1,359 boosters for "AI" — open source, verified from GitHub, ready to install
agent-builder enables developers to create production-ready AI agents with pai-agent-sdk and Pydantic AI, including tools configuration, session persistence, and hierarchical agent setups. Ideal for building autonomous applications, chatbots, and HITL workflows.
"name": "ai-driven-engineering", "description": "AI-Driven Engineering workflow commands for managing issues, tasks, implementation, and PRs.", "name": "Sascha Heyer"
Deep Research is a 7-phase structured research protocol that helps users conduct comprehensive, multi-source investigations with verified citations and source triangulation. It benefits researchers, analysts, and anyone needing thorough, auditable research outputs.
Heuristic scoring (no AI key configured).
"name": "enterprise-team", "displayName": "Enterprise Team - Hire a Whole Company", "description": "Complete virtual company with 76 specialized AI agents across Engineering, Product, Infrastructure, Data, Security, Marketing, Sales, Finance, Legal, and People. Pipeline modes (Full/Sprint/Micro), De
"name": "damusix-ai-tools", "name": "Danilo Alonso" "description": "Local plugins by Danilo Alonso"
"name": "nuanced-dev", "description": "Nuanced LSP plugin for Claude Code", "homepage": "https://github.com/nuanced-dev/lsp",
Agent Tower Plugin orchestrates multiple AI coding assistants (Claude, Codex, Gemini) to deliberate on coding tasks through council, debate, and consensus workflows. Developers benefit from diverse AI perspectives and structured decision-making for complex coding challenges.
"name": "desplega.ai", "description": "desplega.ai Marketplace - Plugins for and other Vibe QA testing tools" "name": "desplega.ai",
An AI-First DevOps toolkit for Cursor that establishes structured workflows, memory management, and mode-based task execution to enable intelligent automation across the development lifecycle. DevOps engineers and AI-assisted developers benefit from systematic prompt-based automation and decision tracking.
"name": "@tekmidian/pai", "displayName": "PAI Knowledge OS", "description": "Personal AI Infrastructure — persistent memory, session continuity, and knowledge graph for Claude Code",
A debugging specialist agent that performs root cause analysis for errors, test failures, and unexpected behavior by capturing context, isolating issues, and implementing minimal fixes. Developers benefit from proactive debugging assistance that goes beyond symptom treatment to address underlying problems.
A Cursor IDE rule set that enforces markdown linting standards to keep documentation consistent and error-free. Useful for teams maintaining specs, READMEs, and other markdown-based project documentation.
"name": "greedysearch", "description": "Multi-engine AI web search — Perplexity, Bing Copilot, and Google AI in parallel with Gemini synthesis. No API keys needed.", "name": "Apostolos Mantzaris",
"version": "5.10.0", "description": "Memory → Evaluation → Credential → Access Control for AI agents. Persistent memory with W3C Verifiable Credentials, capability-based access control, drift detection, and FSRS-6 spaced repetition.", "name": "kobie3717",
"description": "Dual-scope knowledge base for LLM workflows with hybrid full-text + semantic search, typed relations, and publishing.",
VS Code extension that enables AI assistants like Claude to interact directly with your development environment through the Model Context Protocol. Developers using Claude Code or Claude Desktop gain seamless IDE integration for coding assistance and debugging.
"version": "1.13.0", "description": "Structured agentic development methodology - from issue analysis to merge", "name": "Kevin Ryan"
"name": "magi-researchers", "version": "0.17.0", "description": "Three AI models, one synthesis \u2014 multi-model research workflow for scientific domains",
GPRPy enables Claude to process and visualize ground-penetrating radar data through signal processing, velocity analysis, and depth conversion—essential for geophysicists, archaeologists, and civil engineers analyzing subsurface structures.
"name": "agent-lint", "description": "Check how well your repo supports AI coding agents.", "homepage": "https://github.com/0xmariowu/agent-lint",
Opendidac Cursor Rules is a specialized prompt that transforms Cursor into a senior fullstack developer assistant optimized for building an educational platform with diverse question types, code execution environments, and real-time evaluation tracking. It benefits educators and developers building sophisticated assessment and training systems.
Official MCP client for Buildable, an AI-powered development platform that integrates with Cursor and Claude to streamline project planning and automation. Developers using Claude-based IDEs can leverage this to manage and build projects more efficiently.
A system prompt for autonomous AI agents operating within local development environments using MCP servers, designed for developers building sovereign, locally-controlled AI systems with governance protocols.
