Kwin-MCP – MCP server for AI-driven Linux GUI automation via KWin
Isolated KWin sessions bypass RemoteDesktop portal; AI agents control Linux GUIs without prompts.
Zero-dependency Rust CLI for cross-platform GUI automation. Screenshots, window management, mouse, keyboard. JSON-in/JSON-out. Built for AI agents.
Grid-cell targeting beats pixel guessing and works where accessibility trees fail.
Developers building AI agents, automation engineers
pyautogui · xdotool · SikuliX
Isolated KWin sessions bypass RemoteDesktop portal; AI agents control Linux GUIs without prompts.
Splitting planner (Claude/Codex) from an orchestrator/skill layer that handles retries, rollback and stateful sessions is the project's best idea — it directly targets the brittleness of long LLM GUI workflows. The repo gives practical bits (CLI, install script, direct coordinate tap mode and unified JSON outputs), but it's early and niche: useful if you're building LLM-controlled phone automation, less interesting for general automation folks.
Feature-first flag model with staged rollout, but LaunchDarkly and Split already own this space.
Requests-based automation beats browser overhead when the AI can reverse-engineer APIs.
Dependabot alternative with AI test generation and supply chain poisoning checks.
Visual diff trees beat screenshot dumping for token efficiency at scale.