294 boosters for "agents" — AI-graded, open source, ready to install
Cursor Rules for the Agency Swarm framework that guide AI agents in architecting collaborative multi-agent systems with structured planning, tool development, and testing workflows. Developers building AI agent teams benefit from this systematic approach to agency creation.
A comprehensive guide for integrating tools with Claude agents, covering tool registration, custom development, composition patterns, and optimization. Developers building agent-based applications benefit from clear patterns for extending agent capabilities.
The tq booster teaches AI agents how to use the tq agent-first Git-compatible task queue system for managing, claiming, and resolving tasks in distributed workflows. It's valuable for teams using Claude Code that need structured task management without polluting their main repository.
A multi-agent architecture that organizes AI agents into a hierarchy (Architect, Planner, Executor) to decompose and solve complex problems through structured delegation. Developers building sophisticated AI systems that require task decomposition and specialized agent roles will benefit from this reusable framework.
Rex is a documentation retrieval agent that helps users and other agents quickly find information about project architecture, conventions, and implementation details by searching README.md, CLAUDE.md, and docs/ files.
Kibi is a local-first AI agent CLI tool that integrates with Claude via MCP, providing a terminal-based interface for AI-powered workflows. It benefits developers and power users who want to run AI agents locally with full control over their data and LLM interactions.
Heuristic scoring (no AI key configured).
mcp-orchestrator automates the discovery, deployment, and integration of MCP servers for AI agents, with Docker-first containerization and fallback native deployment options. It's essential for developers building complex agent systems who need reliable infrastructure management.
Open AI Town is a virtual world where AI agents can join via HTTP API to socialize, chat, and interact with other agents. It enables developers to build multi-agent systems with social simulation capabilities.
Shiller is a crypto promotion platform where influencers and AI agents can apply for campaigns and earn money based on social media views. It's designed for content creators looking to monetize their reach across TikTok, Instagram, YouTube, and Twitter.
An MCP server that enables Claude to interact with GitHub repositories, issues, and pull requests through the Octokit API. Developers building AI agents or automation tools that need GitHub integration will find this particularly valuable.
Copilot Instructions that teach AI agents how to correctly start and interact with duck-dag's development environment, preventing common mistakes like sending unnecessary terminal input to running servers.
TnC Helper is a multi-agent AI architecture with 5 specialized GPT-4o agents that inherit from a common BaseAgent class for coordinated task execution. It benefits developers building complex applications requiring distributed AI task handling across multiple domains.
Mcp Impresario enables Claude to execute code remotely on any SSH server, seamlessly extending Claude's capabilities to interact with external infrastructure. This is valuable for developers and AI agents needing to run tasks on remote machines, cloud instances, or local servers.
agentproof is a verification booster that allows AI agents to prove their identity and gain trusted status across agent networks. It's designed for AI agents joining platforms like Moltbook who need to demonstrate legitimacy.
Botcash enables AI agents to communicate privately and mine cryptocurrency on a Zcash-based blockchain without platform censorship. It targets developers building autonomous agents that need decentralized, encrypted messaging infrastructure.
A Cursor rules prompt that directs AI agents to leverage the Hytopia MCP Server for SDK guidance and game development examples, enabling developers to build games with up-to-date Hytopia documentation and best practices.
A Nuxt 4 project orchestrator agent that analyzes complex requirements, creates implementation plans, and coordinates specialized sub-agents for SSR, UI, state management, and performance optimization. Ideal for tech leads and architects managing large-scale Nuxt projects.
A multi-agent red-teaming framework that orchestrates coordinated AI security testing with an arbiter to consolidate findings and maintain an immutable audit trail. Security engineers and AI developers use it to systematically test LLM vulnerabilities with repeatable, deterministic results.
A skill booster that enforces opinionated UI constraints and best practices for building accessible, performant interfaces with AI agents on Claude Code. Developers using terminal-based IDEs (Neovim, tmux) benefit from clear, enforceable standards for component selection, animation, and interaction patterns.
An emergency escalation agent that routes system problems to human operators when any agent encounters errors or uncertainty. Useful for systems requiring human oversight, but highly specialized and environment-dependent.
An intelligent agent selection system that evaluates and ranks AI agents for different SDLC phases, enabling teams to automatically match optimal agents to tasks with confidence scoring and human oversight. Ideal for organizations managing multi-phase software development pipelines with diverse agent capabilities.
An MCP server that integrates Claude with Lu.ma's event management API, enabling AI agents to programmatically create, manage, and query events and guest information. Useful for developers building event automation workflows and AI assistants that need event management capabilities.
Prawn Task Manager is an MCP server that converts natural language into structured development tasks with dependency tracking and iterative refinement, enabling AI agents to reason about and manage complex workflows. It's designed for developers building AI-powered systems that need task decomposition and chain-of-thought capabilities.
