Frequently asked questions

Yes. Loach is open source under the MIT license. There are no subscriptions, paywalled features, or usage limits inside the app. If you connect to a paid endpoint (e.g. OpenAI), you pay them for tokens — Loach itself is free.

Native desktop apps for Windows, Linux and macOS (Apple Silicon) are published with every release. The macOS build is not Apple-notarized, so first launch needs a one-time Gatekeeper bypass — see Installation → macOS. Intel Macs are not supported.

No, not on its own. There is no telemetry. The only outbound requests Loach initiates are (a) generations against the remote provider you configured, and (b) update checks (which can be turned off). With a purely local provider like Ollama, Loach works fully offline. See Storage & privacy.

In a SQLite database at <app-data-dir>/loach.db:

• Windows: %APPDATA%\dev.loach.app\loach.db
• Linux: ~/.local/share/dev.loach.app/loach.db

No. Loach is the workspace; the model is supplied by a provider. Install Ollama and pull a local model, or configure an OpenAI-compatible endpoint.

Anything supported by Ollama. Popular choices include Qwen, Gemma, DeepSeek, GPT-OSS, Mistral and Llama derivatives. Use the in-app Models tab to pull and manage them.

Yes — that's the point. Ollama and your OpenAI-compatible endpoint live side-by-side, and you switch between them from the chat header without changing anything else.

One at a time. The base URL and API key are a single configuration in Settings → Providers. To switch from, say, Groq to OpenRouter, update the base URL and key — your existing chats are preserved.

Yes — try smaller quantizations (e.g. a 4-bit 3B/4B model), and enable Low VRAM mode globally or per-chat. This sends Ollama's low_vram flag with every request.

In your operating system's credential manager — Windows Credential Manager, the Linux Secret Service, or the macOS Keychain. Keys are never written to the SQLite database or to plain-text config.

Optional PIN, password, or both. Your credentials are hashed with Argon2id and stored in the OS credential manager (separately from API keys). The plaintext is never persisted. Configure it in Settings → App lock.

You can clear the app lock by removing the corresponding entry from your OS credential manager (the entry is created and managed by the Loach app). Doing so unlocks the app but leaves the rest of your data intact.

Open Settings → Data management and use Export. You'll get a single JSON file containing chats, Spaces, Snippets and settings. API keys are not in the export — they live in the OS credential manager.

Install Loach on the new machine, then use Restore in Settings → Data management with the JSON file you exported from the old one. You'll need to re-enter API keys on the new machine since those don't travel in the export.

Settings → Data management → Delete all data wipes the SQLite database. Remove the corresponding entries from your OS credential manager to delete API keys and the app-lock hash.

For Ollama: make sure ollama serve is running and at least one model is pulled. Loach probes http://localhost:11434 on launch — if Ollama is on another host or port, update the base URL in Settings → Providers.

For an OpenAI-compatible provider: confirm the base URL, that the API key is set, and that the endpoint actually exposes a /models route. Some self-hosted servers require a non-standard model identifier — try typing it manually.

Try a smaller model or a more aggressive quantization. Turn on Model preloading so the first request doesn't wait on a cold start. Enable Low VRAM mode if you're memory-constrained.

That usually means the model output isn't well-formed Markdown. Lower the temperature, or add an explicit instruction like "Reply in valid GitHub-flavoured Markdown". Loach uses remark-gfm + rehype-highlight under the hood, so anything valid will render.

Open an issue on the GitHub repository: github.com/ztcs-software/loach/issues. Please include your OS, Loach version, and steps to reproduce.