- Home
- Skills
- Agents & Orchestration
- Agent Desktop for Linux
Works with the AI Agents you already use
Agent Desktop for Linux
Give your AI agent its own isolated Linux desktop. It operates real apps with its own pointer and keyboard while you keep working on yours.
Free
Agent Desktop for Linux
Example session with this skill installed
Open a local form in the browser on your own desktop, fill in the name "Ana López", choose "Portugal", tick "I accept" and submit it. Don't touch my mouse.
- Read your context and instructions
- Compiled the agent desktop
What I did
Done. I worked on my own private display, so your pointer, keyboard and windows were never touched.
| Step | Command | Result |
|---|---|---|
| Start private desktop | adc start --nested | Display :7, openbox, private accessibility bus |
| Open the form | adc browser file:///…/form.html --name work | Chrome with an agent-owned profile |
| Read the page | adc snapshot -i --app chrome | 5 form controls found |
| Name | adc type @4cd4:e14 "Ana López" | Typed with the real keyboard (accents included) |
| Country | adc select @4cd4:e16 Portugal | Selected, dropdown closed |
| Consent | adc check @4cd4:e15 | Checked |
| Submit | adc click @4cd4:e17 | Pressed "Enviar" |
| Verify | adc find --name "Enviado" | "Enviado: Ana López / true / Portugal" |
| Finish | adc stop | Browser closed gracefully, cookies saved |
Snapshot excerpt
- textbox "Nombre" @4cd4:e14 [69,172 159x22]
- checkbox "Acepto" @4cd4:e15 [235,174 14x14]
- combobox "País" @4cd4:e16 [335,173 73x20]
- button "Enviar" @4cd4:e17 [411,172 55x22]
Next steps
- Add
--record ~/Videos/form.mp4toadc startto get a video of the run. - If a site asks for a login or captcha, I'll run
adc ask-userand you finish that step yourself in one click.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual GUI automation on Linux is high-friction, often stealing focus or clashing with user activity. This skill provides a dedicated, isolated X11 workspace where an agent operates its own pointer and keyboard without interrupting your work.
What it does
- Isolated Desktop Management creates a private Xephyr display with its own focus, clipboard and D-Bus session
- Accessibility-First Navigation uses AT-SPI to snapshot, find, and interact with GUI elements via stable references.
- Human-Like Input simulates real pointer glides, clicks, drags, and keyboard events that trigger genuine application logic.
- Visual Verification captures screenshots with coordinate grids and screen recordings for task auditing.
- Persistent Browsing manages isolated browser profiles so agent sessions and logins stay separate from yours.
- Safe User Hand-off triggers system notifications for captchas or 2FA, allowing you to temporarily take control.
How it works
- Run
adc doctorto verify system dependencies and X11 environment compatibility. - Initialize a private session using
adc start --nestedto launch the isolated agent workspace. - Use
adc snapshotoradc findto identify interactive elements by their accessibility roles and names. - Execute actions like
adc click @ref,adc type, oradc drag-xyto complete desktop tasks. - Terminate the session with
adc stopto gracefully close applications and save recordings.
Frameworks & tools
Built for Linux (X11/GNOME) environments using Python 3, PyGObject, AT-SPI, Xephyr, Openbox, and ImageMagick. It integrates standard CLI tools like xdotool, wmctrl, and ffmpeg for input and media handling.
Why this beats prompting it yourself
Standard agents struggle with GUI coordinates and focus stealing, often failing when window positions shift. This skill provides a structured accessibility engine and a sandboxed display, ensuring the agent interacts with actual UI objects rather than guessing pixel locations.
Use cases
- Automating form entry in legacy desktop applications that lack an API.
- Setting up and testing complex software environments in an isolated workspace.
- Performing long-running web tasks that require persistent sessions and visual verification.
- Recording step-by-step GUI tutorials or bug reproductions automatically.
Known limitations
Does not support Wayland native sessions. Applications that do not expose an accessibility tree require coordinate-based interaction. Requires specific system packages listed by the doctor command.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires X11 environment. No native Wayland support. Apps without AT-SPI trees require coordinate-based interaction. Specific apt packages like Xephyr and Openbox must be installed.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 8 days ago
- Free with an Agensi account
- Software
Python 3 (PyGObject, AT-SPI)XephyropenboxxdotoolImageMagickFFmpeg
Node.js
Git
- Optional
- Google Chrome
Permissions
File Scopes
Runs a private X display (Xephyr) on its own workspace. Writes screenshots and state to $XDG_RUNTIME_DIR/adc, agent browser profiles to ~/.local/share/adc (mode 0700) and optional recordings to ~/Videos. Network is only used by the browser the agent opens. Credentials are never typed by the agent: sign-ins are handed to the user.