Download
← All posts
Updates Aug 12, 2026

Skales v12.7.4 - Skales Local

This release ships Skales Local, an inference server that lives inside the app. No key, no account, no separate install. Chat, dictation, read-aloud and images can each run on your machine first, with the cloud as fallback, or stay fully local.

We've just released Skales v12.7.4, bringing some significant updates to how you can use Skales on your own machine. This version focuses on giving you more control and transparency over your AI interactions, especially when working locally.

Your AI, Your Rules

Skales now ships with its own inference server built right into the app. This means you can use many AI models without needing external keys, accounts, or separate installations. You'll find a new "Models" tab in Settings where you can browse, search, and manage models categorised by their function – language, vision, voice, and more.

Local First, Cloud Second

You now have explicit control over where each AI capability runs. Chat, dictation, read-aloud, and image generation can each be set to prioritise your local machine, the cloud, or be turned off entirely. This gives you the flexibility to keep sensitive data local or leverage cloud power when needed, with clear indicators showing which model is active.

Clearer Answers, Clearer Choices

Before you send a message, you'll see the name of the AI model that will respond, right above the composer. If a task needs to go to the cloud, Skales will now indicate why. When neither your local setup nor the cloud can provide an answer, you'll get a clear explanation instead of a spinning icon.

Bringing Your Own Models

Downloading models is now more robust, with progress indicators, resume functionality, and checksum verification. You can also easily bring your own compatible models (.gguf, .onnx, .safetensors) directly into Skales. The app now also recognises and uses existing model folders from Ollama and LM Studio, so your disk space is used efficiently.

Download Skales

New here? Skales is the private AI agent you install like an app - free for personal use, any model, everything stays on your machine.

Download Skales

More from the blog

Updates Sep 6, 2026 Skales v12.9.26 - Grip Grip is the release where Skales stops when you say stop, and tells you what it costs before it spends. Under every reply sits the price of the session, read from the provider or from the price table, with the sub-agents' bill included; a ceiling you set in Goals stops a run before the next paid step and asks you three things - continue, take a cheaper model, or stop - in the chat, in the Code window, in Iris and on the phone. A typed "stop" is honoured before the first request leaves the machine, and a stopped run says so in its own bubble instead of pretending it finished. Credentials are locked away from the file, shell and search tools; a bulk action or a publish asks first, in every mode, and a yes never covers more than the card names. Updates Sep 4, 2026 Skales v12.9.25 - Backbone Backbone is the release where Skales got one engine. A chat you type, a task you scheduled, a job on a timer, a plugin, a webhook, a Discord message, a Telegram or WhatsApp turn and the desktop Buddy used to run on different loops with different rules; now they all run on the same one, with the same guards, the same budget and the same record of what happened. Close Skales in the middle of a run, update it, let it crash: the run comes back as an unfinished run, says how far it got, and one Continue picks it up at that step. Ask for something big and Skales can hand parts of it to sub-agents, each in its own checkout of your repository, and collect the results. Under every reply sits a context meter that names what filled the window: the system prompt, the tool definitions, your skills, your memory and the conversation itself. Updates Sep 2, 2026 Skales v12.9.21 - Cockpit 2.0 Cockpit 2.0 is named for the screen it replaces. What used to be two stacked tab bars, a second title and a row of icon chips is now one board: everything that stands, in four columns, with goals, your own tasks, Autopilot tasks and schedules as cards you can filter, drag and act on. One head, one action. The phone got the same board in 2.9.21, and a computer on an older version still fills it from what it can tell rather than showing an empty screen.

All posts →