# kowork.space > A coworking office for your AI coding agents. An app that turns Claude Code, Codex and Antigravity into one team of AI coding agents. It runs on your computer, opens in your browser, and uses the subscriptions you already pay for. kowork.space is an app for Windows, macOS and Linux that runs on your computer and opens in your browser; one command installs it. Each AI coding agent is a person at a desk in a pixel-art office, backed by a real agent CLI: Claude Code (`claude`), Codex (`codex`) or Antigravity (`agy`, Gemini models). You talk to the Boss. A PA decides who does what, the team builds it, and risky work is reviewed by an agent on a different provider. It does not replace the CLIs: it gives them desks, a manager and a way to work together. - Website: https://kowork.space/ - Made by: illsn (https://illsn.com), an independent developer in Navi Mumbai, Maharashtra, India - Support: support@kowork.space - Availability: A one-time purchase with free updates: Single device $9.99 (1 machine), Multi-device $19.99 (up to 3 machines). These are launch prices; after launch they go up to $29.99 and $49.99. Buy at https://kowork.space/#access. ## Key facts - Runs on the Claude, ChatGPT and Gemini subscriptions you already have, through the CLIs you are logged in to. API keys are optional fallbacks. - Local only: the app listens on your own computer. Chats, logs, the task board and API keys stay on your machine. - Every open project is its own office with separate CLI processes, sessions, queues, task board, chat and terminals. - Each agent has a permission mode (Read-only, Ask, Always allow) and On, Pause and Off switches. The fire alarm stops everyone. - The PA that routes work can be Jev (TypeSafe API key) or Laya (a free model installed locally, about 1.5 GB), or the Boss can route by itself. ## Features ### Talk to the Boss You only ever need to talk to one person. The Boss reads your message and either answers, hands it to someone as a task, or turns a bigger request into a project with concrete subtasks. When everything is done the Boss writes the wrap-up. Want someone specific? @mention them and the Boss is skipped. ### Automatic routing and subtasks The PA classifies each message as chat, task or project, scores its complexity and picks who should do it, all in one call. A project becomes structured subtasks, each assigned on its own. If the PA is less than 55% sure, you get "Give it to…" buttons instead of a guess. The PA can be Jev, powered by the TypeSafe API, or Laya, a free model the app installs on your machine. Or skip the PA and let the Boss route. ### Cross-provider review After each delegated task the PA checks whether the result is complete and whether it is risky. Anything rated medium risk or higher goes to a reviewer on another provider automatically, because models from one family share blind spots. The setup wizard seats reviewers on a different provider than the lead engineer whenever it can. ### A task board you can drag onto desks Every project has a board. Drag a card onto someone's desk to give it to them. A task still in To do has an assignee dropdown, so you can overrule the PA: the move is noted in the Boss's chat, the journal and the PA's log. The board, chat and terminal share the right sidebar. ### On, Pause, Off. And Stop all. Pause finishes the current turn and holds the queue. Off kills the whole process tree right away. The fire alarm on the corridor wall switches off everyone in every project at once. Live approvals work the same way: when a Claude agent needs permission for a command, its chat shows the exact command with Allow once, Always allow or Deny. ### Out of office when a quota runs out When a subscription hits its usage limit, everyone on it walks out the front door and their desk gets an OOO tent with the reason and return time. Work is not routed to them until the quota resets, and then they come back automatically. Add an API key and they fall back to it instead of leaving. ## How it works 1. It finds your CLIs. A setup wizard checks which agent CLIs are installed and logged in, and which models each one offers. 2. It proposes a team. Role seats are filled from each CLI's models, with reviewers on a different provider than the lead engineer. You can rename people, swap models and drop seats. 3. You start talking to the Boss. Open a project folder and say what you want. The Boss answers, hands out tasks, or turns a bigger request into a project with subtasks. ## FAQ ### Do I need API keys? No. The agents run through your installed CLIs (claude, codex and agy) on the subscriptions you already have. API keys are optional: add one per provider in Settings → Account and it is used when the subscription runs out, or always, your choice. The PA that routes work can be Jev, which needs a TypeSafe key, or Laya, a free model the app installs on your machine (about 1.5 GB, once). Without either, the Boss routes work itself. ### What happens when my subscription hits its limit? Everyone on that subscription goes out of office: they walk out, their desk gets an OOO tent with the reason and return time, and the PA stops routing work to them. They come back automatically when the quota resets. With an API key configured, that provider falls back to the key instead of leaving. ### Can agents run commands on my machine? Only as far as you allow. Each agent has a permission mode (Read-only, Ask, or Always allow). Claude agents pause and show the exact command with Allow once, Always allow this or Deny. Codex runs inside its workspace sandbox with the network off. Every agent has On, Pause and Off, and the fire alarm stops everyone. ### Where does my data go? Nowhere. The app only listens on your own computer. Project state (chats, logs, the task board, each agent's session, uploads) lives in a .kowork folder inside the project, which is gitignored. Global settings and keys live in the app data folder. The only network calls the app makes itself are the licence check and the update check. ### Does it work with several projects at once? Yes. Each open project is a tab with its own office: the same team at separate desks, with separate CLI processes, sessions, queues, task board, chat and terminals. Closing a tab does not stop running work; the project shuts down once nothing is running. ### What do I need installed? The CLIs you want to use (claude, codex, agy), logged in. On Windows, Node is also needed for the terminal view (it is already there if your CLIs came from npm). Everything else comes with kowork.space: one command installs it, `kowork` starts it. ### It opens in my browser. Is it a web app? It runs entirely on your computer and uses your browser as its window. It listens only on your own machine (127.0.0.1) with a private link, so nothing else on the network can reach it, and your code, chats and keys never go to a server. That is also why it can drive the CLIs you are logged in to. ### How is it licensed? A one-time purchase with free updates. A licence key activates the app on your machine; activation is verified offline for up to 45 days, so you do not need to be online to work. Single-device and multi-device (up to 3 devices) licences are available; for more devices, contact support. ## Notes Claude, Codex and Gemini are trademarks of their respective owners. kowork.space is not affiliated with them.