393 boosters for "LLM" — open source, verified from GitHub, ready to install
PocketFlow-PHP is a set of Cursor rules that guide AI agents to build modular, agentic PHP applications using a minimalist LLM framework with strict architectural constraints. Developers using Cursor for PHP projects with AI assistance benefit from clear architectural guardrails.
"name": "proof-engine-marketplace", "name": "Yaniv Golan", "email": "yaniv@golan.name"
Dossier is an MCP server that enables LLMs to discover, verify, and execute dossiers—standardized automation workflows. It's useful for developers and AI teams who want to automate complex, multi-step tasks through Claude and other AI platforms.
A TypeScript MCP server booster for integrating the ReviewWebsite API with Windsurf, providing CLI tools, validation schemas, and structured patterns for AI-assisted development. Ideal for developers building AI-powered review applications or extending Windsurf with ReviewWebsite capabilities.
"name": "truesight", "description": "MCP server and agent skills for the Truesight AI quality platform. Score inputs, build evaluations, analyze errors, and review results through natural language.", "name": "Goodeye Labs"
Oros cursor rules provide development guidelines for a decentralized AI chat application that bridges LLM capabilities with blockchain tasks through a Go proxy and React frontend. Developers building or contributing to multi-LLM dApp integrations would benefit from these structured rules.
"name": "brainlayer", "name": "Etan Heyman", "url": "https://github.com/EtanHey"
ArmBench-LLM is a system prompt for benchmarking large language models using Armenian character-to-numeric matching tasks. It's designed for developers evaluating LLM performance across multiple coding platforms.
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.
This MCP Server dynamically converts OpenAPI specifications into Claude-compatible tools, enabling AI models to interact with any REST API without manual tool configuration. Developers and API providers benefit by instantly exposing their APIs to Claude with minimal setup.
"name": "dialectic-marketplace", "name": "Urav Maniar", "email": "urav06@gmail.com"
ArmBench-LLM is a system prompt framework for evaluating large language models on Armenian language tasks through structured multiple-choice questions. It's designed for developers and AI researchers who need standardized benchmarking tools across popular coding assistants and chat platforms.
A Korean-language code review guide for the Trade Safety project, providing development standards for a K-pop merchandise trading safety analysis tool. Developers building scam-detection features for international fan communities would benefit from its architectural and code quality guidelines.
"name": "@orcarouter/mcp", "mcpName": "io.github.Continuum-AI-Corp/orcarouter-mcp", "description": "Official Model Context Protocol server for OrcaRouter — an OpenAI-compatible LLM API gateway.",
"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"
An MCP server enabling AI assistants to manage Netskope's Zero Trust Network Access Platform directly through natural language, benefiting security teams and network administrators seeking to automate access control workflows.
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.
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": "agent-callable", "name": "Platform Team", "email": "820504+grams@users.noreply.github.com"
A debate judge agent that objectively evaluates arguments using zero-sum scoring across Toulmin structure, evidence strength, and logical rigor. Ideal for researchers, educators, and developers building computational debate systems.
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 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 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.
"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"
