Fabric MCP knowledge server — stdio transport for Claude Code / Cursor / Codex CLI, manages .fabric/ knowledge base + agents.meta.json + event ledger.
Installer for the Chrome Gemini Repair Codex skill.
LLM API proxy with real-time traffic sniffing and visualization
Run Next.js apps on Vite. Drop-in replacement for the next CLI.
DeployGate MCP server: upload mobile apps, manage distribution pages, set up CI/CD, and onboard your team. Supports iOS (IPA) and Android (APK/AAB).
Pi extension that exposes OpenAI's hosted image_generation tool to any model, authenticated via the openai-codex (ChatGPT Plus/Pro) OAuth credential.
Control Codex from anywhere. Even on your phone.
一键安装qx-agw skill到各平台
Install lacy — talk to your terminal
A bridge between QQ Official Bot and Codex Desktop, with media relay, STT, thread management, and incremental reply delivery.
The reasoning canvas for any AI CLI. Works with Claude Code, OpenAI Codex, Google Gemini, and Factory.ai Droid — captures each tool's reasoning as a navigable, forkable tree.
BIQ BLUE MCP Server - BigQuery cost optimization and analytics for AI assistants
Engineering + Product team — 23 agents as Claude Code specialists. Infrastructure, DevOps, backend, security, ML/AI, mobile, UX, analytics, growth, strategy, and more.
Fork of OpenAI Codex for Android Termux. This wrapper installs the matching native package for arm64, armv7, x86_64, or x86 and exposes 'codex' and 'codex-exec'.
Paperclip recall plugin with an isolated holographic SQLite memory store.
Zod schemas and helpers for AI coding assistant hook stdin/stdout and hooks config (Claude Code, Codex, Copilot, Gemini CLI, Cursor).
MCP server for the Air.inc platform
Zero-dependency statusline HUD for OpenAI Codex CLI — model, context, git, tokens, and tool activity at a glance
A Model Context Protocol server for MySQL database operations
CLI wrapper around OpenAI Responses API with GPT-5.5 Pro, GPT-5.5, GPT-5.4, GPT-5.2, GPT-5.1, and GPT-5.1 Codex high reasoning modes.
MCP server for calendar computation. Analyze schedules, find conflicts, free time, and suggest optimizations — powered by @daywatch/cal.
Run an agent prompt repeatedly in a batch loop, tee-ing each run to the console and a per-run log file.
Local-first UI review artifacts for agent-made frontend changes.
Ship quality products with AI-powered E2E acceptance testing that validates your web app like a real user — from Claude Code and Cursor to PR.