This comprehensive system optimizes AI agent performance, offering production-ready agents, skills, hooks, and MCP configurations. It's ideal for building robust, continuously learning AI agents across various platforms like Claude Code, Codex, and Gemini, ensuring high-performance, secure, and scalable AI solutions.

prompts.chat is the world's largest open-source library offering a curated collection of prompt examples for various AI chat models like ChatGPT, Claude, and Gemini. It's ideal for developers and users looking to discover, utilize, and improve AI prompts for diverse applications, from coding to creative writing.

Claude-Mem provides a persistent memory system for Claude Code, automatically capturing tool usage, summarizing observations, and injecting relevant context into future sessions. This allows AI agents to maintain continuous knowledge of projects and past decisions across multiple interactions, significantly enhancing long-term project engagement.

Mem0 provides an intelligent memory layer for AI assistants and agents, allowing them to remember user preferences and adapt over time. It's ideal for building personalized AI applications like customer support chatbots or autonomous systems that require consistent, context-rich conversations.

Context7 integrates current, version-specific documentation and code examples directly into your LLM's context, eliminating outdated information and hallucinations. It's ideal for developers needing precise, up-to-date API details, configuration, or code snippets for any library or framework.

MemPalace provides a local-first AI memory system that stores verbatim conversation history and project files, enabling highly accurate semantic retrieval without external API calls. It's ideal for developers and AI agents needing a private, structured, and high-performance knowledge base for their work within the Claude Code ecosystem.

Ruflo is a multi-agent AI orchestration framework for Claude Code, designed to coordinate over 100 specialized AI agents across various environments. It provides capabilities like self-organizing swarms, self-learning memory, federated communication, and enterprise-grade security, enabling agents to collaborate effectively rather than just execute tasks in isolation. This makes it ideal for complex, distributed AI-assisted development workflows.

Payload is an open-source, Next.js native headless CMS and app framework designed for modern web development, allowing direct installation into your existing /app folder. It offers a fully extensible admin panel, robust APIs, and integrates with Claude Code via a dedicated plugin to streamline development workflows. It's ideal for developers building high-performance websites, e-commerce stores, or blogs who need a flexible, self-hosted content solution.

This MCP server empowers AI coding agents to fully control and inspect a live Chrome browser, offering robust capabilities for in-depth debugging, performance analysis, and reliable web automation. It's ideal for agents needing direct browser interaction to diagnose issues, gather performance metrics, or automate complex user flows.

GitNexus transforms any codebase into a detailed knowledge graph, mapping dependencies, call chains, and execution flows. This provides AI agents with deep architectural awareness, significantly improving their reliability for complex development tasks. It is particularly effective for developers using AI assistants to navigate, debug, and refactor large codebases with precision.

This tool provides multi-agent orchestration for Claude Code, enabling complex AI-assisted development workflows with a focus on ease of use. It allows users to leverage Claude, Codex, and Gemini agents for tasks like code review, UI/UX design, and iterative improvement, streamlining the entire development process.

This MCP server enables LLMs to interact with web pages using Playwright's structured accessibility snapshots, eliminating the need for visual models or screenshots. It is ideal for specialized agentic loops requiring persistent state, rich introspection, and iterative reasoning over page structure, such as exploratory automation or self-healing tests.

The GitHub MCP Server enables AI agents, assistants, and chatbots to interact directly with GitHub's platform. It's ideal for automating development workflows, managing codebases, and streamlining team collaboration through natural language commands.

Taskmaster is an AI-driven task management system designed for seamless integration with various AI chats and IDEs like Claude Code and Cursor AI. It helps developers organize, track, and automate development tasks, supporting complex workflows with dependencies, subtasks, and automated research.

SuperClaude is a meta-programming framework that structures Claude Code into a comprehensive development platform, offering systematic workflow automation through 30 slash commands and intelligent agents. It excels at guiding developers through the entire lifecycle, from brainstorming and research to implementation and testing, especially when seeking enhanced performance via optional MCP integrations.

