← Back to catalog Hollama · managed by DINAO

A minimalist AI interface, hosted in France

The clean AI chat powered by Hollama, installed and maintained by DINAO. A simple interface to your Ollama models — your sessions stay in your browser, not at OpenAI.

Hosted in FranceMinimalist InterfaceOllama & OpenAIGDPR CompliantOfficial publisher image
Overview

What is Hollama?

Hollama is an open-source minimalist AI chat interface, designed to easily interact with Ollama servers and OpenAI-compatible endpoints. Its philosophy boils down to one idea: do one thing — chat — and do it well, with a clean, fast interface and no complex backend infrastructure to maintain.

The application connects directly from the browser to one or more Ollama servers, OpenAI-compatible endpoints, or both simultaneously. You can save multiple backends and route each session to the one of your choice. It supports Markdown and reasoning models, offering a modern experience despite its lightweight nature.

Key privacy point: every session, prompt, setting, and API key is stored in the browser's local storage — conversations do not accumulate on the server. Distributed as a static web interface, Hollama is very easy to deploy and self-host, making it one of the simplest Ollama clients available.

Compatible offers

Host Hollama at DINAO

Resource tiers compatible with Hollama prerequisites (minimum 1 vCPU / 256 Mo / 1 Go). Hosted in France, fully managed.

Standard
2 vCPU · 4 Go · 40 Go
19,90 € /month excl. VAT
  • 2 dedicated vCPU
  • 4 Go RAM
  • 40 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
Performance
4 vCPU · 8 Go · 80 Go
39,90 € /month excl. VAT
  • 4 dedicated vCPU
  • 8 Go RAM
  • 80 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
Dédié
8 vCPU · 16 Go · 160 Go
79,90 € /month excl. VAT
  • 8 dedicated vCPU
  • 16 Go RAM
  • 160 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
🧠

This application uses AI

The container hosts the application, not the AI engine (which requires dedicated GPUs) : inference is handled externally, with your own provider key. Prioritize a sovereign engine — Mistral AI, NumSpot, Scaleway, or OVHcloud AI Endpoints (France, GDPR) ; an international provider (OpenAI, Anthropic…) only if a specific capability requires it. Inference subscriptions are not included in hosting.

Under the hood

Technical details

vCPU
1 vCPU
ideal : 1 vCPU
Memory
256 Mo
ideal : 512 Mo
Disk
1 Go
ideal : 2 Go
Image : ghcr.io/fmaclen/hollama:latest Registry : ghcr.io Services : hollama Ports : 4173
FAQ

You might be wondering…

How does Hollama differ from a large AI interface?

Hollama aims for simplicity: it is a minimalist chat interface that focuses on the essentials, without the heaviness of a full platform. Ideal if you want a fast UI for your Ollama or OpenAI models.

Where are my conversations stored?

In your browser's local storage (sessions, prompts, API keys). Conversations do not accumulate on the server, which enhances privacy.

Can I connect multiple models?

Yes. You can register multiple Ollama servers and OpenAI-compatible endpoints simultaneously, and route each session to the backend of your choice.

Where is inference hosted?

On DINAO infrastructure in France, in one of the available data centers. In local mode (Ollama), your data does not leave the territory.

Do technical skills are required?

No for usage: the interface is ready to use. DINAO handles installation, security, and updates; you just need to choose your models and chat.