AI & ML

Sourcebot is a code search and intelligence engine that enables natural language querying, IDE-level code navigation, and cross-repository search across GitHub, GitLab, and other hosts.

A tool that integrates macOS native applications like Messages, Mail, Calendar, and Notes into the Model Context Protocol, enabling AI-driven automation of your Apple ecosystem.

A native macOS LLM server and MCP aggregator that runs local MLX models and connects to remote providers while exposing a suite of system tools for filesystem, browsing, and git operations.

A robust framework to programmatically assemble prompts using JavaScript/TypeScript, enabling orchestration of LLMs, tools, and data with built-in RAG and containerized code execution support.

Solon is a high-performance Java enterprise application framework designed as a lightweight and efficient alternative to Spring, offering 700% higher concurrency and 90% smaller package sizes.

A specialized MCP server providing AI assistants with direct access to shadcn/ui v4 components, blocks, and demos across React, Svelte, Vue, and React Native frameworks.

UltraRAG v2 is a low-code MCP framework designed for building complex RAG pipelines using a component-based architecture and YAML-driven flow control. It simplifies the implementation of advanced retrieval-augmented generation systems by wrapping core logic into reusable MCP servers.

A comprehensive MCP server suite providing a seamless connection between AI agents and the Azure ecosystem, enabling operations across cloud infrastructure, databases, and developer services.

Local-first knowledge management system that builds a semantic graph from Markdown files, enabling persistent memory across conversations with LLMs.

A comprehensive marketplace and discovery platform for Claude Code, offering curated collections of agents, commands, hooks, and skills to extend AI workflows.

A metasearch MCP server that aggregates web search results from multiple backends including Google, Bing, DuckDuckGo, and Brave for text, images, videos, news, and books.

A Model Context Protocol server that allows AI assistants to search, download, and analyze academic research papers from arXiv with local storage capabilities.

A specialized MCP server designed to crawl, index, and query technical documentation, turning complex web content into LLM-ready context for rapid software development.

A specialized MCP server acting as a proxy between LLMs and existing enterprise endpoints, enabling discovery and execution of auto-healing, LLM-mapped tools.

Lemonade is a high-performance local LLM server and SDK that optimizes inference on GPUs and NPUs (including AMD Ryzen AI). It provides an OpenAI-compatible API to run GGUF, FLM, and ONNX models locally with hardware acceleration.

Shrimp Task Manager is an MCP server designed for AI-driven development, providing persistent memory, structured workflows, and automated task decomposition with dependency tracking.

High-performance web crawling and RAG server that integrates Crawl4AI with Supabase and Neo4j for semantic search, code example extraction, and AI hallucination detection via knowledge graphs.

The official Perplexity MCP server provides AI assistants with real-time web search, deep research, and advanced reasoning capabilities using Sonar models and the Perplexity Search API.

Universal database MCP server connecting to MySQL, MariaDB, PostgreSQL, and SQL Server.

A robust web access MCP server by Bright Data that provides AI agents with unblockable web search, markdown scraping, and structured data extraction from major retail, social, and financial platforms.

MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding

A cloud browser MCP server that enables AI agents to perform complex web automation, scraping, and autonomous tasks with built-in stealth features and credential management.

A comprehensive PostgreSQL MCP server that enables AI agents to perform schema exploration, SQL execution, and advanced performance tuning using industrial-strength index optimization algorithms.

Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.

An MCP client and hub for Neovim that integrates multiple MCP servers into the editor, supporting tools, resources, and prompts for popular AI plugins like Avante and CodeCompanion.

Dive is an open-source MCP host desktop application that acts as a central hub for integrating LLMs with MCP servers, featuring built-in local tools for file management and system execution.

A powerful AI-driven RSS hub and information processing center that uses MCP to bridge RSS feeds with LLMs, enabling automated summarization, monitoring, and daily reporting.

Bifrost is a high-performance LLM gateway that provides a unified OpenAI-compatible API for over 15 providers with built-in MCP support for external tool calling.

A comprehensive MCP server that empowers AI agents to perform 60+ blockchain actions on Solana, including token deployment, NFT management, DeFi trading (swaps, perps, lending), and cross-chain bridging.

A universal memory platform that allows users to collect, organize, and recall information across any LLM via the Model Context Protocol. It provides a centralized knowledge base that syncs personal data from various sources with optional self-hosting support.