agent-workspace-linux
Active·★ 195·MIT·Updated 2026-10-18
Agent-workspace-linux provides an isolated, hidden Linux desktop environment for AI agents, allowing them to control a dedicated graphical interface and browser without interfering with the user's main system. This enables agents to perform tasks like GUI testing or web automation in a sandboxed, observable workspace.
#AI Agent Workspace#Isolated Environment#Headless Linux#X11 Display#Browser Automation#Sandboxing#Model Context Protocol (MCP)#GUI Automation
01
Features
01Isolated X11 workspace for agents with GUI control.
02Daemon-enforced permission ceiling for network, mounts, and applications.
03Sandboxed browser control via loopback CDP, independent of host browser.
04Live floating viewer for real-time observation and control (pause/stop).
02
Compatibility
Linux
Operating System
Verified via docs
X11
Display Protocol
Verified via docs
03
Quick start
1
$ sudo apt install xvfb openbox xdotool xauth x11-utils imagemagick xclip bubblewrap pkg-config libxkbcommon-x11-dev
2
$ ./install.sh
04
Use cases
↳QA GUI applications or websites without interfering with the user's live desktop.
↳Perform browser, web, or shopping automation in an isolated, observable, and disposable profile.
↳Run, screenshot, and inspect applications in a clean, temporary Linux desktop environment.
↳Provide a dedicated desktop for long-running or headless agents without human supervision.
05
Alternatives
lnwjud★ 205
Windows-first local AI-agent runtime & MCP gateway with 214 configurable tools (208 advertised by default) for files, Git, processes, WSL, desktop/browser automation, MCP Tasks, observability, and Secure MCP Tunnel.
ILSpy-Mcp★ 75
🔓 UNLEASH ILSpy'S POWER. Reverse-engineer DOTNET code at GOD SPEED. AI-assisted debugging that THINKS with you. Decompile ANYTHING. 🚀
filesystem-mcp★ 25
A local filesystem MCP server that lets LLMs and AI agents read, write, search, diff, patch, and manage files safely and efficiently. Built for reliable, structured, and controlled filesystem interaction.
mockloop-mcp★ 17
Intelligent Model Context Protocol (MCP) server for AI-assisted API development. Generate mock servers from OpenAPI specs with advanced logging, performance analytics, and server discovery. Optimized for AI development workflows with comprehensive testing insights and automated analysis.
StructSmith★ 26
Local-first, MCP-native tool for modelling software architecture. C4-style semantic model, React Flow editor, SQLite, single container — a self-hosted Structurizr alternative your AI client can edit over MCP.
Comments
Log in to leave a comment
No comments yet. Be the first!