← Back to catalog Big-AGI · managed by DINAO

A professional AI workshop, hosted in France

A multi-model AI workspace powered by Big-AGI, installed and maintained by DINAO. Personas, multi-model Beam chats, image and voice generation — on your French servers.

Hosted in FranceSovereign in local modeYour open-weight modelsGDPR CompliantOfficial publisher image
Overview

What is Big-AGI?

Big-AGI is an open-source AI suite designed for professionals who expect functionality, aesthetics, simplicity, and speed. Designed as a true multi-model workspace, it goes beyond a simple chatbot to offer a comprehensive working environment around large language models.

Its flagship feature, Beam, allows querying multiple models simultaneously, comparing their responses, and merging them to achieve the best result. The application also includes AI personas, image generation, voice, response streaming, syntax highlighting and code execution, PDF import, and numerous presets for developers.

Big-AGI deploys on-premise or in the cloud and connects to both locally served open-weight models and APIs from major providers. It is an independent project, funded by Pro subscriptions while maintaining a free and open core.

Compatible offers

Host Big-AGI at DINAO

Resource tiers compatible with Big-AGI 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
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 : 5 Go
Image : ghcr.io/enricoros/big-agi:latest Registry : ghcr.io Services : big-agi Ports : 3000
FAQ

You might be wondering…

Are my data used to train models?

No. Your prompts and conversations remain private on your instance. In local mode, no data leaves our French servers.

What does the Beam feature offer?

Beam queries multiple models in parallel for the same question, then lets you compare and merge their responses to get the best result.

Where is the data hosted?

On DINAO infrastructure in France, in one of the available datacenters. In local mode, your data does not leave the territory.

Are technical skills required?

No for usage: the interface is ready to use. DINAO handles installation, security, and updates. Your technical teams can connect their own models.

Can I connect my own models or API keys?

Yes. You use locally hosted open-weight models, or connect an external API (OpenAI, Anthropic, Mistral…) with your own key.