Frequently asked questions

Any of them. Atlarix ships with built-in Core models and supports bring-your-own-key (BYOK) for 145+ providers and 4,400+ tool-capable models, read live from the models.dev catalog — OpenAI, Anthropic, Google, and every OpenAI-compatible endpoint — plus local models via Ollama and LM Studio. The list refreshes itself, so new models appear without an app update. Add keys under Settings → AI Providers.

Settings → AI Providers → choose a provider → paste your key. Your key is stored locally on your device and used to call that provider directly. BYOK models appear in the model selector alongside Core models.

Most errors are provider-side (rate limits, quota, transient overload). See the AI rate limit & provider errors guide at /docs/help/ai-rate-limit — usually switching models or retrying resolves it.

Your code stays on your machine. Unless you set up your own models, Atlarix runs on Atlarix Core — your request passes through our authenticated proxy (we don't log or retain it), then goes directly to the model provider under their own data policy. Run a local model (e.g. Ollama) and nothing leaves your machine at all. Add your own API key and requests go directly to that provider — we never see the traffic.

Atlarix is a desktop app for macOS, Windows, and Linux. Download links are on the home page.