Choosing & Managing Your AI

Picking a provider

Vrge routes AI calls through four providers. You choose which one in Settings → AI & Intelligence.

Ollama (Local)— runs on your machine, no network, no API key, no cost. Install Ollama separately and point Vrge at your preferred model (e.g. llama3.2:3b). First-class for privacy-sensitive work.
Anthropic Claude, OpenAI GPT-4o, Google Gemini— bring your own API key. Pay the provider directly. Vrge takes no markup and never proxies your content.
Switching to a cloud provider triggers a consent modal with a redaction preview showing exactly what will be sent. Nothing leaves your machine without your explicit accept.

Set a per-user daily token budget in Settings → AI & Intelligence. A warning banner appears at 80% usage; a hard stop at 100%. No surprise bills.
A one-toggle kill switchdisables all sources, stops the observer, and cancels in-flight AI calls instantly. No confirmation dialog — one click, instant stop.

The AI activity log shows every single call: timestamp, provider, task, token count, estimated cost, and whether content was redacted. Exportable as JSON.
Redact-by-default: when calling a cloud provider, Vrge replaces names, emails, addresses, and dollar amounts with tokens before the call. Full- content mode requires a deliberate per-source opt-in.