Models & providers
EditVolt is bring-your-own-model: connect the providers you already use, under your own keys. Requests go directly from your machine to the provider — EditVolt runs no proxy in between and adds no markup.
Supported providers
| Provider | Connection |
|---|---|
| Anthropic Claude | API key — or bridge your existing Claude Code CLI sign-in with one click |
| Google Gemini | AI Studio API key |
| OpenAI-compatible | Any base URL + key: OpenAI, OpenRouter, Azure OpenAI, vLLM, LM Studio, Together… |
| Hugging Face | Remote inference or local |
| Ollama | Local daemon at localhost:11434 — no key, 100% local |
Model lists are fetched live from each provider, so new models appear in the picker automatically.
API keys
Keys are stored in your operating system keychain — never in plaintext files — and read only for the duration of each request. Add them under Settings → Models.
Routing
Pick a default provider (editvolt.provider.default) and optionally enable smart routing:
- Fast lane (
editvolt.routing.autoFastLane) — quick, mechanical tasks go to a fast model - Heavy model (
editvolt.routing.heavyModel) — complex chat and agent turns go to your preferred frontier model
EditVolt never silently substitutes providers: if the one you chose is unavailable, you get an honest error, not a quiet reroute — and switching from a local to a cloud model always asks first.
:::tip Fully local setup
Install Ollama, pull a model, and set editvolt.privacy.strict: true — every AI feature then runs locally with zero cloud calls. See Privacy controls.
:::