Download
← All posts
Tutorials Jun 10, 2026

Run Skales completely free - local models and real free-tier APIs

No paid plan, no GPU farm, no trial countdown. Three honest ways to run a full AI agent at zero cost - fully local with Ollama, free cloud tiers, or the ChatGPT subscription you already have.

Skales itself never charges a subscription - it is free for personal use. The only cost is the AI model behind it, and even that can be zero. Three ways, in order of privacy:

1. Fully local - Ollama or LM Studio

The maximum-privacy path: install Ollama or LM Studio, and Skales auto-detects them. Browse the model library inside Skales, install a model with one click, done - no API key, no internet required, nothing ever leaves your machine.

Good starting points on normal hardware: qwen3, gemma, llama3.3 or mistral in small sizes. Turn on LLM Profiles and even compact models handle Skales' tools reliably.

2. Real free cloud tiers

Several providers offer genuine free tiers - paste one key into Settings → AI Providers and go:

The community keeps a current overview of who offers what: Free LLM API Resources. Pick one, drop the key into Skales, and you are running.

Bonus: configure several and the Fallback Provider Chain switches automatically when one hits a rate limit. Free tiers chained together are surprisingly robust.

3. The subscription you already pay for

If you have ChatGPT Plus, Pro, Business or Enterprise: sign in with it under Settings → AI Providers → Subscriptions - no API key needed. Your existing plan becomes your agent's brain. Power users can bring a Claude Code or Gemini CLI token the same way.

The point

A real autonomous agent - goals, coding, email, media - at a running cost of exactly zero is the whole reason Skales is BYOK. Your keys, your models, your machine.

Download Skales - the install takes 30 seconds, and there is no trial clock ticking.

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 →