Promptfoo is a CLI and library designed for evaluating and red-teaming LLM applications, enabling developers to ship secure and reliable AI apps. It excels at automating prompt and model testing, comparing different LLMs, and integrating security vulnerability scanning into CI/CD pipelines.

This plugin provides a suite of AI skills and agents designed to make each unit of engineering work easier than the last, fostering a 'compound engineering' approach. It excels at guiding developers through planning, execution, review, and knowledge codification, reducing technical debt and improving long-term productivity.

Cua is a comprehensive platform enabling AI agents to interact with computers through background macOS automation, cross-OS sandboxes, and robust benchmarking tools. It excels when developers need to build, evaluate, and deploy agents capable of visually interacting with GUIs, clicking, typing, and performing complex tasks across diverse operating systems.

This repository provides a vast collection of 235 production-ready skills and agent plugins, offering domain expertise across engineering, marketing, product, and C-level advisory. It's ideal for developers and teams seeking to augment their AI coding agents with specialized knowledge and workflows for diverse tasks.

Hindsight is an advanced agent memory system designed to enable AI agents to learn and evolve beyond simple conversation recall. It excels in long-term memory tasks, providing state-of-the-art performance for building smarter, more adaptive AI employees and conversational agents.

Kubeshark indexes cluster-wide network traffic at the kernel level using eBPF, offering instant answers to queries with network, API, and Kubernetes semantics. It's invaluable for SREs and AI agents requiring deep network visibility, incident response, and root cause analysis in Kubernetes environments.

This repository offers a comprehensive suite of AI agents, skills, and data connectors tailored for financial services, covering workflows in investment banking, equity research, private equity, and wealth management. It's ideal for firms looking to automate analyst work products like models, memos, and reconciliations, ensuring human review for all outputs.

Superset is a desktop application that orchestrates CLI-based coding agents across isolated git worktrees, enabling parallel execution and efficient task management. It's ideal for developers who need to run multiple AI agents simultaneously without context switching, providing a unified interface for monitoring, reviewing, and editing agent-generated changes.

This repository provides a collection of standardized Agent Skills for AI/ML tasks, including model training, evaluation, and dataset management on the Hugging Face Hub. It is designed for developers using coding agents like Claude Code, Codex, or Gemini CLI to streamline complex machine learning workflows.

mcp-use is a fullstack framework designed for building robust Model Context Protocol (MCP) Servers and interactive MCP Apps for AI agents like Claude and ChatGPT. It excels when developers need to create production-ready AI tools with custom UIs, offering SDKs, a debugging inspector, and cloud deployment options.

This skill enables AI agents to interact directly with Amazon Aurora DSQL, a serverless, PostgreSQL-compatible distributed SQL database. It's ideal for developers needing AI assistance with schema management, query execution, database migrations, and diagnosing query plans within their AWS cloud-native development workflows.

This MCP server integrates with Firecrawl to enable AI agents to search the web, scrape structured data from any URL, and interact with web pages. It is ideal for providing real-time, dynamic web context to LLMs, facilitating deep research and autonomous agent operations.

Desktop Commander is an MCP server that extends AI agents' capabilities to control the local desktop, enabling them to manage files, execute terminal commands, and oversee processes. It excels in complex development workflows, data analysis, and document automation by offering persistent shell sessions, long-running background tasks, and native support for structured files like Excel, PDF, and DOCX.

This Model Context Protocol server provides robust browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, and generate test code. It is ideal for AI agents needing to perform web scraping, UI testing, or execute JavaScript in a real browser environment.

This is a comprehensive marketplace offering a wide array of Claude Code skills from Trail of Bits, specifically designed to enhance AI-assisted security analysis, testing, and development workflows. It is ideal for developers and security professionals seeking specialized tools for tasks like smart contract auditing, code review, and vulnerability detection.