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 Mng-dev-ai · MCP Server · ★ 224
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claudex safe to install? View the security audit →
Agentrove Self-hosted AI coding workspace for running Claude Code, Codex, Copilot, Cursor, and OpenCode agents from one interface. Agentrove is under active development. Expect breaking changes between releases. What It Does Runs Claude, Codex, Copilot, Cursor, and OpenCode through ACP adapters. Gives each workspace its own Docker or host sandbox. Combines chat, code editor, terminal, file tree, diffs, secrets, and git tools in one workspace. Supports workspaces from empty folders, git clones, existing local folders, or GitHub repositories. Streams agent sessions with cancellation, permission prompts, queued follow-up messages, file mentions, slash commands, and attachments. Includes sub-threads, pinned chats, worktree mode, personas, custom instructions, environment variables, and installed agent skills. Provides GitHub-assisted repository browsing, pull request review, PR creation, reviewer selection, and git branch/commit/push/pull helpers. Ships as a Docker web app and a macOS desktop app. Quick Start R
| Stars | 224 |
| Forks | 44 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66.7936998287831/100 |
| Open Issues | 10 |
| Last Updated | 2026-03-07 |
| Created | 2025-12-15 |
| Platforms | browser, claude-code, mcp, node |
| Est. Tokens | ~298k |
Looking for a claudex alternative? If you're comparing claudex 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.
Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructur
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool call
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center
Comprehensive UI/UX and Backend component design skills for AI-assisted development with Claude
Explore other popular mcp server tools:
claudex is Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, GitHub Copilot, OpenRouter), custom skills, and MCP servers.. It is categorized as a MCP Server with 224 GitHub stars.
claudex is primarily written in TypeScript. It covers topics such as agent, anthropic, claude.
You can find installation instructions and usage details in the claudex GitHub repository at github.com/Mng-dev-ai/claudex. The project has 224 stars and 44 forks, indicating an active community.
claudex is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to claudex on Agent Skills Hub include sandstorm, orchestkit, zapcode. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: