skales

The private AI that lives on your computer and does real work, not just chat.

📋 Table of Contents

• Demo
• ⚡ Why Skales?
• 🚀 What Skales Can Do
  • 🎯 Background Goals
  • ✨ Skales IQ + Skales Stack
  • 📐 Workflows
  • 🧩 Agent Skills
  • 🛠️ Skales Codework
  • 🏢 Organization
  • 👥 Teams
  • 📱 Skales Mobile
  • 🗣️ Voice: Talk to Skales
  • 🌐 Inline HTML Preview
  • 🖥️ Computer Use
  • 🦁 Lio AI (Code Builder)
  • 🎨 Skales Studio
  • 🗂️ Templates
  • 🌐 Built-in Browser Agent
  • 🌐 WordPress 2.0
  • 🎮 Playground
  • AIPointer ⦿
  • 🦎 Desktop Buddy
  • 📅 Planner, Calendar and AI Tasks
  • 🧠 Memory and Dreaming
• 🔌 Integrations
• 🧠 15+ AI Providers
• 🌍 Discover
• 📊 Skales Wrapped
• 🛡️ Privacy and Security
• 📦 Installation
• 🏗️ Architecture
• 🤝 Community
• ⭐ Star History
• 📜 License
• 🆓 Try Skales Free

Demo

⚡ Why Skales?

Skales is an AI agent that lives on your desktop. Not in a browser tab, not behind a restrictive API, not in a complex Docker container. It sits on your machine, has access to your files, your browser, your calendar, your email, and it does real work.

A 6-year-old built a game with it. A grandmother approved the setup.

🚀 What Skales Can Do

🎯 Background Goals

Type /goal and what you want, like /goal build me a trading bot, and Skales takes it on as ongoing work instead of a single reply. It plans the steps and runs the whole task autonomously, in the background with the chat closed, picking back up where it left off after you reopen the app. It stops only when the task is done, when it genuinely needs your decision, or before a consequential action like sending an email, where it asks once (with a one-tap always-allow); it does not pause every few steps to ask you to continue. A long chat that grows into a real multi-step task is carried on as a goal on its own, and a goal that parked at its limit resumes itself while you are idle. Run more than one at a time, set one on a repeating schedule, or let Skales recognize a goal from how you ask. The step limit under Settings is a safety ceiling against a runaway task (0 means run to completion), not a check-in. Every finished goal folds what it learned back into Memory, so the next one starts ahead.

💻 Code Mode (/code)

Point any chat at a folder on your computer and it works there like Claude Code, without leaving the conversation. A Chat / Code / Edits / Plan / Auto switch under the composer, on the New Chat screen (pick a folder and mode before your first message), or the /code command (/code <task> to start in one line) binds the folder: Plan investigates and proposes, read-only; Code asks before each edit; Edits approves your file edits as it goes but still asks first before a shell command, a git push or a deploy; Auto runs the whole task on its own after a one-time consent. It patches files with edit_file instead of rewriting them, runs your build, installs and tests (test_run), and commits and pushes with your own git identity (git_commit / git_push, no added attribution). It renders git diffs inline in the chat as colored changes (green added, red removed) instead of plain text, and the model gets a repo map of the bound folder (which files exist and what each exports and imports) so it heads straight to the right file in a larger codebase. Shell commands get real time to finish (configurable up to 10 minutes), so installs, builds and deploys complete; it can deploy the folder with deploy_project (Firebase/Vercel/Netlify/npm) and ask you structured questions with a slide-up form when it needs a decision. A dedicated Chat & Code settings tab lets you give code work its own model (run a strong cloud model for code while chat stays on your default) and turn on deep reasoning (xhigh). If the folder is outside what Skales may touch, it asks first and widens access only the way you choose. Each chat keeps its own folder, so a normal chat is unchanged. Every file change carries a one-click Undo (per file, or "Undo all" for a whole turn), edits still land when the model's quoted text is slightly off (whitespace and indentation tolerant), each change shows an added/removed count at a glance, typing @ suggests the files in your bound folder so you can point at the exact one, and in Plan mode Skales asks a couple of quick clarifying questions before laying out the plan, then a Build this plan button carries it straight into Code.

✨ Skales IQ + Skales Stack

Skales IQ is a free, built-in trial model: start chatting the moment you open Skales, no API key of your own, with tool use and vision included. When the trial runs out, add your own key (15+ providers) or switch to a local model and keep going for free. Skales Stack is an optional toggle that answers a few trivially-deterministic things (the live time, plain arithmetic) instantly on your machine without spending a model call, and shows which local capabilities (media, browser, search) are ready.

📐 Workflows

Workflows are the hand-drawn half of the goal system. A typed /goal lets Skales plan the steps for you