125 boosters for "lm" — AI-graded, open source, ready to install
A specialized agent that systematically crafts and optimizes prompts for LLMs and AI systems through iterative refinement and performance measurement. Ideal for AI engineers, prompt designers, and developers who need to maximize LLM effectiveness across applications.
A specialized agent that systematically crafts, tests, and optimizes prompts for LLMs through multiple cognitive modes (generative, critical, evaluative, informative) and performance measurement. Ideal for AI engineers, prompt researchers, and developers seeking to maximize LLM output quality.
A Windsurf prompt that enforces French-language interaction with Cowboy Bebop references and provides detailed specifications for exercise UI design using Bulma. Intended for French-speaking developers building interactive math exercise platforms.
A practical integration guide for enhancing OCR text extraction with visual and language LLM capabilities using local Ollama models in Caption Extractor. Developers working with document processing, image analysis, and text correction workflows benefit from this reusable agent framework.
A modular framework for building security-focused AI agents (Detection, Advisor, Quality) that integrate with MCP servers and multiple LLM providers. Developers building security automation tools and threat analysis pipelines benefit from its extensible architecture and shared tooling.
A specialized system prompt that transforms Claude into an LED display consultant for sports venues, enforcing structured JSON data capture after each user interaction to build quote specifications incrementally.
A system prompt that enables LLMs to classify Hacker News content into mutually exclusive LLM and software development categories using context-aware analysis. Useful for content curators, researchers, and developers building topic-classification systems.
This system prompt enables smaller LLMs (8B-20B parameters) to control Windows 11 desktops through the Model Context Protocol, automating desktop tasks via natural language. It's valuable for developers building AI agents, automation workflows, and users seeking lightweight local alternatives to cloud-based desktop controllers.
A hierarchical taxonomy (L0-L5) for classifying data agents by autonomy level, helping teams clarify capabilities, set expectations, and allocate responsibility in LLM-powered data systems. Useful for architects, product managers, and developers building or evaluating data agents.
This MCP server enables AI assistants to read, search, and interact with any MediaWiki wiki (Wikipedia, internal wikis, etc.), allowing LLMs to access and leverage wiki content programmatically. Developers and organizations using MediaWiki instances benefit from seamless AI integration for knowledge retrieval and automation.
A safe, high-signal web browsing MCP server that enables Claude to fetch and extract content from web pages using Playwright, ideal for LLM agents needing reliable real-time information. Developers building Claude integrations that require web access will find this particularly valuable.
This MCP server integrates with Civic Plus See Click Fix, enabling users to access and interact with civic data through an LLM interface. It's useful for municipal staff, developers, and citizens working with See Click Fix complaint and issue tracking systems.
Markitai is an opinionated Markdown converter with native LLM enhancement support, designed to help developers using GitHub Copilot maintain consistent code standards and project guidelines. It's ideal for teams managing Python projects with strict type annotations, code style, and testing requirements.
An expert prompt engineering agent that optimizes prompts for LLMs and AI systems, helping developers build better AI features and improve agent performance through proven prompt patterns and techniques.
Forge provides a framework and provider abstraction layer for building execution agents that autonomously write, review, test, debug, and deploy code across multiple LLM platforms. Developers building AI-driven development tools, CI/CD automation, and code generation systems will benefit from this structured agent foundation.
Clara is a privacy-focused, client-side WebUI for interacting with LLMs without any backend infrastructure or data leaks. Developers and privacy-conscious users who want complete control over their AI conversations benefit from this tool.
Kibi is a local-first AI agent CLI tool that integrates with Claude via MCP, providing a terminal-based interface for AI-powered workflows. It benefits developers and power users who want to run AI agents locally with full control over their data and LLM interactions.
A multi-LLM system prompt for coordinating development across Claude, ChatGPT, Cursor, and Windsurf with architecture guidelines and agent synchronization protocols. Primarily benefits teams using multiple AI assistants in coordinated workflows.
Heuristic scoring (no AI key configured).
Cursor Rules for WitsV3 provides development guidelines and best practices for contributing to an LLM orchestration system, covering architecture, async patterns, code structure, testing, and task management. Developers working on WitsV3 or similar LLM wrapper projects benefit from these structured conventions.
A multi-agent red-teaming framework that orchestrates coordinated AI security testing with an arbiter to consolidate findings and maintain an immutable audit trail. Security engineers and AI developers use it to systematically test LLM vulnerabilities with repeatable, deterministic results.
A Canvas LMS integration MCP server that enables quick access to courses, assignments, and grades directly from Claude, Cursor, and Claude Code. Students and educators benefit from streamlined coursework management without leaving their AI assistant.
Converts deepagents' single `task` tool into individual `AgentTool` instances for cleaner sub-agent delegation in adk-deepagents. Developers building hierarchical multi-agent systems benefit from this more modular approach to agent composition.
