody

Product advisor, executive coach, AI builder

Before Rundock, I was running five things at once. Content, clients, marketing, research, admin. Posts were going up later than I wanted. Client work was eating into evenings. Research I'd meant to read had been sitting unopened for weeks. There was only one of me, and the maths had stopped working.

I started building Rundock because my first child was on the way and time was about to compress. I needed more output from the same hours. So I tried as many AI tools as I could. They were either too complicated or just gave me one assistant. What I needed was a team. The day a beta user sent me a screenshot of his own org chart, I knew the metaphor had clicked. This was closer to hiring people than to chatting with a model.

Today, I still work most days. The difference is what I'm doing in those hours. Cos has the morning briefing waiting. Penn has hooks and a draft for me to push back on. Arlo's weekly digest lands on Saturday whether I open it or not. I set the direction and edit the work. The team keeps it moving. That's what Rundock is for.

Get the Lean Agent Team, free Take the AI Readiness Scorecard How I help businesses build their AI systems

Something you talk to, or a team you run.

Rundock runs a team on the subscription you probably already pay for. Here's how it compares.

ChatGPT or Claude on its own: one assistant that forgets how you work. Rundock adds a team on the same subscription.

Obsidian or Reflect: they hold what you know. Rundock puts a team to work on it.

Notion: their agents live in their cloud. Yours live in your folder.

Claude Code, OpenClaw, CrewAI: engines. Rundock is the car, and you don't need to be a mechanic.

Your team is plain files you own. It runs on Claude Code or Codex today, and on whatever comes next, without a rebuild.

Get started.

You don't need to write code. You need Rundock, Claude Code and a folder to call your workspace.

Free for macOS and Windows. All download options.

The app walks you through setup. It uses Terminal twice: to paste the one command that installs Claude Code, if you don't have it yet, and in a window Rundock opens to connect your Claude account. After that, your day happens in Rundock.

01

Download Rundock for Mac or Windows

One file. Open it and it runs.

Rundock runs on Claude Code, and needs a Claude Pro ($20/mo) or Max ($100/mo) subscription. The setup wizard gives you the one command that installs Claude Code, or you can run it now:

curl -fsSL https://claude.ai/install.sh | bash

On Windows, the wizard gives you the PowerShell version. Specialists can also run on a ChatGPT plan via the official Codex CLI.

On Linux? Run Rundock from source.

02

Choose a workspace

Point Rundock at any folder on your computer. That folder becomes your workspace. Your agents, files and conversations live there.

03

Build your team

Doc, your platform agent, walks you through building your first agents. Named, configured and ready to work in under ten minutes.

Your org chart is yours. People ask about it.

Common questions

What does Rundock cost?

Rundock is free. You'll need a Claude Pro ($20/mo) or Max ($100/mo) subscription for the AI processing, since Rundock runs on top of Claude Code. Add a ChatGPT plan if you want specialist agents on Codex too. That's the total cost.

What if I'm not technical?

If you can describe what you want, Rundock can build it. You'll spend more time naming your agents than writing code. Doc, the built-in platform agent, walks you through setup and builds your first agents with you.

Why not just use Claude Code?

Claude Code is one engine, and it ties your team to a single provider. Rundock runs the same team across Claude Code and Codex, and lets you move between them without rebuilding. You keep the org chart, the coordination, and the files you own. When a better engine comes along, your team is ready to run on it.

Is Rundock a harness or an orchestrator?

Neither: Rundock runs on harnesses. Claude Code and Codex are the harnesses; they own the agentic loop, tool execution and context management, and they improve without Rundock lifting a finger. Rundock is the layer above: the workspace where a team of harness-run agents is built, managed, observed and improved. If you want a word for it, it's an orchestration layer, but the orchestration primitive is delegation between named agents on an org chart, not a graph you program.

Do I have to design agent graphs or loops?

No. In Rundock the org chart is the graph: roles are the nodes, delegation is the edges, and the loop belongs to the harness. You get what multi-agent graphs exist for (specialisation, parallel work, handoffs, human approval gates) through a structure any manager already understands. Reorganising your team is dragging a reporting line, not a refactor.

How does Rundock relate to best practices for working with AI?

It makes them structural instead of disciplinary. Context engineering: every specialist has a small, role-scoped context, because that's what an agent file is. Reusable procedures: skills are files. Persistent memory: legible markdown you can read and correct, not an opaque store. Human in the loop: the permission model and the review flow. Observability: delegation happens in front of you. You don't follow the best practices. You get them by default.

Where does my data live?

On your machine. Rundock keeps your files, agents and history on your machine. Only the active conversation is sent for processing: to Anthropic via Claude Code, or to OpenAI via Codex if you run specialists on your ChatGPT plan.

Can I bring my context from ChatGPT, Notion, or Claude?

Your workspace is plain markdown files. If you have notes elsewhere, copy them into your workspace and your agents can read them straight away. No import tool, no migration step.

Can my agents work on a schedule?

Yes. Set up routines so your team runs on its own. The weekly research digest, the Monday content review, the overnight email triage. Pick the schedule, walk away, get the output when it's ready.

Does my computer need to be on?

Yes. Your team runs on your machine; when the machine is off, so is the team. Routines run while Rundock is running. A guide to giving your team an always-on home of its own is on the roadmap.

Is this another tool I have to babysit?

There's nothing to host and nothing to maintain beyond updating the app. The team runs when you ask it to, every action that matters asks permission, and the org chart shows you everything at a glance. Rundock is where you already work, not another service to keep alive.

What if Rundock stops being maintained?

Your workspace is yours. Agents and skills are markdown files you own. The code is source available. Worst case, you keep using whatever version works on your machine, or fork it, or take your agents to any tool that supports the Claude agent format.

How long until I'm up and running?

Around an evening. Install Claude Code (10 minutes). Download Rundock and pick a workspace folder (5 minutes). Talk to Doc and let him build your first three agents (30 to 60 minutes). You're running.

Stay close.

Join my newsletter for notes on building and running a team of AI agents. Free.

Sign up at liamdarmody.com