← Back to catalog MiroFish · managed by DINAO

Simulate public reactions, hosted in France

A multi-agent simulation engine powered by MiroFish, installed and maintained by DINAO. Your documents and scenarios stay on our French servers — never with an American AI provider.

View compatible offers →
Hosted in FranceHundreds of AI agentsScenario anticipationGDPR compliantOfficial publisher image
Overview

What is MiroFish?

MiroFish is an open-source multi-agent simulation engine, both a web application and an HTTP API, designed for scenario prediction. It automatically builds a high-fidelity parallel digital world, populated by hundreds of intelligent agents with independent personalities, long-term memory, and behavioral logic, which interact freely and evolve socially.

The principle is simple: you upload a document — press release, policy draft, financial report — and MiroFish generates AI agents with varied profiles that simulate public reaction, for example on social media. You thus anticipate the reception of a decision before making it public.

On the technical side, MiroFish combines a Vue frontend, a Flask backend, and simulation services, deployable via Docker. An offline variant allows fully local operation (for example with Neo4j and Ollama), with no calls to cloud APIs — ideal for sovereign and confidential use.

Compatible offers

Host MiroFish at DINAO

Resource tiers compatible with MiroFish prerequisites (minimum 2 vCPU / 4 Go / 10 Go disque). Hosted in France, fully managed.

Standard
2 vCPU · 4 Go · 40 Go
19,90 € /month excl. VAT
  • 2 dedicated vCPU
  • 4 Go RAM
  • 40 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
★ Recommended for this app
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

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.

Under the hood

Technical details

vCPU
2 vCPU
ideal : 4 vCPU
Memory
4 Go
ideal : 8 Go
Disk
10 Go disque
ideal : 20 Go disque
Image : ghcr.io/666ghj/mirofish:latest Registry : ghcr.io Services : mirofish Ports : 3000 (interface web frontend), 5001 (API backend)
FAQ

You might be wondering…

What is MiroFish actually used for?

MiroFish builds a digital world populated by AI agents with distinct personalities. You submit a document — press release, policy draft, report — and it simulates public reaction, for example on social media, to help you anticipate.

Are my documents used to train an AI?

No. In local mode, your documents and scenarios remain on your instance and are never transmitted or used for training. This is the truly sovereign mode.

Can I use my own AI model?

Yes. You can connect a local open-weight model (served by Ollama) or connect an external API with your key. The choice depends on your confidentiality and cost requirements.

Are technical skills required?

No for usage: DINAO installs, secures, and updates the instance (Vue frontend, Flask backend). A technical team can still exploit the HTTP API.

Can I change plans or export my data?

Yes. You can upgrade or downgrade at any time, and your data remains exportable — no proprietary lock-in, as MiroFish is open source.