Skip to content

FB - Install IA agent on VPS #8080

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Aug 18, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,146 @@
---
title: 'How to install an AI agent on an OVHcloud VPS'
excerpt: 'Find out how to deploy an AI agent like Open Interpreter or GPT4All on an OVHcloud VPS'
updated: 2025-08-18
---

## Objective

This guide explains how to deploy an on-premises AI agent on an OVHcloud VPS, without depending on the cloud of external providers. You will use a ready-to-use Docker container containing an open-source AI agent, such as [Open Interpreter](https://github.com/openinterpreter/open-interpreter), [GPT4All](https://github.com/nomic-ai/gpt4all) or [Auto-GPT](https://github.com/Significant-Gravitas/AutoGPT).

**Find out how to deploy an AI agent such as Open Interpreter or GPT4All on an OVHcloud VPS.**

## Requirements

- An [OVHcloud VPS](/links/bare-metal/vps) (Debian 11 or higher is recommended)
- Administrative (sudo) SSH access to your server
- Python ≥ 3.10 installed on the VPS

## Instructions

### Update your VPS and install Python <a name="step1"></a>

Open a terminal and connect to your VPS with the following command (replacing `VPS_IP` with the real IP):

```bash
ssh <user>@VPS_IP
```

Update the packages:

```bash
sudo apt update && sudo apt upgrade -y
```

Verify that Python ≥ 3.10 is installed:

```bash
python3 --version
```

If necessary, install Python 3.10+ and pip:

```bash
sudo apt install -y python3 python3-pip python3-venv
```

### Create a virtual environment and install Open Interpreter <a name="step2"></a>

Recent environments limit the use of `pip` globally. It is recommended that you create and use a virtual environment:

```bash
python3 -m venv ~/venv-openinterpreter
source ~/venv-openinterpreter/bin/activate
```

Install Open Interpreter:

```bash
pip install --upgrade pip
pip install open-interpreter
```

### Configure an AI template for the agent (local or remote) <a name="step3"></a>

#### Option 1 - Use OpenAI (GPT-4o, GPT-3.5, etc.)

You must have an OpenAI API key. Add it when you launch it for the first time, or set it beforehand:

```bash
export OPENAI_API_KEY="API_KEY"
interpret
```

Then follow the instructions.

#### Option 2 - Use a local model (via Ollama)

If you do not want to use OpenAI, run a local model using Ollama:

```bash
interpreter --local
```

This will give you several options (Ollama, LM Studio, etc.). We recommend using Ollama, as it is easy to install and compatible with several modern models such as `llama3` or `mistral`.

Install Ollama:

```bash
sudo apt install curl -y
curl -fsSL https://ollama.com/install.sh | sh
exec $SHELL
```

Load the model:

```bash
ollama pull mistral
```

Then try again:

```bash
interpreter --local
```

#### Common errors

**Model requires more system memory (6 GiB) than is available (1 GiB)**

This error indicates that your VPS does not have enough RAM. Here are your options:

- Choose a new VPS with at least 8 GB RAM.
- Use the OpenAI API (see `Option 1` above).
- Use a lighter model, like mistral.

### Test your AI Agent <a name="step4"></a>

Test the following use cases:

```console
What is in the /tmp folder?
```

Sample response:

![AI agent](images/question-version-python.png){.thumbnail}

```console
Write a Python script that lists the files in the current folder.
```

The agent interprets your request, generates code, and executes it locally.

Sample response:

![AI agent](images/question-python-script.png){.thumbnail}

### Conclusion <a name="step5"></a>

With this guide, you have installed an AI agent on your OVHcloud VPS, capable of executing commands from simple natural language instructions. Whether you have opted for a remote model like GPT-4 via OpenAI or a local model like Mistral via Ollama, you now have an intelligent assistant directly in your terminal, without dependency on a web interface or a third-party service.

## Go further

For specialized services (SEO, development, etc.), contact [OVHcloud partners](/links/partner)

Join our [community of users](/links/community).
Original file line number Diff line number Diff line change
@@ -0,0 +1,146 @@
---
title: 'Comment installer un agent IA sur un VPS OVHcloud'
excerpt: 'Découvrez comment déployer un agent IA comme Open Interpreter ou GPT4All sur un VPS OVHcloud'
updated: 2025-08-18
---

## Objectif

Ce guide explique comment déployer un agent IA local sur un VPS OVHcloud, sans dépendre du cloud de fournisseurs externes. Vous utiliserez pour cela un conteneur Docker prêt à l'emploi contenant un agent IA open source comme [Open Interpreter](https://github.com/openinterpreter/open-interpreter), [GPT4All](https://github.com/nomic-ai/gpt4all) ou [Auto-GPT](https://github.com/Significant-Gravitas/AutoGPT).

