What is Avelyn?

Avelyn is a hybrid, privacy-first AI writing assistant specifically designed for macOS. It integrates system-wide, allowing you to highlight text in any application (like Chrome, Slack, Word, or VS Code), hit a customizable global keyboard shortcut, and refine or rewrite your prose instantly using local offline models or secure cloud APIs.

Yes, this utility is highly secure. Unlike traditional cloud writing assistants that stream your inputs to remote servers, Avelyn operates with zero background keylogging. In local mode, calculations run in-memory without network requests. In cloud mode, your API keys are stored locally and fully masked inside settings to prevent over-the-shoulder leaks.

Yes. When configured with local offline engines like Ollama, the assistant operates 100% offline. No active internet connection is required to rewrite, format, translate, or proofread your text, making it ideal for air-gapped workstations or sensitive corporate environments.

Avelyn supports Local Ollama, Avelyn Cloud (OpenRouter), and Custom API endpoints. In 'Auto Provider' mode, it automatically routes tasks based on classification and text size (e.g. sending coding tasks to the Coding Provider, and long texts to the Writing Provider), with automatic fallbacks if a provider goes offline.

Yes. Avelyn includes immediate query cancellation to halt model streams instantly, saving local CPU/GPU cycles and API tokens. You can also configure the active context window size (such as 2,048 or 4,096 tokens) in settings to prevent system RAM pressure.

The system is different because it is built from the ground up for complete data sovereignty, zero keylogging, and multi-provider flexibility. Rather than locking you into one vendor, Avelyn lets you combine local open weights models with secure pay-as-you-go cloud APIs.

The software supports macOS 13 (Ventura), macOS 14 (Sonoma), and macOS 15 (Sequoia) or newer. It is optimized to run on both Intel-based Macs and Apple Silicon machines (M1, M2, M3, M4 series), though Apple Silicon is highly recommended for faster token generation and lower memory latency during local LLM model execution.

Yes. By choosing the 'Custom API' provider, you can connect LM Studio, vLLM, or any private OpenAI-compatible endpoint. Simply input your base URL, API key, and model ID inside the settings panel.

Absolutely not. The application code is built with zero telemetry dependencies. It does not contain analytic tracking scripts, error reporting mechanisms that connect to external endpoints, or remote config fetching. Your texts, keys, and logs remain strictly on your local device.