Can MiroFish run offline?

MiroFish can be self-hosted, but fully offline operation depends on whether your model endpoint, memory service, and required dependencies are also available locally.

What is needed for private MiroFish deployment?

You need the web app, backend, storage, model configuration, graph or memory dependencies, and a network boundary that matches your privacy requirements.

MiroFish-Offline

MiroFish-Offline means self-hosted first, fully offline only if every dependency is local.

Offline and private deployments are about privacy, control, and local experimentation. The key distinction is simple: self-hosted does not automatically mean air-gapped.

Check the GitHub repository Run a first local test

Before deploying sensitive material, verify your model provider, graph memory service, logs, uploads, and backups. A private frontend is not enough if the backend still sends data to cloud services.

What self-hosting gives you

Control over the web app and backend runtime.
Local storage for uploads and simulation artifacts when configured that way.
Freedom to choose model endpoints and deployment boundaries.
Better visibility into logs, costs, and operational behavior.

Offline readiness levels

Local app

The UI and backend run on your machine, but model calls may still leave your network.

Private network

The stack runs inside your own server or LAN, with controlled access and private storage.

Fully offline

All models, memory services, dependencies, and data stores are available without external network calls.