Your AI second brain, hosted in France
A personal assistant with continuous memory powered by OpenHuman, installed and maintained by DINAO. Your notes, your connections to 118+ services, and your history remain on our French servers — never in a vendor's cloud.
What is OpenHuman?
OpenHuman is a local-first personal AI assistant designed to be the memory and right arm of everything you do daily. Built in Rust + Tauri and released under the GNU GPL3 license, it builds a continuous memory of your work — a true second brain — stored entirely on your end in an Obsidian-compatible Markdown vault and a local SQLite database.
OpenHuman connects to 118+ services, remembers your activity, reflects, and can interact with you via audio and video. Since it can call tools and run inference locally via Ollama, a functional setup never needs to send your data to a vendor's cloud.
Available on macOS, Windows, and Linux, OpenHuman is for those who want an assistant that truly remembers — while keeping full control over their information.
Host OpenHuman at DINAO
Resource tiers compatible with OpenHuman prerequisites (minimum 2 vCPU / 4 Go / 10 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 might be wondering…
Does my data go to the cloud?
No. OpenHuman is local-first: your memory (Markdown vault + SQLite database) stays on your DINAO instance in France. With on-device inference, no data is sent to an external provider.
What tools can OpenHuman connect to?
Over 118 services (messaging, calendar, file storage, instant messaging…). It uses them to remember your activity and act on your behalf, not just to chat.
Do I need a GPU?
Not necessarily: small models run on CPU. For larger or faster models, a GPU is available as an option on higher-tier plans.
Where is the data hosted?
On DINAO infrastructure in France, in one of the available data centers. Your data never leaves the country.
Can I export my memory?
Yes. Memory is stored in Obsidian-compatible Markdown and SQLite: open formats, exportable at any time, with no proprietary lock-in.
