A private, secure, and highly responsive desktop AI assistant. Connect directly to Ollama with no cloud dependency. Your data, your hardware, your rules.
All processing happens on your machine via your Ollama instance. Nothing leaves your system. Zero telemetry, maximum privacy.
Seamlessly integrates with any model served by Ollama (Llama 3, Mistral, Gemma) with instant switching.
Chat history stored in a robust local database for instantaneous loading and data integrity.
Split a conversation at any point to explore new lines of thought without losing context.
Teach Cortex about you. It persistently remembers your projects, preferences, and facts to personalize future responses.
Adjust Temperature, Context Window, and System Prompts via a dedicated GUI.
Choose the installation method that suits you.
The complete package including source code and latest patch notes.
GitHub ReleaseJust the application. Requires existing Ollama setup.
Download EXE (67MB)Includes tools to pull models and install Ollama.
Setup Tool (65MB)Built with PySide6 (Qt). Handles theming, rendering code blocks, and user input.
Manages state, coordinates async threads, and dispatches tasks to prevent UI freezing.
SQLite persistence layer combined with a Synthesis Agent that interfaces with Ollama API.