Security and privacy

HoloDesktop CLI operates your real desktop. It can observe visible windows, reason over what it sees, click, type, scroll, and interact with local apps. The main privacy question is where the model runs. See Hosted or local models to pick a mode.

​

What H Company receives

​

What the agent can see

During a run, the CLI observes the visible desktop so it can decide what to do next. Observations can include anything visible on screen:

• apps and browser tabs;
• local documents;
• chat or email content;
• account names and workspace names;
• file paths;
• permission dialogs;
• secrets or personal information visible in the foreground.

Anything visible on screen can become task context. Before a sensitive run, close unrelated tabs, documents, chats, password managers, and admin consoles.

​

What H Company retains

The CLI itself does not upload a recording of your desktop, your local run artifacts, or your local runtime logs to H. In hosted mode, the Models API is zero data retention by default: prompts and screenshots are processed and discarded, and only request metadata (time, model, token counts) is kept. H is SOC 2 and ISO 27001 certified and runs its own models, so nothing is shared with a third-party model provider.

​

Local artifacts

The CLI keeps diagnostic artifacts on your machine so you can inspect and debug runs. Those artifacts can include task text, event history, screenshots, model outputs, tool results, local paths, and app state that appeared during the run. These files are local diagnostics, not an analytics upload. They are useful for debugging but can be sensitive, so review and redact them before sharing, and prefer redacted snippets over whole run directories when posting in an issue or attaching them to support threads. For exact paths, see Paths and files. For event structure, see Debug a failed run.

​

Host integrations

When HoloDesktop CLI runs through MCP, ACP, or a skill, the host decides when to call it and what task text to pass into the run. Before enabling a host integration, check:

• whether the host asks before tool calls or can invoke tools automatically;
• whether the configuration is project-local or global;
• whether the prompt gives the CLI permission to operate unrelated apps;
• whether the visible desktop contains information outside the task.

The privacy boundary does not change because the call came from a host: model inputs go where the mode sends them.

​

Practical checklist

Before a sensitive run:

​

Next steps