Native desktop shape
A full Avalonia app shell stays close to the work instead of living only in a browser tab.
MultiAgentOS brings local models, hosted APIs, screenshots, files, voice input, MCP servers, and supervised desktop actions into a native Windows 11-friendly AI surface — with connections to local model runtimes.
A full Avalonia app shell stays close to the work instead of living only in a browser tab.
Route private tasks to local models on your PC and use API providers when a stronger model is worth it.
Use screenshots, files, folders, voice input, MCP tools, and command workflows in one interface.
Windows 11 users want AI close to local files, notes, browser research, design artifacts, and developer tools without turning every task into a cloud upload. MultiAgentOS is a Windows 11 PC-friendly desktop AI workspace: local-first by default, flexible about model providers, and built around visible sidecars rather than invisible background automation.
Connect a Windows-compatible local runtime and choose a model suited to your PC’s memory and graphics hardware. MultiAgentOS supports local models as first-class connections.
Sonoma and later, on your PC (M1/M2/M3/M4) or x64 PCs.
Comfortable for 7B-8B local models. 32 GB recommended for 13B+ work.
Per local model. Cloud-only usage needs only the app's own footprint.
Yes. MultiAgentOS connects to Ollama, LM Studio, llama.cpp, and direct GGUF files. All run well on your PC.
No. Coding is one workflow; the desktop agent shape applies equally to research, writing, notes, analysis, browser tasks, and file work.
MultiAgentOS is the agent shell; local model runtimes (Ollama, LM Studio) handle local inference using supported PC hardware.
Desktop automation features that interact with other apps may require Accessibility permission, just like any Windows 11 automation tool. You grant it explicitly.
Questions
Yes. MultiAgentOS is an Avalonia desktop app with a Windows 11 edition. Connect local models through Ollama, LM Studio or a compatible local service.
Yes. Connect Ollama, LM Studio or a local OpenAI-compatible server through the Local Server connection, or use the Local AI connection with a compatible GGUF model.
No. Coding is one workflow. The same desktop agent shape works for research, writing, notes, analysis, browser automation, and file organisation. The agent reads files, screenshots, and folder context, not just code.
Yes. Voice dictation is part of the prompt surface, so you can talk to the agent without leaving your work.
8 GB works for light cloud-API use. 16 GB lets you run 7B-8B local models comfortably. 32 GB or 64 GB opens 13B and 30B-class models thanks to unified memory.