**Découvrez comment déployer un agent IA comme Open Interpreter ou GPT4All sur un VPS OVHcloud.**

## Prérequis

- Disposer d'un [VPS](/links/bare-metal/vps) fonctionnel (Debian 11 ou supérieur recommandé)
- Disposer d'un accès administrateur (sudo) via SSH à votre serveur
- Python ≥ 3.10 installé sur le VPS

## En pratique

### Mettre à jour votre VPS et installer Python <a name="step1"></a>

Ouvrez un terminal et connectez-vous à votre VPS avec la commande suivante (en remplaçant `IP_VPS` par la véritable IP) :

```bash
ssh <user>@IP_VPS
```

Mettez à jour les paquets :

```bash
sudo apt update && sudo apt upgrade -y
```

Vérifiez que Python ≥ 3.10 est installé :

```bash
python3 --version
```

Si nécessaire, installez Python 3.10+ et pip :

```bash
sudo apt install -y python3 python3-pip python3-venv
```

### Créer un environnement virtuel et installer Open Interpreter <a name="step2"></a>

Les environnements récents limitent l’usage de `pip` globalement. Il est recommandé de créer et d'utiliser un environnement virtuel :

```bash
python3 -m venv ~/venv-openinterpreter
source ~/venv-openinterpreter/bin/activate
```

Installez Open Interpreter :

```bash
pip install --upgrade pip
pip install open-interpreter
```

### Configurer un modèle IA pour l’agent (local ou distant) <a name="step3"></a>

#### Option 1 – Utiliser OpenAI (GPT-4o, GPT-3.5, etc.)

Vous devez disposer d’une clé API OpenAI. Ajoutez-la lors du premier lancement ou en la définissant au préalable :

```bash
export OPENAI_API_KEY="API_KEY"
interpreter
```

Suivez ensuite les instructions.

#### Option 2 – Utiliser un modèle local (via Ollama)

Si vous ne souhaitez pas utiliser OpenAI, exécutez un modèle local grâce à Ollama :

```bash
interpreter --local
```

Cela vous proposera plusieurs options (Ollama, LM Studio, etc.). Nous vous recommandons d'utiliser Ollama, car il est facile à installer et compatible avec plusieurs modèles modernes comme `llama3` ou `mistral`.

Installez Ollama :

```bash
sudo apt install curl -y
curl -fsSL https://ollama.com/install.sh | sh
exec $SHELL
```

Chargez le modèle :

```bash
ollama pull mistral
```

Puis relancez :

```bash
interpreter --local
```

#### Erreurs fréquentes

**Model requires more system memory (6 GiB) than is available (1 GiB)**

Cette erreur indique que votre VPS n’a pas assez de mémoire vive (RAM). Voici vos options :

- Opter pour un VPS disposant d'au moins 8 Go de RAM.
- Utiliser l'API OpenAI (voir `Option 1` ci-dessus).
- Utiliser un modèle plus léger, comme Mistral.

### Tester votre agent IA <a name="step4"></a>

Testez les exemples d'utilisation suivants :

```console
Quel est le contenu du dossier /tmp ?
```

Exemple de réponse :

![IA agent](images/question-version-python.png){.thumbnail}

```console
Écris un script Python qui liste les fichiers dans le dossier courant.
```

L’agent interprète votre demande, génère du code et l’exécute localement.

Exemple de réponse :

![IA agent](images/question-python-script.png){.thumbnail}

### Conclusion <a name="step5"></a>

Grâce à ce guide, vous avez installé un agent IA sur votre VPS OVHcloud, capable d’exécuter des commandes à partir de simples instructions en langage naturel. Que vous ayez opté pour un modèle distant comme GPT-4 via OpenAI ou un modèle local comme Mistral via Ollama, vous disposez désormais d’un assistant intelligent directement dans votre terminal, sans dépendance à une interface web ou à un service tiers.

## Aller plus loin

Pour des prestations spécialisées (référencement, développement, etc), contactez les [partenaires OVHcloud](/links/partner)

Échangez avec notre [communauté d'utilisateurs](/links/community).
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
id: 81b4dda2-5ca2-4868-b6a0-232ec0af92d5
full_slug: vps-install-ia-agent
1 change: 1 addition & 0 deletions pages/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -300,6 +300,7 @@
+ [Automating the deployment of your website on your VPS via GitHub Actions](bare_metal_cloud/virtual_private_servers/deploy-website-github-actions)
+ [Automating the deployment of your website on your VPS via GitLab CI/CD](bare_metal_cloud/virtual_private_servers/deploy-website-gitlab-ci-cd)
+ [How to create and import a Lovable website on an OVHcloud VPS](bare_metal_cloud/virtual_private_servers/import-lovable-website-on-vps)
+ [How to install an AI agent on an OVHcloud VPS](bare_metal_cloud/virtual_private_servers/install-ia-agent-on-vps)
+ [Managed Bare Metal](products/bare-metal-cloud-managed-bare-metal)
+ [OVHcloud services and options](bare-metal-cloud-managed-bare-metal-ovhcloud-services-and-options)
+ [Setting up a VPN for OVHcloud Zerto DRP](bare_metal_cloud/managed_bare_metal/zerto-virtual-replication-customer-to-ovhcloud)
Expand Down