PaiSwitch

by itwanger · Codex Skill · ★ 24

About PaiSwitch

PaiSwitch 面向 AI Coding Agent 的模型控制台。 PaiSwitch 不只是一个“改配置文件”的小工具,而是一套本地优先的 Agent Model Control Plane。它把 Claude Code、Codex 等 Agent 的底层模型选择、API Key 管理、协议适配、配置备份、自然语言切换和 Skills 管理收拢到同一个工作台里,让开发者可以在官方模型、国产大模型、多模型网关和自定义供应商之间稳定切换。 当前已支持 Claude Code 与 Codex 两条链路,覆盖 DeepSeek V4、智谱 GLM-5/GLM-5.1、Kimi、Qwen、OpenRouter、SkyClaw、讯飞星辰 MaaS 等模型或网关,并保留 OpenAI / Anthropic 官方登录路径。 核心价值 架构图 切换链路 支持矩阵 Agent 目标 | C

aianthropicclaude-codecodexcoding-agentdeepseekdeveloper-toolsllmllm-proxymacos

Quick Facts

Stars24
Forks8
LanguageJava
CategoryCodex Skill
Quality Score64.5190617863818/100
Open Issues2
Last Updated2026-06-09
Created2026-02-12
Platformsclaude-code, codex, java
Est. Tokens~78k

Compatible Skills

These tools work well together with PaiSwitch for enhanced workflows:

  • mcp-zap-server — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • api2mcp4j — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • tianji-ai-agent — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • spring-ai — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • maven-tools-mcp — semantic(0.16)+complementary+rare_topics+same_lang+similar_pop+shared_platform (55%)

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Java Agent Tools

Frequently Asked Questions

What is PaiSwitch?

PaiSwitch is 🔀 AI Coding Agent 模型切换器:为 Claude Code / Codex 一键切换 DeepSeek、Qwen、Kimi、OpenRouter 等模型,内置本地 LLM 代理、API Key 管理和 macOS 桌面版。. It is categorized as a Codex Skill with 24 GitHub stars.

What programming language is PaiSwitch written in?

PaiSwitch is primarily written in Java. It covers topics such as ai, anthropic, claude-code.

How do I install or use PaiSwitch?

You can find installation instructions and usage details in the PaiSwitch GitHub repository at github.com/itwanger/PaiSwitch. The project has 24 stars and 8 forks, indicating an active community.

View on GitHub → Browse Codex Skill tools