Setup guides

Build a local AI agent stack one clean step at a time.

These tutorials cover the pieces users ask for first: Ollama, OpenAI API keys, local GGUF models, MCP tools, and desktop automation in MultiAgentOS.

See product Browse use cases

Product demo

See the full desktop AI workspace.

Full-frame MultiAgentOS screenshots from the current app: a built-in browser the agent drives, the Bridge chat panel, model routing, and structured results together.

1 Ask
2 Route model
3 Run tools
4 Review action

Full-frame MultiAgentOS workspace showing the navigator, the browser workspace in the centre, and the Copilot Agent Inspector with Chat, Plan, Activity, Artifacts, and Context. — Full-frame screenshot from the current MultiAgentOS app.

Browser workspace screenshot in MultiAgentOS. — **Browser workspace** Drive a built-in browser from the chat panel and watch every step in one window.

Visible tool runs screenshot in MultiAgentOS. — **Visible tool runs** Every tool call is shown with its arguments and result, so nothing happens behind your back.

Live research screenshot in MultiAgentOS. — **Live research** Read and act on real pages while the Bridge chat panel stays docked below.

Set up Ollama for local AI agents

Install Ollama, pull a model, confirm the local server, and connect it to MultiAgentOS.

Read guide

Add an OpenAI API key safely

Create a project key, store it securely, and route selected workflows to OpenAI models.

Read guide

Choose local GGUF models

Understand quantization, memory, context, and test prompts before trusting a model in an agent.

Read guide

Connect MCP tools

Use MCP servers to expose controlled tools to your desktop AI agent.

Read guide

Desktop automation setup

Prepare permissions, visible status, stop controls, and scoped actions for safe desktop operations.

Read guide

Long-form Ollama walkthrough

Read the deeper blog version of a local agent setup with Ollama.

Read article