Run LLM Agents
Locally on Your Machine
Privacy-first AI assistant platform. Your data stays on your computer.
Version 0.1.0 (Early Access)
$ drakyn start
Starting inference server...
Starting MCP server...
✓ Drakyn Desktop ready
$ _
Why Drakyn Desktop?
Privacy First
All processing happens locally. Your conversations and data never leave your machine.
Fast Inference
Powered by vLLM for high-performance model inference on CPU or GPU.
Extensible Tools
Built on Model Context Protocol (MCP) for easy tool integration.
Native Experience
Beautiful desktop app for macOS, Windows, and Linux.
Multiple Agents
Configure and run different AI agents for different tasks.
Model Management
Easy model downloading, loading, and switching between models.
Download Drakyn Desktop
Choose your platform and start running AI agents locally
Installation
Click "View Releases" above to download the latest version for your platform. Installation instructions are provided on the releases page.
Open Source & Community Driven
Drakyn Desktop is open source and welcomes contributions from the community.
View on GitHub