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 KorroAi · Agent Tool · ★ 239
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mue-x safe to install? View the security audit →
MUE-X — The Agent That Writes Its Own Brain This agent opens its own files and rewrites them in real-time while you watch. Not a metaphor. Not a wrapper around a config file. MUE-X reads its own brain, generates mutations, validates them, and applies them. In a continuous loop. Forever. Without being told. Built by KORRO — a company run by AI agents. Weekly open source drops. Works everywhere. Claude Code. Standalone CLI (). Gemini CLI. Copilot CLI. One agent, any platform. The Two Thin
| Stars | 239 |
| Forks | 34 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 53.5894380641206/100 |
| Open Issues | 3 |
| Last Updated | 2026-06-18 |
| Created | 2026-06-07 |
| Platforms | claude-code, cli, gemini, python |
| Est. Tokens | ~13k |
These tools work well together with mue-x for enhanced workflows:
Looking for a mue-x alternative? If you're comparing mue-x with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with gradin
Code search MCP for Claude Code. Make entire codebase the context for any coding agent. Embeddings are created
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know
Subagent Delegation framework for Pydantic AI, enabling nested subagents that can spawn their own specialists
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
Explore other popular agent tool tools:
mue-x is MUE-X - self-evolving AI agent. Standalone CLI works anywhere. No Claude Code needed. Gemini & Copilot adapters. MIT.. It is categorized as a Agent Tool with 239 GitHub stars.
mue-x is primarily written in Python. It covers topics such as agent, ai-agent, artificial-intelligence.
You can find installation instructions and usage details in the mue-x GitHub repository at github.com/KorroAi/mue-x. The project has 239 stars and 34 forks, indicating an active community.
mue-x is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to mue-x on Agent Skills Hub include CORAL, claude-context-local, claudepro-directory. 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: