Skales is a desktop AI agent you install on your computer. It connects to any AI provider you choose (Claude, GPT, Gemini, Grok, or local Ollama via your own keys), runs entirely on your machine with no cloud middleman, and stores all conversations, memories, and files locally. You can set autonomous goals that run in the background, automating workflows across your desktop and browser.
Reviewed by Marcus Holmberg
Skales
skales.app No ratings yet. Be the first.
Rate Skales: No account needed
Threat level
Hardened
A hardened pick. Worth the effort once you have chosen to shrink your footprint on purpose. Enough for most people. Threat levels
Our take
Skales is the most transparent approach to a personal AI agent: your data lives on your machine, you pick which AI provider and which API keys go where, and inference calls go directly from your computer to your chosen provider. No subscription, no cloud backup, no data sharing. The trade-off is that you are managing your own API keys and picking your own model, so there is a small setup step. For anyone who wants AI agent power without the privacy surrender of a cloud-first tool, and who is willing to bring their own API key, Skales is the clear pick.
GitHub at a glance
skalesapp/skales
Stars
1,105
+ 10 this week
Stars, last 21d
Website at a glance
skales.app
C score 50
Basic website security headers
Graded by Mozilla HTTP Observatory, tested 4d ago
Inspect this site yourself
Measures the security configuration of the tool's own website, not the privacy of the product itself. A strong tool can still score low here.
Skales alternatives
Lumo Proton's hosted AI assistant with zero-access encryption of saved chats and a strict no-logs policy.
Duck.ai DuckDuckGo's private AI chat that lets you talk to multiple models with no account and no training on your prompts.
Euria Infomaniak's Swiss-hosted AI assistant that pledges no training on user data and operates under GDPR and Swiss data law.
Apple Intelligence Apple's AI. On-device where it can, with verifiable Private Cloud Compute for the rest.
Ollama Ollama lets you download and run large language models locally via a simple CLI and REST API. Supports a growing library of open models including Llama, Mistral, and Gemma on Windows, Mac, and Linux with no data sent to the cloud.
llamafile A Mozilla project that packages a complete LLM and its runtime into a single executable file. Download one file, run it on Windows, Mac, or Linux with no installation, no dependencies, and no network connection required.
* Average ratings will show on this page once the threshold of 5 ratings is reached.