---
title: "Environments"
description: "Choose a deployment environment for Vellum: Vellum Cloud (recommended), local, or user-hosted (GCP/AWS/custom), with trade-offs for each."
canonical_url: "https://www.vellum.ai/docs/environments"
md_url: "https://www.vellum.ai/md/docs/environments"
related:
  - "/docs"
  - "/docs/constitution"
  - "/docs/data-sharing"
  - "/docs/developer-guide"
  - "/docs/extensibility"
  - "/docs/getting-started"
  - "/docs/glossary"
  - "/docs/help"
---

# Environments

## Overview

An environment determines where your assistant runs. By default, assistants run in **Vellum Cloud**, our managed platform, so you can sign up and go without managing any infrastructure. If you'd rather host the runtime yourself, you can run it locally on your Mac or deploy it to your own GCP, AWS, or custom Linux host. The environment you select affects latency, availability, resource limits, and how much control you have over the underlying infrastructure.

For self-hosted runtimes, you can specify the environment during hatch using the `--remote` flag:

`vellum hatch --remote <local | gcp | aws | custom>`

## Architecture

The following diagram shows how the different environments relate to channels and external providers:

![Architecture diagram showing the relationship between channels, environments, and external providers](/architecture-diagram.png?dpl=62fff8f2ae0aa281d28d0ba8ecc0bcd427ad18c1)

## Vellum Cloud (recommended)

Run your assistant on Vellum's managed platform. No cloud accounts or server management required, just sign up and go.

Vellum handles provisioning, upgrades, scaling, and infrastructure so you can focus on using your assistant. Managed assistants use Anthropic (Claude) as the default provider, billing is handled through your Vellum account, and your workspace is encrypted and isolated to you.

- Pros

  Zero setup, always-on, automatic upgrades, no infrastructure to manage. Reachable from web, desktop, mobile, voice, and chat channels.

- Cons

  No direct access to local files or tools on your machine without the desktop app. Provider selection is managed by Vellum.

## Local

Run the assistant runtime on the same machine as the desktop app. Useful for development, testing, and privacy-sensitive use cases where you want everything on hardware you own.

`vellum hatch`

When running locally, the assistant daemon and gateway both start on your machine. Latency is low and your assistant has direct access to local files and tools.

- Pros

  Low latency, full access to local files and tools, runs entirely on your hardware.

- Cons

  Tied to your machine being on. Uses local compute resources.

## User Hosted

Run the assistant on infrastructure you control. This is useful when you need the assistant to stay running independently of your local machine, when you need more compute resources, or when you have specific compliance requirements. Three hosting options are supported:

### GCP

Provisions a Google Cloud Compute Engine VM and bootstraps the assistant runtime on it.

`vellum hatch --remote gcp`

Requires `gcloud` authentication and the `GCP_PROJECT` and `GCP_DEFAULT_ZONE` environment variables.

### AWS

Provisions an AWS EC2 instance and bootstraps the assistant runtime on it.

`vellum hatch --remote aws`

Requires AWS credentials configured via the standard AWS CLI authentication flow.

### Custom

Deploy the assistant to any machine you can SSH into. Set the `VELLUM_CUSTOM_HOST` environment variable to your target host.

`VELLUM_CUSTOM_HOST=user@hostname vellum hatch --remote custom`

This option gives you full flexibility. Use any Linux machine (on-premises, a VPS, or a VM from any cloud provider) as the assistant's runtime environment.

## Choosing an Environment

| Environment  | Best For                                                                   | Requires                     |
| ------------ | -------------------------------------------------------------------------- | ---------------------------- |
| Vellum Cloud | Most users. Zero-ops managed hosting, always-on, accessible from anywhere. | Vellum account               |
| Local        | Personal use, development, testing, privacy-sensitive workflows            | Desktop app, vellum CLI      |
| GCP          | Always-on assistant on your own infrastructure                             | GCP account, gcloud CLI      |
| AWS          | Always-on assistant, AWS-native teams                                      | AWS account, AWS CLI         |
| Custom       | On-premises, custom infra, any SSH host                                    | SSH access to target machine |