Download
← All posts
Updates Jun 28, 2026

Skales v11.6.0 - Bedrock

Replies no longer freeze, reasoning models get the time they need to finish, and long tasks that write lots of files now run all the way through. Your reminders, goals and memory are far more dependable too, so nothing silently gets skipped or scrambled. And other improvements.

We're pleased to share Skales v11.6.0, an update focused on making your local AI agent more dependable and straightforward. This release centres on ensuring that when Skales says it's done something, it truly has, and it communicates clearly when it hasn't.

Tools Work as Advertised

Across all the tools Skales uses, from messaging and your calendar to Notion and YouTube, actions now accurately report their status. If something fails, isn't configured correctly, or only partially succeeds, Skales will tell you immediately with a clear reason, rather than a misleading "success" message.

Messages Reach Their Destination

Sending messages is now more precise. WhatsApp will match contacts exactly to avoid sending to the wrong person. Telegram confirms a message has truly been sent, and Discord will split long messages appropriately. Twitter mentions and your timeline are back, and Signal will correctly report delivery failures.

Dependable Reminders and Scheduled Tasks

Reminders will now fire at the correct time, and any delivery errors will be retried instead of being lost. Scheduled goals that previously crashed will now recover and run, and malformed schedules will be rejected upfront.

Longer Tasks Complete

Goals that involve writing many files will no longer stop prematurely. If a step is cut off by length, valid parts will still run, and the rest will be retried. Tasks waiting for your approval will no longer be mistaken for failures.

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 →