ccswitchmulti — security grade SAFE, quality 56/100

Security audit verdict: SAFE · quality 56/100

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 BigStrongSun · Codex Skill · ★ 107

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

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

About ccswitchmulti

CCSwitchMulti 面向八类 Agent 工具的 Provider 管理与 Codex 多模型路由工具 English Changelog 求助和反馈:可以提交 GitHub Issue,也可以扫码加入小红书讨论群一起讨论。(二维码有效期至 2026-07-20) CCSwitchMulti 分支说明 CCSwitchMulti 是面向 Codex 多模型工作流维护的桌面工具。它提供 Provider 数据库、本地代理、MCP/Skills 同步、会话管理、云同步和 Tauri 跨平台结构,同时加入 Codex MultiRouter 工作流,让多个模型来源可以合并到同一个 Codex Provider 后面使用。 使用 发布版本时,请先阅读本节,因为这里记录的是 CCSwitchMulti 的核心能力、实现边界和使用注意事项。 Codex 多路由配置说明书 如果你是第一次配置 Codex MultiRouter,请先看这份中文说明书: CCSwitchMulti Codex 多路由使用说明 它按实际操作顺序覆盖 Codex Desktop 登录、CCSwitchMulti OAuth 授权、添加 DeepSeek / GLM / 本地模型源、开启 、获取模型列表、配置上下文窗口、创建多模型路由、设置子 Agent 前 5 个候选

ai-toolsccswitchmulticodexcodex-multirouterdeepseekdesktop-applocal-llmlocal-proxymulti-model-routeropenai

Quick Facts

Stars107
Forks10
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score56.2463047202207/100
Open Issues38
Last Updated2026-09-23
Created2026-08-09
Platformscodex, rust
Est. Tokens~24k

Compatible Skills

These tools work well together with ccswitchmulti for enhanced workflows:

  • token_proxy — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • bitrouter — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)

ccswitchmulti alternative? Top 6 similar tools

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

  • llmio by atopos31 · ⭐ 316

    Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关,提供权重负载均衡、可观测性与费用追踪

  • token_proxy by mxyhi · ⭐ 93

    Local AI API gateway for OpenAI / Gemini / Anthropic. Runs on your machine, keeps tokens counted (SQLite), off

  • gemini-cli-desktop by Piebald-AI · ⭐ 502

    Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversati

  • codexmate by SakuraByteCore · ⭐ 351

    One dashboard for all your local AI coding agents. Switch providers, manage sessions, and orchestrate tasks ac

  • lovcode by MarkShawn2020 · ⭐ 303

    A desktop companion app for AI coding tools. Browse Claude Code chat history, manage configurations, commands,

  • palot by ItsWendell · ⭐ 187

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

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is ccswitchmulti?

ccswitchmulti is CCswitch的全面升级,专门优化codex体验。支持官方订阅和第三方模型混用,自动路由,支持v2subagent使用第三方模型. It is categorized as a Codex Skill with 107 GitHub stars.

What programming language is ccswitchmulti written in?

ccswitchmulti is primarily written in Rust. It covers topics such as ai-tools, ccswitchmulti, codex.

How do I install or use ccswitchmulti?

You can find installation instructions and usage details in the ccswitchmulti GitHub repository at github.com/BigStrongSun/ccswitchmulti. The project has 107 stars and 10 forks, indicating an active community.

What license does ccswitchmulti use?

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

What are the best alternatives to ccswitchmulti?

The top alternatives to ccswitchmulti on Agent Skills Hub include llmio, token_proxy, gemini-cli-desktop. 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