No Terminal, No Docker — Just an AI Agent on Your Desktop

Your private AI agent shouldn’t require Docker and a terminal.
Skales is a local-first desktop AI agent for people who want an agent to work with their files, browser, calendar, email, and code.
It helps you delegate multi-step work from your own computer by combining background goals with desktop tools, coding workflows, and a choice of hosted or local models.
Key features:
• One-click desktop setup – install it on Windows, macOS, or Linux without Docker or terminal setup
• Background goals – hand it a multi-step goal, close the chat, and let it continue until completion or a decision is needed
• Built-in code workflows – bind a folder, review inline diffs, run tests, and undo file changes
• Flexible model access – start with the built-in trial, connect 15+ providers, or run offline with Ollama or LM Studio
• Mobile access – pair Android or iOS with your desktop via QR to use its tools remotely
Public GitHub repo; the current Skales app is closed source under BSL 1.1.
🔗 GitHub: https://lnkd.in/dYtj5U99
⸻
♻️ Share this with your network if you found it useful or insightful.
✉️ If you’re into AI, ML, agents, and building real systems, join my newsletter (it’s free): dankornas.substack.com

Skales is a source-available (BSL 1.1) desktop AI agent for Windows, macOS, and Linux that installs without Docker or a terminal. It supports background/autonomous goals via scheduled or cron-based tasks, includes built-in autonomous coding workflows with diff review and undo, connects to 15+ hosted providers or runs fully offline via Ollama/LM Studio, and pairs with a mobile app over QR for remote control. Data is stored locally by default (~/.skales-data), and the project describes itself as a full agent "harness" — tool layer, memory, and provider abstraction — rather than a simple chat wrapper.