Is Osaurus for Windows free?

Yes. No subscription, and no caps on local use. You only pay a cloud provider if you choose one, or for optional Osaurus Cloud credits.

Do I need an account?

No. Install it from the Microsoft Store and start. You only need an Osaurus account for cloud credits or Workspaces.

Do I need a graphics card?

Only to run models on your PC, where most models want 8 GB of video memory or more. Without one, use cloud models with your own keys or subscription. The agents, memory, and tools work the same.

Can I use my ChatGPT or Claude subscription?

Yes. Sign in with ChatGPT, or use your Claude Pro or Max plan through Claude Code. No API key to paste.

Does it work on Snapdragon and other ARM64 laptops?

Yes. It runs as a native ARM64 app. Cloud models work on any ARM64 PC. Local models run on the CPU there unless the PC has an NVIDIA GPU, so cloud models are the better fit.

Does it run on Windows 10?

The beta is built for Windows 11. It also installs on Windows 10 version 2004 or later, but we recommend Windows 11.

Does my data leave my PC?

Your chats, files, and models stay on your PC, encrypted. Prompts leave only when you use a cloud model, and only to that provider. Usage analytics and crash reports are optional. Turn them off in Settings, under Data & privacy.

How is it different from the Mac app?

The same agents, memory, tools, and choice of model. Workflows, image generation, and voice are not on Windows yet. They arrive during the beta.

It is a beta. What should I expect?

Frequent updates through the Microsoft Store, and some bugs, especially in first-run model downloads and with less common graphics drivers. Tell us what broke in the Windows community.

Public beta · Free on the Microsoft Store

Own your AI.
On Windows.

AI agents that live on your PC. They read your files, run commands, browse the web, and keep working while you are away. Run open models on your own graphics card, or connect the cloud models you already use.

Get it from the Microsoft Store

No account
x64 and ARM64
Native Windows app
Encrypted on disk

Osaurus for Windows running an open-source AI model on a PC, showing the agents sidebar and a new chat.

Agents that do the work.

Osaurus does the job instead of handing you an answer to copy and paste. Give it a goal and a folder, and follow each step.

Agents

Ask once. It reads, runs, and reports back.

An agent reads the files, runs PowerShell and git, searches the web, and shows every step it took. For a bigger job, agents split the work and report back.

Reads and edits files, documents, and PDFs
Runs commands in PowerShell, with git built in
Searches the web and cites its sources

An Osaurus agent on Windows answering a question about slow map loading, showing the files it read, the command it ran, a web search and a code fix.

Approvals

It asks before it edits.

Agents ask before they edit a file or run a command. See the change, then allow it once, or always for that agent and folder. Every change is saved, so you can undo it later.

Approve inline, per agent and per folder
Every file change is saved and can be reverted
Set any agent to always ask, or never touch your files

Osaurus for Windows asking for permission before editing a file, with a diff of the change and Deny, Always allow and Allow once buttons.

Local models

Models that fit your PC.

Osaurus checks your graphics card and memory and tells you what runs well before you download. It uses the fastest option your PC has: CUDA on NVIDIA, then Vulkan, then the CPU. Once a model is on disk, it works offline.

Qwen, Gemma, gpt-oss, Llama, and more from Hugging Face
Finds the models you already have in LM Studio and Ollama
Works with NVIDIA, AMD, and Intel graphics

The Osaurus model catalog on Windows showing Qwen 3.8 27B, its GGUF quantization, VRAM fit on an RTX 5090 and a Download button.

What ships in the beta.

These are built in today. There is nothing extra to install.

A browser your agent drives.
Watch it work through a site, take over when you want, then hand it back. Logins stay in an encrypted vault.
Runs while you are away.
Schedule a task for every morning, or start one when a file lands in a folder.
Message it from other apps.
Talk to your agents from Telegram, Slack, or Discord, or connect them to n8n.
Your agents, on your iPhone.
Pair an iPhone with Osaurus Connect and pick up a conversation away from your desk.
Connect your tools.
Connect MCP servers, including ones that use OAuth sign-in. Their tools go through the same approvals.
A local AI server.
Point any OpenAI-, Anthropic-, or Ollama-compatible app at 127.0.0.1:1337, and it uses your models.
Memory and skills.
Agents keep a memory of your work, with a note of where they learned each thing. Import new skills from GitHub.
A sandbox for code.
Agents can install packages and run code in a Linux sandbox on WSL, away from your files.

One set of agents.
Any model you choose.

Choose a model for each agent and switch any time without losing its memory or skills. Run open models on your PC, sign in with a plan you already have, or bring your own keys.

Rather not manage keys? Osaurus Cloud credits give you frontier models from a prepaid balance. They are optional, and only for cloud models.

Sign in

ChatGPT
Claude Pro or Max, through Claude Code
xAI
OpenRouter

Your API key

OpenAI
Anthropic
Google Gemini
Azure OpenAI
DeepSeek
Venice
Any OpenAI-compatible endpoint

On your PC

Open models on your GPU
Ollama
Another Osaurus PC on your network

OpenAI
Anthropic
Google Gemini
xAI
OpenRouter
Venice
Ollama
LM Studio

Private by default.

Your chats, keys, and models live on your PC. Local models never touch the network. When you choose a cloud model, only that agent sends anything, and only to that provider.

Encrypted on disk.
Chats, memory, and keys sit in an encrypted database, locked to your Windows account.
Privacy Filter.
Swaps personal details for placeholders before a prompt reaches a cloud model, shows you what it found, and puts the real values back in the reply.
No account.
Install it and start. You only need an Osaurus account for cloud credits or Workspaces.
Diagnostics are your choice.
Usage analytics and crash reports help us fix the beta. Turn either one off in Settings, under Data & privacy.

Runs on the PC you already have.

Any Windows 11 PC runs Osaurus with cloud models. Local models want a graphics card with 8 GB of video memory.

With cloud models

Windows 11
x64 or ARM64
Any graphics card, or none
An internet connection for the provider

With models on your PC

8 GB of video memory or more: NVIDIA, AMD, or Intel
16 GB of RAM
About 20 GB free for a typical model
Internet once, to download the model

No 8 GB graphics card? Use cloud models, and keep the agents, memory, and tools on your PC. On ARM64 laptops, local models run on the CPU unless the PC has an NVIDIA GPU.

Still have questions?

Ask the people who build it in the Windows community.

Get it from the Microsoft Store