342 boosters for "agents" — open source, verified from GitHub, ready to install
A multi-agent CrewAI system for Facebook advertising campaign management that enforces comprehensive code standards, testing requirements, and documentation practices. Teams managing ad campaigns at scale benefit from structured agent-based optimization and consistent code organization.
Markdown Agents is a framework for defining AI agents using simple markdown files with YAML frontmatter, enabling version-controlled, portable agent configuration across Claude Code and Desktop. Developers benefit from reduced cognitive load, git-native memory tracking, and predictive AI collaboration without session amnesia.
"name": "skill-builder", "description": "Create, audit, optimize Claude Code skills. Converts bloated CLAUDE.md files into lean briefing documents plus on-demand skills, enforcement hooks, and validation agents.", "name": "Francis Meetze",
This MCP server enables autonomous AI agents to reason more effectively through a dual-cycle metacognitive framework that combines fast intuitive reasoning with slower deliberative verification. It's designed for developers building sophisticated autonomous agents that need robust self-monitoring, loop detection, and belief revision capabilities.
"name": "agentmind", "description": "Agent Self-Learning Memory System — Make AI Agents understand you better over time", "homepage": "https://github.com/Youhai020616/Agentmind",
"name": "open-academic-paper-machine", "description": "Open Academic Paper Machine — Autonomous academic paper production system with idea evaluation gate and paper-vs-code audit. NEW in v6.4: /audit-paper command and audit-engine skill — static audit of a paper's empirical claims (datasets, models,
A comprehensive set of development guidelines and reusable agents for building AI-powered Python applications in Windsurf using Mirascope, covering patterns for LLM integration, component structure, and best practices. Developers building intelligent agents and tools in Python will benefit from these standardized patterns and pre-built components.
"name": "codealive", "description": "CodeAlive context engine for semantic code search and AI-powered codebase Q&A. Enables AI coding agents to understand entire codebases beyond just open files — search across all indexed repositories, trace cross-service dependencies, discover usage patterns, and
"name": "plan-review", "description": "Multi-perspective plan review with VP Product, VP Engineering, and VP Design for implementation plans and architecture proposals.", "name": "Will Smith",
"name": "cadre-devkit-claude", "description": "Cadre team development kit for Claude Code - security hooks, workflow automation, and productivity tools", "name": "Cadre Team"
"name": "cre-skills", "description": "112 institutional-grade CRE skills covering ~97% of commercial real estate workflow steps. Deal screening, underwriting, structuring, due diligence, capital markets, market research, asset management, leasing, investor relations, development, disposition, sourci
A development guide for extending PatientHub with new patient simulation agents, enabling researchers and developers to implement custom behavioral models for healthcare simulations.
  <!-- upstream-badges-start -->
"name": "signalwire-builder", "description": "Expert knowledge for building SignalWire applications including all SDKs, REST APIs, SWML, Relay/Fabric, AI Agents, and modern JSON/YAML-based communication systems", "name": "SignalWire",
"description": "Intellectual property data tools - async Python clients for USPTO, EPO, Google Patents, and JPO for AI agents", "name": "Parker Hancock", "url": "https://github.com/parkerhancock"
"name": "sui-dev-agents", "description": "Complete SUI blockchain development toolkit with skills, agents, commands, hooks, and rules for Move smart contracts, frontend integration, testing, and deployment", "name": "Ramon Liao",
"name": "openclaw-skill", "description": "Complete OpenClaw documentation as a skill — 333 pages of verbatim official docs for gateway config, channels, providers, tools, CLI, and deployment", "name": "Brabaflow — AI-Native Agency",
Oros cursor rules provide development guidelines for a decentralized AI chat application that bridges LLM capabilities with blockchain tasks through a Go proxy and React frontend. Developers building or contributing to multi-LLM dApp integrations would benefit from these structured rules.
PocketFlow-PHP is a set of Cursor rules that guide AI agents to build modular, agentic PHP applications using a minimalist LLM framework with strict architectural constraints. Developers using Cursor for PHP projects with AI assistance benefit from clear architectural guardrails.
A collection of 28 specialized AI subagents for Claude Code that extend development workflows across backend, frontend, mobile, DevOps, and infrastructure domains. Developers benefit from domain-specific expertise automatically available within their coding environment.
Codeweaver enables AI agents to perform semantic code search across 166+ programming languages with offline capability and hybrid search—ideal for developers building code-aware automation and AI-driven development tools.
Defines standardized conventions for creating, structuring, and managing AI agents across `.claude/agents/` and `.opencode/agent/` directories, ensuring consistency, security, and maintainability in multi-agent projects. Developers working with AI agents in monorepos, enterprise systems, and DevSecOps workflows benefit from clear role definitions and tool permission standards.
"name": "north-starr", "description": "Agentic development workflow for Claude Code — skills, agents, and project context from your codebase", "name": "Selcuk Yucel",
"name": "alphaagent-team", "email": "support@answeragent.ai" "description": "AlphaAgent Team Plugin Marketplace - Claude Code plugins for autonomous coding assistance",
