Download
← All posts
Updates Jun 21, 2026

Skales v11.4.22 - Real Work

Your agents used to stop after about ten steps and call it done. Not anymore. Scheduled tasks, autopilot, and anything you send from Telegram, WhatsApp, or the Buddy now run real multi-step work all the way to the end, as deep as a goal.

Hello everyone,

We've just released Skales v11.4.22, and this update is focused on making sure your AI agent can actually get more done for you. We've been listening to your feedback about tasks not quite finishing, and we've made some significant improvements to how Skales handles longer, more involved work.

Deeper Task Execution

Previously, tasks might stop after a few steps, even if there was more work to be done. Now, your scheduled, planner, and autonomous tasks will run much deeper, respecting your set "Goal step budget" (or running to completion if you set it to 0). This means your AI can tackle more complex, multi-step projects without interruption.

Enhanced Multi-Agent Collaboration

When Skales uses multiple agents to complete a subtask, each agent will now work more thoroughly. This ensures that each part of the job is completed properly before moving on, leading to more reliable outcomes.

Improved Task Budgets

Tasks coming in from Telegram, WhatsApp, the desktop Buddy, and the CLI now have a more realistic working budget. This allows for more substantial work to be done on each incoming task. The desktop Buddy has also been updated to scale its capabilities with the model you're using, just like our communication channels.

More Capable Browser and WordPress Agents

For tasks involving web browsing or managing WordPress sites, our agents can now execute more steps. We've also increased the per-turn tool-call limit, meaning these agents are less likely to be cut short when working with multiple files or pages.

Increased Autonomous Work Capacity

We've raised the hourly call budget for autonomous tasks. This makes it more feasible for Skales to complete those deeper, multi-step runs that are essential for getting real work done.

We're excited for you to try these improvements.

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 →