AI coding rules that actually work. Enforce instruction files via hooks — CLAUDE.md, .cursorrules, copilot-instructions, and more.
Local MCP orchestrator for managing Codex, Claude, and Cursor worker runs through a persistent daemon, with a daemon-owned orchestration_run engine for multi-step workflows.
AI-assisted novel writing workflow for Claude Code, Gemini CLI, OpenCode, and Codex CLI
Claude Code workflow on free LLM providers (opencode-ai + freellmapi shim)
React multi-step forms where logic has no limits - for any use case
Autonomous issue resolver
OpenCode plugin adapter for bg-subagents: registers task_bg, intercepts task, steers via chat.params, delivers completion via Bus + chat.message fallback.
HarmonyOS Full-Lifecycle Development Assistant. Specialized in the complete development lifecycle of HarmonyOS applications, including project creation, UI development, state management, network requests, data storage, permission requests, performance opt
OpenCode plugin to query Z.ai GLM Coding Plan usage statistics including quota limits, model usage, and MCP tool usage
Model Context Protocol (MCP) server for PrimeNg component library
OpenCode plugin for Windsurf/Codeium authentication - use Windsurf models in OpenCode
EZ Agents — Meta-prompting with multi-model support (Qwen, Kimi, OpenAI)
CodeTime plugin for OpenCode - Track AI coding activity and time spent with codetime.dev
<div align="center"> <br> <header> <img src="https://github.com/cubanducko/playwright-i18next-fixture/blob/main/assets/logo.png?raw=true" height="64" /> </header> <br> <h1>playwright-i18next-fixture</h1> <p> 📝 Use your `i18next` translati
Core library for test-copilot
Git-backed persistent memory for OpenCode — stores AI agent memories on a detached branch via git plumbing
Token Usage Analytics Dashboard
Static SQL safety analysis for AI agents — catch dangerous queries before they reach your database.
Nuxt Multi-tenancy module
Feishu/Lark adapter for driving opencode sessions from Event Callback messages.
Core FlowDesk contracts and Release 1 boundaries.
AI-agnostic development workflow framework that automates the full software development lifecycle
An MCP (Model Context Protocol) server for performing a11y test on webpages using playwright axe-core. The results are then used in an agent loop with your favorite AI assistant (Cline/Cursor/GH Copilot) to find problems with a11y and suggest improvements
An OpenClaw plugin that orchestrates coding agent sessions as managed background processes. Launch, monitor, and control coding agents (Claude Code, Codex, experimental OpenCode, and more) directly from your AI gateway.