Local Intelligence. Unleashed.

Python PySide6 Platform Status Version 1.0.0

A private, secure, and highly responsive desktop AI assistant. Now featuring Vector Memory, Real-Time Translation, and Context-Aware Suggestions. Your data, your hardware, your rules.

Download v1.0.0 Documentation

Seamless in Light or Dark

Dark Mode
Dark Mode Interface
Light Mode
Light Mode Interface

100% Local & Private

All processing happens on your machine via your Ollama instance. Nothing leaves your system. Zero telemetry, maximum privacy.

Auto-Translation

Instantly translate AI responses into your preferred language using a dedicated local neural network.

Vector Memory

Semantic search embeddings allow Cortex to recall relevant context from far deeper in your history.

Suggestions

Intelligent, context-aware conversation bubbles help keep the dialogue flowing smoothly.

Deep Customization

Edit system instructions, fine-tune temperature/seed, and fork conversations directly from the new v1.0.0 UI.

Robust Data

Dual-layer storage with SQLite for chats and Vector Embeddings for long-term semantic recall.

Get Cortex v1.0.0

Choose the installation method that suits you.

Official Release

Recommended • v1.0.0

The complete package including source code and latest features.

Download v1.0.0

Manual Setup

For Developers

Clone the repo and install dependencies manually via Python.

View Source

Binaries

Windows (.exe)

Compiled executables for v1.0.0 are available in the Releases tab.

Download .exe

System Architecture v1.0

Presentation (UI)

Built with PySide6 (Qt). Handles theming, chat bubbles, and the new Suggestion UI.

Orchestrator

Coordinates the Synthesis Agent, Title Worker, and new Translation/Suggestion pipelines.

Data & Models

Interfaces with Ollama for Chat, Embedding, and Translation models. Stores data in SQLite + Vectors.

Cortex Screenshot 1 Cortex Screenshot 2 Cortex Screenshot 3 Cortex Screenshot 4