OpenGUI — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by akemmanuel · Codex Skill · ★ 113

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is OpenGUI safe to install? View the security audit →

About OpenGUI

Desktop + web command center for coding-agent Harnesses. Run OpenCode, Claude Code, Codex, and Pi across multiple projects with streaming chat, prompt queue, model switching, voice input, and MCP tools. Download latest release · Why OpenGUI · Supported Harnesses · Buil

agent-uiai-agentsclaude-codecodexcoding-agentsdesktop-appdeveloper-toolselectronllm-toolsopencode

Quick Facts

Stars113
Forks10
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score67.94509379381/100
Open Issues1
Last Updated2026-10-01
Created2026-02-17
Platformsbrowser, claude-code, codex, node
Est. Tokens~16k

Compatible Skills

These tools work well together with OpenGUI for enhanced workflows:

  • agentrove — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (60%)
  • palot — semantic(0.42)+complementary+same_lang+similar_pop+shared_platform (60%)
  • prompt-line — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • skill-manager — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)

OpenGUI alternative? Top 6 similar tools

Looking for a OpenGUI alternative? If you're comparing OpenGUI with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • jat by joewinke · ⭐ 251

    The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic S

  • palot by ItsWendell · ⭐ 190

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • sandboxed.sh by Th0rgal · ⭐ 514

    Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

  • sage by usetig · ⭐ 106

    An LLM council that reviews your coding agent's every move

  • ai-agent-session-center by coding-by-feng · ⭐ 82

    Real-time dashboard for Claude Code and Codex AI coding agents: live terminals, status alerts, prompt queues,

  • mcp-gearbox by rohitsoni007 · ⭐ 62

    A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is OpenGUI?

OpenGUI is Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.. It is categorized as a Codex Skill with 113 GitHub stars.

What programming language is OpenGUI written in?

OpenGUI is primarily written in TypeScript. It covers topics such as agent-ui, ai-agents, claude-code.

How do I install or use OpenGUI?

You can find installation instructions and usage details in the OpenGUI GitHub repository at github.com/akemmanuel/OpenGUI. The project has 113 stars and 10 forks, indicating an active community.

What license does OpenGUI use?

OpenGUI is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to OpenGUI?

The top alternatives to OpenGUI on Agent Skills Hub include jat, palot, sandboxed.sh. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools