Browse the library

This plugin provides plain-language skills for AI agents like Claude Code and Cursor, translating technical output into honest session reports, clear verdicts, and actionable steps for non-engineers.

An MCP server that gives AI coding agents efficient access to up-to-date documentation for APIs, services, and libraries.

This resource provides battle-tested configurations, plugins, and hooks for Claude Code, OpenAI Codex, and Cursor agents.

A ranked list of AI agent harnesses, frameworks, and learning resources, with an MCP server to allow agents to query and recommend harnesses.

Provides a lightweight long-term memory framework for LLM agents, offering structured organization and adaptive retrieval of conversational and action-aware memory.

This is a curated, community-driven list of Model Context Protocol (MCP) servers, tools, frameworks, and clients for AI agents.

This Python framework enables developers to build custom MCP servers and tools with features like authorized tool calling and secure secret management.

This free desktop application unifies the management of AI agent skills, allowing users to write a skill once and sync it across 32 AI coding tools via symlinks.

This CLI tool helps manage and activate AI agent capabilities, including modular skills, expert workflow roles, and slash commands, for various coding assistants.

An AI second brain system with agent skills and scripts for Claude Code that builds and maintains a self-organizing knowledge base in Obsidian.

An MCP server that provides a structured thinking journal with persistent sessions, revisions, and branching for complex reasoning.

A collection of forward deployed engineering skills for AI coding agents to clarify goals, design architecture, build, integrate, and verify solutions.

A token-efficient code research tool for AI agents to search and understand local files and GitHub repositories.

An awesome list and hosted registry of Model Context Protocol (MCP) servers, providing a searchable directory for AI agents and applications to discover and integrate new tools.

Provides an operating layer plugin for Claude Code and OpenAI Codex, adding persistent project memory, intent routing, safety hooks, and parallel agent coordination.

An LLM-based agent communication platform with an MCP server, supporting custom agents, multi-turn dialogues, RAG, multi-layered memory, and human-in-the-loop.

Chinese-language curated list of Claude Code skills, agents and plugins, plus original skills for code review, README writing, API testing, refactoring and profiling.

A code repository indexing MCP server that provides task-relevant context to coding LLMs, improving prompt quality and reducing hallucinations.

Adds high-level decision, research, and personal operator skills to AI coding agents.

An MCP server that enables AI agents to perform headless reverse engineering with IDA Pro, optimized for Apple targets and fast analysis.

projectmem

riponcm

An open-source, local-first MCP server that provides memory and judgment for AI coding agents, recording issues, attempts, and decisions to prevent repeating past failures.

A Ghidra MCP server that provides AI agents with a tool-driven approach for reverse engineering, designed to reduce context rot and improve long-form analysis.

This tool provides a shared, searchable, local-first project memory system for AI coding agents, surviving sessions and agent switches.

A self-hosted memory layer on Cloudflare that shares context across Claude, ChatGPT, and Cursor.