quemsah/awesome-claude-plugins

Automated index of Claude Code plugins and adoption metrics across GitHub repositories, powered by a Node.js/TypeScript crawler

What it solves

This project provides a curated, indexed directory of over 50,000 repositories that offer plugins, skills, and agentic frameworks for AI coding tools like Claude Code, Cursor, and others. It helps developers discover specialized tools to extend the capabilities of their AI agents.

How it works

The repository maintains a ranked list of top repositories, categorized by their utility in enhancing AI agent performance. These plugins range from memory management and token optimization systems to specialized skills for tasks like cybersecurity, SEO, design, and project management.

Who it’s for

It is designed for developers and engineers who use AI coding agents and want to discover community-vetted tools to improve their agent's efficiency, memory, and specialized skill sets.

Highlights

  • Indexed list of over 50,000 repositories.
  • Includes specialized skills for engineering, marketing, research, and cybersecurity.
  • Features tools for token optimization and memory persistence across agent sessions.
  • Supports a wide range of agentic platforms including Claude Code, Codex, and Cursor.

Related

  • Project
    HexRaysSA/ida-mcp

    An official MCP server from Hex-Rays that connects AI agents to the IDA disassembler, letting them reverse engineer binaries and interact with IDA databases programmatically.

  • Project
    awslabs/cli-agent-orchestrator

    CLI Agent Orchestrator (CAO) is a Python tool that lets you run several AI‑coding command‑line interfaces (like Claude Code, Copilot CLI, etc.) as coordinated agents. It starts a local server, launches each provider CLI in its own tmux pane, and offers a web UI, API, and plugin system for building parallel or sequential code‑generation pipelines.

  • Project
    appleboy/CodeGPT

    CodeGPT is a Go‑based CLI that uses LLM APIs (OpenAI, Azure, Gemini, Anthropic, Ollama, Groq, OpenRouter, LiteLLM) to auto‑generate Conventional‑Commit messages and short code‑review summaries. It installs a Git `prepare‑commit‑msg` hook, supports many providers, proxy settings, language translation, streaming output, and a flexible prompt/template system. Install via Homebrew, Chocolatey, an install script, pre‑compiled binary, or `go install`. Configure API keys (or dynamic helpers), choose models, and customize prompts. Ideal for developers who want AI‑assisted commit messages and quick reviews directly from the terminal.

  • Project
    umputun/ralphex

    ralphex is a standalone CLI tool that autonomously executes implementation plans using Claude Code or codex. It runs tasks in fresh agent sessions, performs multi-phase code reviews, and handles commits and branching, so you can write a plan and walk away while the feature is implemented, reviewed, and committed.