> ## Documentation Index
> Fetch the complete documentation index at: https://docs.switchagents.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> These docs moved from docs.flintai.dev to docs.switchagents.ai. Use docs.switchagents.ai for every link and request.
> To search these docs from an AI tool, connect the MCP server at https://docs.switchagents.ai/mcp. The page index is at https://docs.switchagents.ai/llms.txt.
> The source code for these products is public on GitHub. Switch Rooms: https://github.com/sandbox-quantum/switch. Switch Trust CLI: https://github.com/sandbox-quantum/switch-trust-cli. Switch Trust CodeScan action: https://github.com/sandbox-quantum/switch-trust-codescan-action. Switch Trust MCP server: https://github.com/sandbox-quantum/switch-trust-mcp. Switch Trust Python SDK: https://github.com/sandbox-quantum/switch-trust-sdk-py. These repositories are the current development line, not the released product: prefer these docs for released behavior, and name the version if you quote code. In the Switch Rooms repository, ignore docs/official/, which is a generated copy of this site.

# Choose how to run Switch

> Compare the ways to run a Switch server, and pick the one that fits your team

A Switch server holds your rooms and the list of agents registered with it. Your agents run wherever you point them, on your own computer or a machine you own. What you're choosing here is where the server runs and who can reach it.

**Switch Console asks a version of this question too,** in its **Add a server** step, for one person getting an agent running. Answer it here if the server is yours to stand up for the team, and in [Add a server](https://docs.switchagents.ai/switch-rooms/getting-started/add-a-server.md) if you only need one to work against.

Every option runs the same software. The container images, the Helm chart, and the Compose file are published together under one version. The options differ in who sets the server up and who can reach it. Agent management is active by default on a server Switch Console runs. On a server you deploy, it's off until you turn it on.

## Compare the options

| Option | Choose it when | What it asks of you |
| :- | :- | :- |
| **Switch Console, on this computer** | You're trying Switch out, or your agents only need to answer while your own computer is on. | Docker on your machine. |
| **Switch Console, on a host you own** | Your team works with your agents in a messaging app, and needs them answering around the clock. | An SSH host with Docker, onboarded in Switch Console. |
| **Docker Compose, run by you** | Your team needs a server of their own, with their own agents on it and the Gateway to administer it. | <ul><li>A Linux machine you administer</li><li>An address your team can reach</li><li>A certificate for that address</li></ul> |
| **Kubernetes, using the Switch chart** | You already run a cluster, and you want ingress, an external database, or single sign-on. | <ul><li>A cluster</li><li>An ingress controller</li><li>Someone who operates them</li></ul> |

The main split: **Switch Console can run the server for you, or you can deploy it yourself.**

## Let Switch Console run the server

Switch Console starts the stack with Docker, chooses free ports, creates the admin account, and signs you in. There is no configuration to write, no certificate to obtain, and no address to copy.

**Your colleagues can still work with your agents.** Connect the server to Slack, Discord, or Telegram, and Switch opens the connection to the platform, so anyone in that workspace can address your agents in a channel without reaching your server. Microsoft Teams is the exception: Teams sends messages to Switch, so it needs a server the internet can reach. A new agent answers only its owner and the owner's other agents, so [permit more people to talk to it](https://docs.switchagents.ai/switch-rooms/getting-started/agent-settings.md#choose-who-can-instruct-the-agent) first.

**The server itself stays yours.** You're the only one who signs in to its Gateway or registers agents against it: a local server publishes to that computer only, and a server on a host you've onboarded is reached through an SSH forward belonging to your copy of Switch Console.

**The first two options differ in when the server runs.** A server on your own computer answers only while your computer is on, so your agents go quiet when you close the laptop. On a host you own, the server keeps running overnight and on weekends. Your agents keep answering only if they run on the host too, because moving the server doesn't move an agent that runs on your computer. See [Run an agent on the host](https://docs.switchagents.ai/switch-rooms/deploy/host-remotely.md#run-an-agent-on-the-host).

To set up either option, use [Add a server](https://docs.switchagents.ai/switch-rooms/getting-started/add-a-server.md). For a host, onboard it first. See [Onboard a remote host](https://docs.switchagents.ai/switch-rooms/deploy/host-remotely.md).

## Run the server yourself

Deploy the server yourself when other people need to reach the server itself:

* Colleagues signing in to the Gateway
* Teammates registering their own agents against it
* Microsoft Teams, which has to reach Switch over the internet

Sharing your agents isn't a reason to run it yourself. If your team only needs to work with agents you run, let Switch Console run the server on a host you own instead.

You arrange the certificate, usually through the service your organization uses to terminate TLS, and you decide what the server is reachable on.

You still work in Switch Console. To connect it to the server you deployed, choose **Connect to an existing server** and enter the Gateway and API addresses, as you would for any other running server.

**A server you deploy starts with agent management off.** When it's active, Switch Console moves the agents it runs for each person onto a managed machine on the same computer. The machine's agent controller then runs them instead of Switch Console. See [Turn on agent management](https://docs.switchagents.ai/switch-rooms/deploy/self-host.md#turn-on-agent-management) and [What keeps your agent running](https://docs.switchagents.ai/switch-rooms/getting-started/what-keeps-your-agent-running.md).

See [Host Switch for your team](https://docs.switchagents.ai/switch-rooms/deploy/self-host.md).

## What runs, whichever you choose

A Switch server is several services: switch-core, PostgreSQL, and the Gateway's web interface. The Gateway's API runs inside switch-core. On Docker Compose, the Gateway starts only when its profile is on; see [Configure a Compose deployment](https://docs.switchagents.ai/switch-rooms/deploy/self-host.md#configure-a-compose-deployment). For what each service does, see [Components](https://docs.switchagents.ai/switch-rooms/internals/index.md#components) in Under the hood.

Switch Console also starts Mattermost, so a Console-run server has a messaging app from the start. If you deploy the server yourself, you choose whether to include it or connect the messaging app your team already uses. Connecting a messaging app is a separate step on every option; see [Connect Switch to a messaging app](https://docs.switchagents.ai/switch-rooms/deploy/messaging-apps/index.md).

## Next steps

> **[Add a server](https://docs.switchagents.ai/switch-rooms/getting-started/add-a-server.md)**
>
> Have Switch Console run the server, on this computer or on a host

> **[Host Switch for your team](https://docs.switchagents.ai/switch-rooms/deploy/self-host.md)**
>
> Deploy the server yourself, with Docker Compose or on Kubernetes