81 boosters for "dex" — open source, verified from GitHub, ready to install
The definitive SEO and Generative Engine Optimization agent. LLM-agnostic — works on any platform that reads . Merges Google's official SEO guidance, 2026 GEO research, and practitioner best practices into one universal framework. Every finding comes with a
"description": "Zeabur CLI skills for deployment, template management, and troubleshooting", "version": "1.16.1", "repository": "https://github.com/zeabur/zeabur-claude-plugin",
An autonomous coding agent that delegates tasks to Codex CLI with configurable risk modes (full-auto, sandbox, YOLO) to iteratively debug and test code until it passes. Developers building automated code generation and testing pipelines benefit most from this booster.
Summarize and reflect on past Codex session histories to identify patterns, themes, and insights from your coding work. Useful for developers who want to audit their development process, track projects, or surface repeated patterns across multiple sessions.
"name": "llm-council-plugin", "description": "Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.", "repository": "https://github.com/xrf9268-hue/llm-council-plugin",
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.
rsmap enables AI assistants to efficiently search and understand Rust codebases through multi-layered LLM-friendly indexes, eliminating the need to scan source files directly. Developers working with large Rust projects benefit from faster code exploration and architectural understanding.
"name": "magi-researchers", "version": "0.17.0", "description": "Three AI models, one synthesis \u2014 multi-model research workflow for scientific domains",
"name": "trueline-mcp", "description": "Truth-verified file editing for AI coding agents via MCP", "url": "https://github.com/rjkaes"
Persona is a Cursor-integrated prompt kit that guides users through building and deploying a personal portfolio website with structured workflows, design skills, and quality checklists. It benefits developers and designers who want AI-assisted help creating professional online portfolios.
"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
"description": "Fast indexed code search — 5x faster than ripgrep using sparse n-gram indexing", "name": "Aisar Labs", "email": "qaiyyum@aisar.ai"
"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",
Codex enables independent AI code review of Claude's changes using the OpenAI Codex CLI, supporting maker-checker workflows. Developers using Claude Code can leverage this for automated second-opinion code validation before committing.
"name": "nexo-brain", "description": "Local cognitive runtime for Claude Code \u2014 persistent memory, overnight learning, doctor diagnostics, personal scripts, recovery-aware jobs, startup preflight, and optional dashboard/power helper.", "name": "NEXO Brain",
"version": "9.7.14", "description": "CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Gemini, and Claude", "repository": "https://github.com/tellang/triflux",
"name": "init-workspace", "description": "Initialize a multi-agent workspace with shared configuration for Claude Code, Codex CLI, and Gemini CLI", "homepage": "https://github.com/xiaolai/init-workspace",
"name": "claude-local-docs", "version": "1.0.23", "description": "Local-first Context7 alternative — indexes JS/TS dependency docs with a 4-stage RAG pipeline (vector + BM25 + RRF + cross-encoder reranking). Uses TEI Docker containers for GPU-accelerated embeddings and reranking.",
"description": "Multi-model AI plan review: run any acpx-supported agent (Codex, Gemini, Kimi, Qwen, etc.) in parallel, synthesize feedback, debate contradictions", "url": "https://github.com/strml" "homepage": "https://github.com/STRML/cc-debate",
An MCP server that integrates Codex CLI with Claude Code and Claude Desktop, enabling developers to leverage Codex capabilities within Claude's ecosystem for enhanced code generation and AI-assisted development.
Memory Bank MCP Server provides semantic code indexing and AI-powered codebase understanding for developers using Claude. It enables intelligent code exploration and context-aware assistance directly within Claude Desktop and Claude Code.
Intelli-router automatically triages user messages by complexity and routes them to the most cost-effective AI model (local Ollama, Claude Sonnet, Codex, or Claude Opus). Developers building multi-model AI systems benefit from reduced costs and optimized latency.
A Cursor rules file that enforces MVI architecture, Jetpack Compose patterns, and Kotlin conventions for Android PokeDex app development. Developers building modular Android apps with Compose and MVI will benefit from standardized architectural guidance.
Second Brain MCP is a semantic search engine for your codebase that lets you find code by natural language queries (like "find the auth bug") instead of grep, using embeddings and local SQLite vector search. It's ideal for developers who want faster code navigation and context awareness across large projects.
