← Back to catalog LobeChat · managed by DINAO

Your private AI chat, hosted in France

A modern AI interface of the ChatGPT type powered by LobeChat, installed and maintained by DINAO. In local mode (Ollama), your conversations and documents stay on our French servers — they never leave.

View compatible offers →
Hosted in FranceSovereign in local modeMulti-model · MCPGDPR CompliantOfficial publisher image
Overview

What is LobeChat?

LobeChat is an open-source AI chat framework with a modern design, allowing you to deploy your own private, self-hosted ChatGPT-like application in minutes. It is multi-provider: a single interface for OpenAI, Claude, Gemini, Mistral, Perplexity, Bedrock, Azure, and many others.

Crucially, it supports local models via Ollama, enabling you to run AI entirely on your own infrastructure without sending your data to a third party. Its extensible plugin system, MCP (Model Context Protocol) compatibility, and knowledge base (RAG) make it a complete AI platform.

LobeChat is also multimodal: visual recognition (Vision), speech synthesis and recognition (TTS/STT), text-to-image generation, internet search, branching conversations, and reasoning visualization. Deployment is done via Docker, with customizable themes and a local database.

Compatible offers

Host LobeChat at DINAO

Resource tiers compatible with LobeChat prerequisites (minimum 1 vCPU / 1 Go / 2 Go). Hosted in France, fully managed.

Découverte
1 vCPU · 2 Go · 20 Go
9,90 € /month excl. VAT
  • 1 dedicated vCPU
  • 2 Go RAM
  • 20 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
★ Recommended for this app
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 : 2 vCPU
Memory
1 Go
ideal : 2 Go
Disk
2 Go
ideal : 4 Go
Image : lobehub/lobe-chat:latest Registry : docker.io Services : lobe-chat Ports : 3210
FAQ

You might be wondering…

Are my data used to train models?

No. In local mode (Ollama), your prompts, conversations, and documents remain private on your instance and are never used for training, unlike public services.

Can I use my own models?

Yes. LobeChat is multi-provider: local open-weight models via Ollama, or external API (OpenAI, Claude, Gemini, Mistral…) with your own key. You can combine multiple models in a single interface.

Which configuration is truly sovereign?

Local mode via Ollama: everything stays in France on your instance. Connecting LobeChat to an external cloud API is convenient, but your content then goes to the provider — see the sovereignty note below.

Do I need technical skills?

No for usage: the interface is ready to use and DINAO handles installation, security, and updates. A technical team can use the API, SSO, and plugins/MCP.

Can I change plans or export my data?

Yes. You can upgrade or downgrade at any time, and your data remains exportable — no proprietary lock-in.