An elegant AI chat interface, hosted in France
A premium AI chat interface powered by Chatpad AI, installed and maintained by DINAO. Chat with your models in a refined UI — on your French servers.
What is Chatpad AI?
Chatpad AI is not "just another ChatGPT interface" : it is a premium, refined, and open-source chat interface designed to deliver the most pleasant AI chat experience possible. Its stated ambition is to become the ultimate interface for conversing with language models.
The application emphasizes privacy: your data is stored locally, and the tool is free and open source. Among its features, a persona selector allows you to switch between different character profiles from one conversation to the next, to obtain responses tailored to each context.
Technically, Chatpad AI is a simple-to-deploy React application that is easy to self-host (notably via Docker). It connects to your own model provider, making it an elegant gateway to conversational AI that you keep under your control.
Host Chatpad AI at DINAO
Resource tiers compatible with Chatpad AI prerequisites (minimum 1 vCPU / 128 Mo / 1 Go). Hosted in France, fully managed.
- 1 dedicated vCPU
- 2 Go RAM
- 20 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 2 dedicated vCPU
- 4 Go RAM
- 40 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 4 dedicated vCPU
- 8 Go RAM
- 80 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 8 dedicated vCPU
- 16 Go RAM
- 160 GB NVMe
- Daily backups
- Managed & monitored by DINAO
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.
Technical details
You might be wondering…
How does Chatpad AI differ from public ChatGPT?
Chatpad AI is a self-hosted interface: you keep your conversations on your instance and choose the model. In local mode, no data goes to a public service.
Can I use my own models?
Yes. You connect a local open-weight model hosted on your DINAO instance, or an external API (OpenAI, Mistral…) with your own key.
Where is the data hosted?
On DINAO infrastructure in France, in one of the available datacenters. In local mode, your conversations never leave the territory.
Do I need technical skills?
No for usage: the interface is ready to use. DINAO handles installation, security, and instance updates.
Can I change plans or export my data?
Yes. You can upgrade or downgrade at any time, and your data remains exportable, with no proprietary lock-in.