# CC Switch — Desktop Hub for AI Coding CLIs

> CC Switch is a desktop hub for Claude Code, Codex, Gemini CLI, and more. Install via Homebrew cask; switch providers and sync MCP, prompts, and skills.

## Install

Copy the content below into your project:

## Quick Use

1. Install the verified entrypoint:

```bash
brew tap farion1231/ccswitch && brew install --cask cc-switch
```

2. Run a first local check:

```bash
Open CC Switch and add a Provider preset, then click Enable
```

3. Add a repeatable verification step:

```bash
brew upgrade --cask cc-switch
```

---

## Intro

CC Switch is a verified GitHub-backed asset sourced from `farion1231/cc-switch` with 67,100 stars and a MIT license snapshot. Best for: developers juggling multiple AI coding CLIs who want safe switching, shared skills, and usage tracking in one place. Works with: macOS (Homebrew cask), Windows/Linux (release installers); integrates with multiple AI coding CLIs. Setup time: 10 minutes.

### Quantitative notes

- Setup time ~10 minutes
- Supports multiple CLIs (Claude Code/Codex/Gemini CLI, per repo)

---

## Deep Dive

### What it solves

Use this when you need a **repeatable, team-shareable workflow** instead of one-off agent prompts. The goal is to make installation, first-run validation, and rollback **predictable**.

### Minimal mental model

- Treat the GitHub repo as the source of truth: install instructions, configs, and upgrade paths live there.
- Keep your first run small: one command, one verification, one rollback plan.
- Capture a baseline: setup time, first successful run, and one real task completed end-to-end.

### Safe rollout checklist

1. **Verify source**: confirm repo URL, stars, and license match what you expect.
2. **Install** using the Quick Use commands above.
3. **Prove it works** with the verification command; save the output in a note or issue.
4. **Operationalize**: document owner, upgrade command, and rollback command.

### Troubleshooting (common)

- **Install succeeds but nothing shows up**
  - Likely cause: the tool needs a restart/reload (CLI/IDE) or a config file in the right path.
  - Fix: restart the client, then re-run the verification step.

- **Works on one machine, fails on another**
  - Likely cause: Node/Python/Docker versions differ or missing system dependencies.
  - Fix: pin versions (Node/Python), and copy a minimal known-good config.

- **Token cost or latency is worse than expected**
  - Likely cause: tool schemas or verbose outputs get injected into context.
  - Fix: prefer smaller steps, cache results, and keep tool responses concise when possible.


---

### FAQ

**Q: Will uninstall break my CLI tools?**
A: The repo describes a minimal-intrusion approach; keep one known-good official config preset as your rollback path.

**Q: How do I keep MCP/skills consistent across tools?**
A: Use CC Switch's sync features to manage MCP/Prompts/Skills per app, then restart the affected tool if required.

**Q: What is the safest rollout?**
A: Start with one machine, export the preset config, then standardize on a small set of providers and skills.

---

## Source & Thanks

> GitHub: https://github.com/farion1231/cc-switch
> Owner avatar: https://avatars.githubusercontent.com/u/44939412?v=4
> License (SPDX): MIT
> Stars (verified via `api.github.com/repos/farion1231/cc-switch`): 67,100


---

<!-- ZH -->

# CC Switch——AI 编程 CLI 的桌面控制台

> CC Switch 是 Claude Code、Codex、Gemini CLI 等工具的桌面控制台：一键切换 Provider，按应用同步 MCP/Prompts/Skills，并提供用量/成本面板。macOS 可用 Homebrew cask 安装。

## 快速使用

1. 安装（以仓库为准）：

```bash
brew tap farion1231/ccswitch && brew install --cask cc-switch
```

2. 首次运行/检查：

```bash
Open CC Switch and add a Provider preset, then click Enable
```

3. 可重复验证：

```bash
brew upgrade --cask cc-switch
```

---

## 简介

CC Switch 已核验来源于 `farion1231/cc-switch`（67,100 stars，许可证 MIT）。适合：同时用多种 AI 编程 CLI、希望安全切换、统一管理技能与查看用量的开发者。兼容：macOS（Homebrew cask）、Windows/Linux（Release 安装包）；可与多种 AI 编程 CLI 集成。装机时间：10 分钟。

### 量化信息

- 装机约 10 分钟
- 支持多种 CLI（Claude Code/Codex/Gemini CLI 等，见仓库说明）

---

## 深度说明

### 解决什么问题

把“找到项目 → 安装 → 首次验证 → 回滚/升级”变成可复用流程，避免只靠一次性提示词或截图操作。

### 最小心智模型

- GitHub 仓库是事实来源：安装、配置、升级、已知问题都以它为准。
- 第一次只做最小闭环：一个命令安装、一个命令验证、一个可回滚方案。
- 记录基线：装机耗时、首次成功输出、完成 1 个真实任务的证据。

### 安全推广清单

1. **核验来源**：确认仓库 URL / stars / license 与预期一致。
2. 按“快速使用”完成安装与首次检查。
3. 跑通“验证命令”，把输出留档。
4. 标注 owner，并写清升级/回滚步骤。

### 常见排障

- **装了但看不到效果**
  - 常见原因：需要重启 CLI/IDE 或配置文件路径不对。
  - 处理：重启后再跑一遍“验证命令”。

- **一台机器能跑，另一台不行**
  - 常见原因：Node/Python/Docker 版本差异或缺少系统依赖。
  - 处理：固定版本，并拷贝最小可用配置。

- **token 成本/延迟超预期**
  - 常见原因：工具 schema 或输出过长被塞进上下文。
  - 处理：拆小步骤、缓存结果、尽量让工具输出更短。


---

### FAQ

**Q: 卸载会把 CLI 搞坏吗？**
A: 仓库强调 minimal intrusion；建议保留一个“官方登录”预设，作为随时回滚的兜底。

**Q: 怎么保证各工具的 MCP/技能一致？**
A: 用 CC Switch 的同步功能按应用管理 MCP/Prompts/Skills，必要时重启对应 CLI 让配置生效。

**Q: 最安全的推广方式？**
A: 先单机试跑并导出预设配置，再把可控的 provider/技能集收敛成团队标准。

---

## 来源与感谢

> GitHub：https://github.com/farion1231/cc-switch
> Owner avatar：https://avatars.githubusercontent.com/u/44939412?v=4
> 许可证（SPDX）：MIT
> GitHub stars（已通过 `api.github.com/repos/farion1231/cc-switch` 核验）：67,100


---
Source: https://tokrepo.com/en/workflows/cc-switch-desktop-hub-for-ai-coding-clis
Author: Script Depot