301 boosters for "LLM" — open source, verified from GitHub, ready to install
This MCP Server converts Figma designs into pseudo-code structures that LLMs can easily understand, enabling seamless design-to-code workflows for developers and designers building prototypes and applications.
"name": "pupu-skills", "description": "Claude Code 技能记忆插件 — Markdown 技能库 + LLM 路由 + 效用评分，让 Claude 拥有持久化技能记忆", "name": "pupu-skills"
A WhatsApp CLI skill that enables querying chats, searching messages, sending/forwarding content, and managing groups directly from Claude Code. Useful for developers automating WhatsApp interactions or building WhatsApp-integrated applications.
A lightweight MCP server that enables AI agents to send real-time progress updates directly to Telegram, supporting text, images, and files. Ideal for developers who want instant notifications from long-running AI tasks without polling or complex integrations.
A skill that enables Claude Code to query other LLMs (ChatGPT, Gemini, DeepSeek, Grok) through MCP servers by routing requests based on the first word of a query. Useful for developers who need multi-LLM comparison or fallback capabilities within Claude Code environments.
Automates synchronization of custom Ollama models across distributed Vera AI clusters using YAML configuration and templating. Benefits DevOps engineers and teams managing multi-instance LLM deployments who need centralized model management.
An MCP Server that enables Claude to execute SQL queries and interact with databases (PostgreSQL via Sequelize). Developers building AI applications that need database access will find this useful for data retrieval and manipulation tasks.
This MCP server transforms linear AI reasoning into structured, auditable thought graphs using DAG (directed acyclic graph) representations, enabling developers to visualize and verify AI decision-making processes with full traceability.
"name": "silver-bullet", "description": "Agentic Process Orchestrator for AI-native Software Engineering & DevOps. Combines GSD, Superpowers, Engineering, and Design plugins into enforced 20-step (app) and 24-step (DevOps) workflows with 10-layer technical compliance.", "version": "0.13.2",
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.
A Cursor IDE rules configuration providing comprehensive development standards and best practices for LLM application development, including project structure guidelines, coding principles, and documentation conventions.
An MCP server that provides structured access to adversarial tactics and cyber attack techniques for security research, penetration testing, and AI safety evaluation. Useful for security professionals, red teamers, and AI safety researchers studying attack vectors.
"description": "Save tokens and cut inference costs by routing compute through MVM nodes on the cheapest available energy.", "url": "https://github.com/nhevers" "repository": "https://github.com/nhevers/mica-plugin",
The ops agent automates infrastructure management, deployment, and cloud operations for DevOps teams. Developers and DevOps engineers use it to streamline CI/CD pipelines, monitor systems, and maintain production reliability.
An MCP server that automates the installation and setup of other MCP servers, streamlining the process of extending Claude's capabilities. Developers and Claude users benefit by reducing manual configuration overhead when adding new MCP integrations.
A system prompt that guides LLMs to act as rigorous sustainability and risk analysts for Polkadot governance proposals, evaluating treasury allocations through investment frameworks, fiscal precedent, and accountability mechanisms.
Node Code Sandbox MCP enables AI agents and LLMs to safely execute JavaScript code, install npm packages, and test implementations in real-time. Developers building coding assistants, automated testing tools, and interactive AI applications benefit from this secure, MCP-compliant execution environment.
A QA-focused agent that creates comprehensive test suites, identifies edge cases, and ensures code quality through systematic testing methodologies. Developers and QA engineers benefit from automated test strategy development and validation across different testing levels.
Atlas Guardrails provides context packing and duplicate detection tools to help AI coding assistants manage large codebases efficiently and avoid redundant code generation. Developers working on large projects benefit from cleaner context and reduced code duplication.
Augure is a proactive AI agent MCP server that integrates with Claude Desktop and Claude Code, enabling automation through Telegram, email, Docker, and scheduled tasks. It's designed for developers and power users who need an intelligent agent to automate workflows and manage integrations across multiple platforms.
brosh is a Cursor-integrated MCP server that enables AI assistants to capture full-page browser screenshots with scrolling support using Playwright. Developers using Claude in Cursor benefit from automated visual webpage inspection for debugging, testing, and content analysis.
Freshcontext MCP is a real-time web extraction server that provides AI agents with fresh, timestamped data from sources like GitHub, Hacker News, and Y Combinator. Developers building AI applications need current contextual information, making this especially valuable for agents requiring up-to-date web data.
Geist provides Cursor-integrated coding rules and best practices for Python, SQLAlchemy, logging, and server development using FastAPI and LLM models. It helps developers maintain consistent code standards and proper patterns when building AI-powered applications.
gllm is a system prompt that transforms LLMs into code-first orchestrators for efficient task processing, enabling developers to handle large files and complex workflows through programmatic verification rather than context-heavy text generation.
