Why an AI OS is important and how it is different from other AI tools
Agent harnesses, AI apps and the AI inside your SaaS each help one person with one job. An AI OS is where a company's people and agents work together.
KyoubeAI · · 7 min read
Source available · BSL 1.1 · v1.0.0
Where people and AI agents run the company together.
KyoubeAI is an AI operating system for organisations. It turns the AI you already pay for into AI employees that do the work, and into the systems your business runs on.
Autonomous AI employees
Create and manage AI employees.
An AI employee is a colleague with a role, instructions and a budget. Give one a standing goal and it splits the work into tasks, picks them up on its own schedule, and records what it changed. You decide which harness it runs on, which skills it may use, and how much company data it can see.
Multiplayer environment
People and AI employees in one workspace, at the same time.
Everyone signs in with a role, and AI employees belong to the same companies as the people who hired them. Several people and several AI employees can work one board at once: any task can be owned by a person or by an AI employee, project files refresh as they are written, and a save is refused if the file changed underneath you.
Data
Create your own database and tables, or let AI employees design them.
Files, folders and data tables live in the same workspace. Create what your business needs, and your AI employees read and write it from any task. Nothing has to be exported or synced from another system.
Kyoube App-Artifacts
Need a CRM, ERP or any other system? Ask for it.
Describe the system your business needs and an AI employee builds it. It lands in your workspace ready to use, wired to the same data as the rest of the platform, and your AI employees work inside it alongside your team.
External connectivity
Connect the systems your company already runs.
AI employees reach outside systems through MCP connections. A tool profile decides which tools one can see, and a policy decides whether a specific call is allowed. Your own scripts and services get the REST API that every run already carries, plus webhooks and plugins.
A look inside
Runs, spend and pending approvals at a glance.
Hire, pause and assign agents with roles and budgets.
Every task tracked with an owner, a priority and a next action.
Ask the CEO agent for a plan; it becomes tracked work.
A board app an agent built, published as a page.
Log in to a harness, or run kyoube doctor.
Security
Built for SOC 2 and ISO 27001.
SOC 2
You run KyoubeAI on your own servers. Nothing is sent to us, so the system stays inside the scope your SOC 2 audit already covers. Sign-ins, roles and changes are recorded for your evidence requests.ISO 27001
Roles, a data access level per AI employee, and an audit log of every change. That is the access-control and logging evidence an ISO 27001 audit asks for, and the platform produces it.
Blog
How KyoubeAI Compares
Sourced comparisons with the products people ask about, and notes from running the platform.
Note - Comparison
KyoubeAI vs Claude Code
Claude Code is Anthropic's agentic coding tool. KyoubeAI ships it pre-installed, in a self-hosted workspace with roles, shared data, apps and an audit trail.
KyoubeAI · · 4 min read
- Comparison
KyoubeAI vs Codex
Codex is OpenAI's coding agent for the terminal, the editor and the cloud. KyoubeAI is one workspace for a whole company's people and agents, on your server.
KyoubeAI · · 4 min read
Questions people ask about KyoubeAI.
What is KyoubeAI?
An AI operating system for organisations. People and AI employees share one workspace, with the same roles, tasks and audit trail, and the agents build the company's database and the apps that run on it. You run it on your own server with Docker Compose, or we host it for you in early access.
Is KyoubeAI open source?
It is source-available. The code is published under the Business Source License 1.1: you can read, change and redistribute it, and run it in production for free with up to five users. Each version becomes Apache 2.0 four years after it is published.
How much does it cost?
It is free on your own server for up to five people. Beyond that, a self-hosted licence is US$39 per user a month, billed annually, and the hosted plan, in early access, is US$99 per user a month, 5-seat minimum. AI employees never count as users, and you pay your model provider directly.
What do I need to run it?
A machine with Docker Engine 24 or later and Docker Compose v2, on amd64 or arm64, with at least 4 GB of RAM, plus git and openssl. The agents also need a model: an API key from Anthropic, OpenAI or OpenRouter, or a Claude or OpenAI subscription signed in from the Terminal.
Which agents and models does it work with?
Each agent runs on one of three pre-installed harnesses, Claude Code, pi or Hermes Agent, and you choose the harness and the model for each agent. Models come from your own Anthropic, OpenAI or OpenRouter keys, or from a subscription signed in from the Terminal.
Where does the company's data live?
On your server. Each company gets its own PostgreSQL schema, people and agents reach it through four access levels (none, read, write and schema), and every change is audited. Nothing is sent to us.
Bring your organisation online.
Deploy it once, invite your colleagues, and give the AI employees something to do.
- Clone
git clone https://github.com/jknigel/KyoubeAI.git && cd KyoubeAI - Configure
cp .env.example .env - Run
docker compose up -d --build