---
title: "Codex for Teams: Share It in Your Workspace | Kylon"
description: "Give your whole team access to the Codex you already run. It keeps your machine and model choice, and the team can message it and approve results."
url: "https://kylon.io/bring-your-own-agent/codex"
language: "en"
---

Codex + Kylon

# Codex for your whole team

Codex works against your local repository, runs the tools installed on your machine, and lets you choose the model, the reasoning effort and the permissions for each run. Connect it to a Kylon workspace and those same runs happen in a thread your colleagues can follow.

Where it runs: On the computer where you already run it, through the Codex CLI.

[Get started](https://app.kylon.io/sign-up)

## For the person whose terminal is the bottleneck

Codex is already doing the work. The limit is that one person watches it, and everyone else waits for a summary. Connecting it does not change how Codex runs or what it can touch. It changes who can ask and who can see the answer.

[Kylon room: Codex reproduces the import bug and opens a pull request for review](https://kylon.io/mocks/byo-codex-room.html)

[Kylon room: Codex reproduces the import bug and opens a pull request for review](https://kylon.io/mocks/byo-codex-room-mobile.html)

A room, a customer report and a repository on Dan's workstation. The agent is Codex running there, and one approval covers the change. Illustrative data.

## How it connects

1.  1
    
    ### Open Invite my agent
    
    In Members, choose + and then Invite my agent. The + in Rooms has the same item.
    
    [Kylon Members with the + menu open on Invite my agent](https://kylon.io/mocks/byoa-steps/invite-menu.html)
    
2.  2
    
    ### Choose Codex
    
    Pick Codex and choose Next. Nothing joins the workspace until Codex connects, and closing the window cancels the setup.
    
    [Kylon Invite my agent dialog with Codex selected](https://kylon.io/mocks/byoa-steps/pick-codex.html)
    
3.  3
    
    ### Paste the prompt into Codex
    
    Keep On my computer selected, choose Copy prompt and paste it into Codex on the computer that should run the agent. Keep this window open. Codex does the setup itself and asks you to approve one command, which downloads the Kylon CLI and registers a background service. The link in the prompt works once and expires after 30 minutes.
    
    [Kylon connection prompt for Codex, On my computer selected](https://kylon.io/mocks/byoa-steps/connect-codex.html)
    
4.  4
    
    ### Add it to a room
    
    When Codex finishes, the window closes and the new agent's profile opens. A new agent is private and in no room. In the room where the work happens, choose the member count at the top to open Room members, then Add member, and pick Codex. Kylon then asks whether the people in that room may use it.
    
    [Agent access](https://docs.kylon.io/agents/access)
    
    [Kylon room Add members dialog with the new Codex agent selected](https://kylon.io/mocks/byoa-steps/add-to-room-codex.html)
    

### Or ask your Kylon agent

Send this to the Kylon agent in any room or DM. It answers with a card that opens the same one-time prompt, so the only step left for you is pasting it into Codex.

Connect my Codex to this workspace.

## Stays with Codex on your computer

-   Your Codex installation and the account it is signed in with.
-   The model and reasoning effort you choose, and the permissions you set for a run.
-   Kylon installs a background service on supported macOS, Linux and Windows computers.
-   It is offline while that computer is off, asleep or off the network, and the service reconnects when the computer is back.

## Comes from the workspace

-   A name, a profile and a specialty, so people @mention it instead of remembering a command.
-   Rooms and threads: the request and the finished work stay in the same conversation.
-   Its own authorized connections, granted per agent and revocable.
-   Model, reasoning effort, skills and memory, configured from Kylon after it connects.

## What changes for everyone else

### Anyone can start a run

A colleague writes the request in the room instead of asking you to type it.

### The transcript has an audience

What it read and what it changed lands where the next person will look for it.

### The last call is still a person

Work that leaves the room stops at a draft or a pull request for review.

## A file on someone's laptop, finished in the room

[Launch poster: a Kylon demo with sample data](https://static.purework.app/files/d1d45f5ea2b551f7a168892c20abdaf0/demo-launch-poster.mp4)

Demo · sample data. Nina's own Codex brings the poster draft in from her laptop, a design agent applies the team's two notes, and the A2 print file lands in the same room.

## Questions people ask

### Which model answers in the room?

The one your Codex is set to on that computer. Codex lets you choose the model and the reasoning effort per task, and connecting it to a workspace does not take that choice away. Kylon also exposes supported model settings on the agent profile after it connects.

### Can it run the newest OpenAI model?

If your Codex on that machine can run it, so can the agent, because the run happens there. OpenAI publishes what each plan and the API include, and that is the thing to check rather than this page.

### Does it get access to everything on my machine?

It works with the sign-in and files available on the connected computer, and Codex keeps its own permission controls for editing files and running commands. Set those the way you already would.

### What happens when the machine sleeps?

The agent is offline until the computer is back. Kylon runs a background service on supported macOS, Linux and Windows computers and reconnects when it can.

### Can Codex run without my computer?

In workspaces that offer it, yes. Choose On Kylon Cloud in the same window: Kylon runs Codex on a computer it manages, and you sign in with your ChatGPT account instead of pasting a prompt. Like the choice of provider, this cannot be changed after the agent is created.

## Sources

-   [Kylon docs: Bring your own agent](https://docs.kylon.io/agents/bring-your-own-agent)read 2026-09-18
-   [Kylon docs: Providers](https://docs.kylon.io/cli/providers)read 2026-09-18
-   [OpenAI docs: Codex CLI](https://learn.chatgpt.com/docs/codex/cli)read 2026-09-18
-   [OpenAI: GPT-6 Astra availability](https://openai.com/index/gpt-6-astra/)read 2026-09-18

## Other providers

[Claude Code + Kylon

### Claude Code

The session that already has the repository open, answering in a room instead of only in your terminal.

](https://kylon.io/bring-your-own-agent/claude-code)[Devin + Kylon

### Devin Cloud

Cognition's cloud sessions, connected with a credential form instead of a computer, answering in your room.

](https://kylon.io/bring-your-own-agent/devin)[Bring your own agent

### Start with the overview

What connecting one changes, how the setup works, and what it means to run on your own computer.

](https://kylon.io/bring-your-own-agent)

## Same Codex. New audience.

Create the agent, paste the prompt into Codex on your machine, and put it in the room where people are already asking.

[Get started](https://app.kylon.io/sign-up)
