Your autonomous AI agent, hosted in France
The self-hosted agent from Nous Research, installed and maintained by DINAO. Persistent memory, reusable skills, and scheduled tasks run on our French servers — your data never leaves for a cloud provider.
What is Hermes Agent?
Hermes Agent is an open-source autonomous AI agent developed by Nous Research, the lab behind the Hermes model family. Self-hosted, it runs on your own server, learns from every task completed, and becomes measurably more efficient over time.
The agent features persistent memory that retains context across sessions, a system of reusable skills, scheduled tasks (cron), browser automation, code execution, and multi-agent delegation. You grant it access to your channels (terminal, dashboard, workflows, messaging like Discord, Telegram, Slack, Signal, or email) and connect it to the language model of your choice.
It then becomes a long-term agent capable of executing tasks, searching the web, writing and running code, managing files, and interacting with external services. Hermes Agent also exposes inter-agent interoperability protocols (MCP, A2A, OAuth), making it a solid building block for advanced business automations.
Host Hermes Agent at DINAO
Resource tiers compatible with Hermes Agent prerequisites (minimum 2 vCPU / 2 Go / 5 Go). Hosted in France, fully managed.
- 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
1 hidden tier(s) (insufficient resources for this app) : Découverte
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 may also like…
Other applications managed by DINAO in the same category, hosted in France and GDPR compliant.
You might be wondering…
Is my data used to train models?
No. The agent's memory, files, and exchanges remain private on your instance. In local model mode, nothing is shared or used for training.
Which language model does the agent use?
You choose: a local open-weight model hosted on your DINAO instance (sovereign), or an external API with your own key. Switching is free.
Where is the data hosted?
On DINAO infrastructure in France, in one of the available datacenters. Your data does not leave the territory in local mode.
Do I need technical skills?
No for everyday use: the agent is controlled via a ready-to-use interface. DINAO handles installation, security, and updates. Your developers can use the terminal and API.
Can I change plans or export my data?
Yes. You can upgrade or downgrade at any time, and your configuration and memory remain exportable — no proprietary lock-in.
