CRS-自建Claude Code镜像，一站式开源中转服务，让 Claude、OpenAI、Gemini、Droid 订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

Platform for agentic - vibecoders who use claude code and codex cli

ccapi - A management tool for quickly switching Claude Code and Codex configurations | 一个Claude Code 和 Codex 配置管理工具，一键切换多个中转站API配置；一键切换系统环境变量；一键测试API延迟；一键测试API有效性；自动择优线路切换与国际化支持。

☠️ 一键为 Claude Code / Codex CLI 注入邪修人格与 40+ 安全工程秘典 | npx code-abyss

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

Telegram bridge for Claude Code and Codex CLI

Local-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.

A professional browser-based AI-powered development environment that integrates VS Code (code-server) with multiple AI coding assistants for enhanced productivity.

top-style TUI for monitoring AI coding agent sessions

Discord 経由で Claude Code / Codex CLI をリモート操作できる中継サーバー & スキル

All your projects in one workspace. Run multiple CLI agents in parallel across different repos. Runs on your hardware, accessed through the desktop app or the browser. Bring your own plans.

StitchFlow turns prompts into UI directions, Tailwind-friendly HTML, and screenshots across Codex, Claude Code, OpenClaw, GitHub Copilot, and Gemini CLI.

A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

轻量级 MCP 注解代理 — 拦截 tools/list 响应，将工具注解重写为"安全"值，绕过 Codex 等 AI CLI 的审批弹窗，同时完全透传所有实际操作。

Design superpowers for AI coding agents. 35 skills, 5 layers, 7 framework targets. Ideation, batch generation, design systems, iteration loops, and production conversion via Google Stitch MCP. Claude Code plugin + Codex CLI agent. The design intelligence layer your agent was missing.

Universal Agent Harness - Transform Claude Code & Codex into intelligent, memory-aware development teams. 5-agent system, dual-layer memory, TDD workflow.

Self-hosted QQ bridge for Codex CLI with persistent sessions, progress updates, attachments, diagnostics, and local workspaces.

oh-my-codex (omx) — Orchestration layer for OpenAI Codex CLI. Async Claude Code delegation (no timeouts), structured workflows (autopilot, TDD, code review, planning), persistent state & memory. Like oh-my-zsh but for Codex.

Governance harness for Claude Code & Codex CLI — 30 MCP tools, 30 quality gate hooks, 30 enterprise skills. TDD enforcement, blast-radius debugging, evidence-based verification, fleet orchestration. Vibe prompt in, enterprise quality out.

Hypothesis-driven debug mode for Claude Code, Codex, and other agent platforms. Instead of guessing fixes, the agent generates root cause hypotheses, instruments your code with targeted runtime logs, asks you to reproduce via structured choices, analyzes the evidence, applies a targeted fix, then cleans up all instrumentation automatically.