virtual-remote-desktopKasmVNC-based virtual desktop for headless Linux with AI-first automation and human handoff. Use when most steps are automated but a user must manually inter...
Install via ClawdBot CLI:
clawdbot install zhangxin15435/virtual-remote-desktopUse this when the workflow is:
This version replaces x11vnc+noVNC with KasmVNC and keeps computer-use style action scripts for AI control.
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/install_kasmvnc.sh
This installer also prepares required runtime tools:
fluxbox (lightweight desktop)xdotool + scrot (computer-use actions)xauthBefore starting, always confirm these user requirements:
127.0.0.1) or ไธดๆถๅ
ฌ็ฝ (0.0.0.0)Use guided script (interactive Q&A):
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/start_vrd_guided.sh
Preview config without starting:
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/start_vrd_guided.sh --dry-run
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/start_vrd.sh
Important env vars:
AUTO_LAUNCH_URL (optional): open target page automaticallyKASM_BIND (default 127.0.0.1, safer)AUTO_STOP_IDLE_SECS (default 900)BROWSER_MOBILE_MODE=1 (launch browser with mobile emulation)BROWSER_DEVICE=iphone14pro|pixel7|ipadExample:
AUTO_LAUNCH_URL="https://example.com/login" \
AUTO_STOP_IDLE_SECS=1200 \
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/start_vrd.sh
Mobile-friendly VNC stream example (better phone takeover UX):
MOBILE_MODE=1 MOBILE_PRESET=phone \
AUTO_STOP_IDLE_SECS=900 \
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/start_vrd.sh
Mobile stream options:
MOBILE_MODE=1 enables mobile defaultsMOBILE_PRESET=phone|tablet sets default resolution (960x540 / 1280x720)KASM_MAX_FPS can be lowered further (e.g. 18) on weak networksBrowser mobile emulation (website renders as mobile page):
AUTO_LAUNCH_URL="https://example.com" \
BROWSER_MOBILE_MODE=1 BROWSER_DEVICE=iphone14pro \
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/start_vrd.sh
Notes:
MOBILE_MODE (which optimizes VNC stream size).bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/status_vrd.sh
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/health_vrd.sh
bash /home/ubuntu/.openclaw/workspace/skills/virtual-remote-desktop/scripts/stop_vrd.sh
All actions run on the active virtual display from pids.env.
# screenshot (base64)
bash scripts/action_screenshot.sh
# click / type / key / scroll
bash scripts/action_click.sh 500 420 left
bash scripts/action_type.sh "hello"
bash scripts/action_key.sh "ctrl+l"
bash scripts/action_scroll.sh down 4
# helpers
bash scripts/action_mouse_move.sh 800 300
bash scripts/action_cursor_position.sh
bash scripts/action_wait.sh 2
Recommended loop:
action_screenshot.shaction_click/type/key/...When captcha/risk-control appears:
This avoids full manual operation while keeping recovery fast.
KASM_BIND=127.0.0.1KASM_BIND=0.0.0.0AUTO_STOP_IDLE_SECS (e.g. 300)~/.openclaw/vrd-data by default.CHROME_PROFILE_DIR.Generated Mar 1, 2026
Automates login and product listing updates on platforms like Amazon or Shopify, with AI handling routine tasks. When a captcha or risk check appears during login, a human takes over remotely via the VNC session to solve it, then AI resumes automation to complete the listing process. This reduces manual effort while ensuring compliance with platform security measures.
AI schedules posts and engages with followers on platforms such as Facebook or Instagram, automating content distribution. If a multi-factor authentication (MFA) prompt or suspicious activity alert triggers, a user intervenes remotely to approve the action, after which AI continues posting and monitoring. This streamlines campaigns while maintaining account security.
Automates customer data entry and verification for banks or fintech apps, processing forms and documents efficiently. When risk-control systems flag a transaction or require manual approval, a staff member takes over via the virtual desktop to review and authorize, then AI proceeds with the next steps. This speeds up onboarding while adhering to regulatory checks.
AI manages login and in-game tasks for platforms like Steam or mobile games, automating repetitive actions such as claiming rewards. If a captcha appears due to unusual activity, a gamer remotely solves it through the VNC interface, and AI resumes automation to complete the session. This enhances gameplay efficiency without compromising account safety.
Automates booking and reminder systems for clinics, handling patient data entry and calendar updates. When a login requires manual approval or a captcha challenge arises, administrative staff intervenes remotely to resolve it, then AI continues scheduling tasks. This improves operational flow while ensuring data privacy and accuracy.
Offer monthly plans for businesses to access the virtual desktop skill, providing AI-driven automation with human handoff for captcha and risk-control tasks. Revenue comes from tiered subscriptions based on usage hours or number of automated workflows, targeting SMEs needing efficient digital operations.
Charge per instance of human intervention, such as captcha solving or MFA approval, integrated with the skill's VNC sessions. Revenue is generated from micro-transactions for each handoff event, appealing to freelancers or agencies managing multiple automation projects with variable demand.
Sell annual licenses for large organizations, including customization, training, and priority support for the virtual desktop skill in high-stakes industries like finance or healthcare. Revenue stems from upfront licensing fees and ongoing support contracts, ensuring reliability and compliance in automated processes.
๐ฌ Integration Tip
Integrate this skill with existing AI workflows by using the provided action scripts for screenshot analysis and mouse control, ensuring seamless handoff between automation and human intervention.
Advanced filesystem operations - listing, searching, batch processing, and directory analysis for Clawdbot
Perform advanced filesystem tasks including listing, recursive searching by name or content, batch copying/moving/deleting files, and analyzing directory siz...
Essential SSH commands for secure remote access, key management, tunneling, and file transfers.
Extract text from PDF files for LLM processing
The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.
Advanced filesystem operations - listing, searching, batch processing, and directory analysis for Clawdbot