codexia — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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 milisp · MCP Server · ★ 915

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

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

About codexia

Codexia Codexia is a Tauri v2 app for Codex CLI + Claude Code — combining agent workflows, an IDE-like editor, a headless web server, and a prompt notepad in one workspace. Features Agent workflows: Task Scheduler for recurring jobs, remote control via headless web server Workspace: Git worktree management, project file tree, IDE-like editor, prompt notepad, local web preview Data tools: One-click PDF / XLSX / CSV preview Ecosystem: MCP server marketplace, agent skills marketplace Personalization: Theme and accent customization, usage analytics dashboard Requirements Codex CLI Claude Code CLI Installation Homebrew (macOS) Prebuilt releases (macOS / Linux / Windows) GitHub Releases Modern GitHub Release Mirror Quick Start Launch Codex

agentic-aiaiai-agentsawesomechatgptclaude-codecodexcodex-clicodex-desktopcodex-gui

Quick Facts

Stars915
Forks101
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score72.1093603030113/100
Open Issues12
Last Updated2026-09-12
Created2025-08-13
Platformsclaude-code, cli, codex, mcp, node
Est. Tokens~15k

Compatible Skills

These tools work well together with codexia for enhanced workflows:

  • recall — semantic(0.58)+complementary+rare_topics+similar_pop+shared_platform (64%)
  • CodexFlow — semantic(0.57)+complementary+rare_topics+same_lang+shared_platform (64%)
  • crystal — semantic(0.34)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • hapi — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (61%)
  • code-notify — semantic(0.45)+complementary+rare_topics+similar_pop+shared_platform (60%)

codexia alternative? Top 6 similar tools

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

  • open-responses-server by teabranch · ⭐ 184

    Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing statefu

  • octopus by bestruirui · ⭐ 2.6k

    One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关

  • ChatMock by RayBytes · ⭐ 1.5k

    OpenAI & Ollama compatible API powered by Codex

  • Mysti by DeepMyst · ⭐ 1.1k

    AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate

  • archestra by archestra-ai · ⭐ 4.3k

    Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

  • crystal by stravu · ⭐ 3.1k

    (Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, com

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is codexia?

codexia is Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control. It is categorized as a MCP Server with 915 GitHub stars.

What programming language is codexia written in?

codexia is primarily written in TypeScript. It covers topics such as agentic-ai, ai, ai-agents.

How do I install or use codexia?

You can find installation instructions and usage details in the codexia GitHub repository at github.com/milisp/codexia. The project has 915 stars and 101 forks, indicating an active community.

What license does codexia use?

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

What are the best alternatives to codexia?

The top alternatives to codexia on Agent Skills Hub include open-responses-server, octopus, ChatMock. 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 MCP Server tools