Your AI assistant controlled via messaging, in France
The autonomous OpenClaw AI agent, installed and maintained by DINAO. Give it tasks from Signal, Telegram, or Discord : it runs on our French servers — your exchanges do not pass through a third-party cloud.
What is OpenClaw?
OpenClaw is an open-source autonomous AI agent capable of executing tasks using large language models, using messaging platforms as the primary interface. Instead of going through a dedicated application, you send your instructions from Signal, Telegram, Discord, or WhatsApp, and the agent acts on your behalf.
The framework relies on a skills system where each capability is stored as a folder accompanied by metadata, allowing the agent to extend to new use cases. It runs locally, retains its configuration and interaction history from one session to the next, and thus adapts its behavior over time.
OpenClaw integrates with external language models (Claude, GPT, DeepSeek…) as well as open-weight models hosted on your own server. Originating from Peter Steinberger's project, it is now maintained by the OpenClaw Foundation, ensuring longevity for professional use.
Host OpenClaw at DINAO
Resource tiers compatible with OpenClaw prerequisites (minimum 1 vCPU / 512 Mo / 2 Go). Hosted in France, fully managed.
This application uses an unofficial/unverified image or requires custom resources. We review and deploy it upon request.
Request a quoteThis 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 may also like…
Other applications managed by DINAO in the same category, hosted in France and GDPR compliant.
You might be wondering…
Are my conversations confidential?
Yes. In local model mode, your messages and the agent's history remain on your instance, in France. Nothing is shared or used to train a model.
Can I use my own models?
Yes. You connect a locally hosted open-weight model (sovereign), or an external API (Claude, GPT, DeepSeek…) with your own key.
Where is the data hosted?
On the DINAO infrastructure in France, in one of the available data centers. Your data does not leave the territory in local mode.
Do I need technical skills?
No for usage: you chat with the agent from your usual messaging app. DINAO handles installation, security, and updates. Your developers can create custom skills.
Can I change plans or export my data?
Yes. You can upgrade or downgrade at any time, and your configuration remains exportable — no proprietary lock-in.
