83 boosters for "RAG" — open source, verified from GitHub, ready to install
人脑不是硬盘，不会无差别存储所有信息。人脑会： DNA Memory 模拟这个过程，让 Agent 真正"进化"。 并且仅在有新的 写入后才执行 ，避免重复归纳同一批记忆。
"description": "Pinecone vector database integration. Streamline your Pinecone development with powerful tools for managing vector indexes, querying data, and rapid prototyping. Use slash commands like /quickstart to generate AGENTS.md files and initialize Python projects and /query to quickly explo
This MCP server enables AI coding agents to analyze test coverage from LCOV files, making them coverage-aware while optimizing token usage. It's valuable for developers using Claude Desktop or Code who want to improve code quality by integrating coverage insights into their AI-assisted workflows.
"version": "1.54.1", "description": "Sets up your project for effective AI-assisted development — optimized CLAUDE.md files, effective coding guidelines, formatter hooks, built-in code-quality agents, TDD and test coverage, all tailored to your actual codebase.", "name": "oprogramadorreal",
"description": "Beacon — semantic code search for Claude Code", "repository": "https://github.com/sagarmk/Claude-Code-Beacon-Plugin", "homepage": "https://github.com/sagarmk/Claude-Code-Beacon-Plugin",
Use when organizing media files (movies, TV, anime) on NAS or local storage - cleaning junk files, merging scattered episodes, normalizing folder names to "Title (Year)" format, and verifying episode completeness against TMDB
RagCode MCP is a semantic code navigation tool that integrates RAG-powered code search into Windsurf and other IDEs, enabling developers to intelligently query and understand multi-language codebases using local LLMs. It's ideal for developers working with Laravel, Go, Python, and PHP who need fast, context-aware code exploration without leaving their IDE.
A FastAPI-based MCP server that connects Copilot to lead generation APIs while enforcing clean architecture and SOLID principles for maintainable prospect prospecting workflows. Ideal for developers building AI-assisted B2B sales tools.
Autarch Agent System is a multi-agent architecture that orchestrates AI workflows across scoping, research, planning, execution, and review stages, enabling developers to leverage AI for structured, traceable code generation and codebase analysis at scale.
Transforms rough prompts into production-ready LLM prompts using advanced techniques like Chain-of-Thought and RAG optimization. Ideal for developers, AI engineers, and teams building LLM applications who need to craft effective prompts across Claude, GPT, Llama, and other models.
"description": "Pure filesystem-based memory system for Claude Code with custom ontology support", "email": "zircote@gmail.com", "url": "https://github.com/zircote"
Driflyte MCP Server is a web-crawler integration for Claude that enables AI models to fetch and process web content through the Model Context Protocol. It's useful for developers building RAG systems, AI agents, and LLM applications that need real-time web data access.
Forage is a self-improving tool discovery system that enables AI agents to automatically find, install, and learn to use new tools without manual configuration. It benefits developers building extensible AI applications and agents that need dynamic capability expansion.
Heuristic scoring (no AI key configured).
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.
This MCP server enables developers to manage Supabase projects comprehensively, including database operations, authentication, storage, realtime features, and migrations directly through Claude and Cursor. It's ideal for full-stack developers building applications with Supabase who want AI-assisted project management and automation.
"name": "agent-pragma", "owner": { "name": "Peter Wilson" }, "description": "Pragma directives for AI coding agents — deterministic linting, semantic LLM validators, and multi-LLM advisory council for Go, Python, and TypeScript"
A migration guide for transitioning from deprecated hardcoded agents to a dynamic ConfigurableAgent system in a Rust-based agentic chatbot server. Developers maintaining or upgrading agent-based systems benefit from clear configuration patterns and best practices for multi-provider LLM setups.
"name": "brainlayer", "name": "Etan Heyman", "url": "https://github.com/EtanHey"
"name": "wicked-garden", "description": "AI-Native SDLC \u2014 the complete software development lifecycle as a single Claude Code plugin. 14 domains covering code intelligence, delivery metrics, persistent memory, workflow orchestration, brainstorming, on-demand personas, and 80 specialist agents a
"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",
"name": "claude-memory-plugin", "description": "Persistent knowledge storage with semantic search, graph linking, and contextual gotcha injection", "name": "Gareth Williams",
A Twitter/X engagement agent that helps users create viral content, leverage trending topics, and build communities through strategic, concise communication and thread storytelling.
TDD Command enforces test-driven development workflows by guiding developers through the RED-GREEN-REFACTOR cycle with 80%+ coverage targets. Developers prioritizing code quality and test coverage will find this particularly valuable.
