Skip to main content
Most AI tools give you a chatbot. Rundock gives you a team.
Rundock showing an example agent team as an org chart: a Chief of Staff at the top with the team reporting in below, a Rundock Guide agent, team status in the left sidebar, and scheduled routines at the bottom.

A working Rundock workspace: an orchestrator at the top, the team reporting in, scheduled routines on the left, and the panel where the work happens.

Instead of prompting one assistant repeatedly, you have named specialists with defined roles who delegate work to each other. A content writer who hands research to a researcher. An ops agent who picks up admin while you focus on the work that needs you. An org chart you can read at a glance and a conversation you can watch happen in front of you. The team also keeps what it learns. Skills, knowledge and preferences live as files in the workspace. Teach a workflow once and any agent can use it. Correct something once and the correction is written down instead of forgotten. Nothing resets when a session ends, and all of it is yours to read and change. One beta user described it as having a virtual team of highly paid experts, running in parallel. That is the experience.

​
Who Rundock is for

Built for people who run things, not people who code things. You have set up your own tools before. You have never wanted to live in a terminal. Setup is guided and happens once; everything after it is visual. If you already live in a terminal running Claude Code, Rundock still works, but you are not who it was built for. You run content, ops, sales, admin, and research. When you started, there was nobody else, so the work fell to you. A single chatbot is a single assistant. Useful, but it does not scale with the work. An agent platform built for developers assumes you can write code. Rundock sits between the two: you do not need to write code, and you do not get a single assistant. You get a team you can actually manage. Rundock is built for solopreneurs and small business owners who need leverage without hiring. It is built for the person doing five jobs because there is nobody else to hand them to.

​
How it is different from a chatbot

A chatbot is one role. You write everything you need into one prompt and one context window. The tool forgets between sessions and has no sense of who is asking, what they are working on, or who else is involved. Rundock is a team. Each agent has its own file, its own role, its own instructions, and its own knowledge. When you ask the orchestrator to handle something, it reads the org chart and routes the work to the right specialist. The specialist does the work using its own context and tools. You watch both sides of the conversation, in plain English. The shape of the difference: a chatbot scales by adding longer prompts. Rundock scales by adding more agents.

​
What shapes Rundock

Four principles shape every decision: local-first, markdown all the way down, the human leads and the AI delivers, the team is the unit of value. A fifth, Built from real use, explains why those four exist.

Read the principles

The full version, with what each principle rules out and how it shows up in the product.

​
Where to next

Install Rundock and run through first-run setup. Both take about five minutes.

Install Rundock

Get from zero to Rundock open on your machine.

How Rundock works

The mental model. Useful before you build anything.