claudexor — 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 razzant · MCP Server · ★ 479

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

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

About claudexor

Claudexor Claudexor is a local-first control plane for the AI coding agents you already pay for. It runs Codex CLI, Claude Code, Cursor CLI, OpenCode, and raw API adapters behind one typed interface: a chat of turns where read-only questions resume the vendor's own native session, write turns land as inspectable patches, races pit harnesses against each other with cross-family review, and every claim — cost, quota, web evidence, auth route — is a typed fact you can audit, never a vibe. Compared to driving a bare Codex or Claude Code session, Claudexor adds the layer the vendors do not ship: best-of-N races with independent reviewers and arbitration; honest budget/quota accounting (unknown cost is never ); deterministic gates and protected paths; and — since

agent-orchestrationai-agentsai-codingai-coding-assistantclaude-codeclicode-reviewcodexcodex-clicoding-agent

Quick Facts

Stars479
Forks48
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score67.5972542370805/100
Open Issues78
Last Updated2026-09-22
Created2026-06-05
Platformsclaude-code, cli, codex, mcp, node
Est. Tokens~23k

claudexor alternative? Top 6 similar tools

Looking for a claudexor alternative? If you're comparing claudexor 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.

  • ai-devkit by codeaholicguy · ⭐ 1.6k

    The control plane for AI coding agents.

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

  • roam-code by Cranot · ⭐ 518

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

  • hcom by aannoo · ⭐ 490

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • multi-cli by Spielewoy · ⭐ 243

    Run multiple AI coding accounts at the same time.

  • forge-orchestrator by nxtg-ai · ⭐ 135

    Forge Orchestrator: Multi-AI task orchestration. File locking, knowledge capture, drift detection. Rust.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is claudexor?

claudexor is Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.. It is categorized as a MCP Server with 479 GitHub stars.

What programming language is claudexor written in?

claudexor is primarily written in TypeScript. It covers topics such as agent-orchestration, ai-agents, ai-coding.

How do I install or use claudexor?

You can find installation instructions and usage details in the claudexor GitHub repository at github.com/razzant/claudexor. The project has 479 stars and 48 forks, indicating an active community.

What license does claudexor use?

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

What are the best alternatives to claudexor?

The top alternatives to claudexor on Agent Skills Hub include ai-devkit, quint-code, roam-code. 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