Genkit is an open-source framework for building AI-driven applications, providing Node.js and Go libraries, supporting the integration of multiple AI models and vector databases, and including development tools and a plugin ecosystem.

Eino is an LLM application development framework designed specifically for Golang, aiming to simplify the AI application development process through concise, scalable, reliable, and efficient component abstraction and orchestration capabilities. It provides a rich component library, powerful graphical orchestration functions, complete stream processing support, and a highly scalable aspect mechanism, covering the full-cycle toolchain from development to deployment.

The StrawHat AI development repository provides a complete solution for building local and online AI development environments, including various tools such as the Ollama backend, Open - WebUI frontend, and Claude desktop proxy, supporting rapid deployment and development of AI applications.

The privateGPT MCP Server is a server implementation based on the Model Context Protocol (MCP), allowing users to integrate privateGPT as an agent with MCP clients, providing a secure and modular AI application development environment.

The Electron MCP Server is a server based on the Model Context Protocol (MCP), providing comprehensive automation, debugging, and observability capabilities for Electron applications. It implements AI-driven automation through the integration of the Chrome DevTools protocol, supporting real-time UI interactions, visual debugging, deep inspection, and development observability, and can work without modifying the target application's code.

Cursor MCP is a tool that enables seamless integration of Claude AI with desktop applications. It bridges AI capabilities with development workflows through the Cursor IDE, providing real-time programming assistance and context-aware code suggestions.

The Screeny MCP Server is a privacy-first screenshot service designed specifically for macOS, allowing AI agents to securely capture screenshots of pre-approved application windows and providing a visual context for development and debugging tasks.

MCP4Go is a Model Context Protocol (MCP) library implemented in Go language, aiming to simplify the development of AI applications and provide a complete protocol implementation and high-level abstraction.

Swiss MCP is an AI-driven multi-step task coordination center that can integrate various AI tools to complete complex tasks, such as content creation and full-stack application development.

Databutton launches an AI - driven MCP server building tool that supports React and Python application development

OmniMind is an open - source Python library designed to simplify Model Context Protocol (MCP) integration and support the development of AI agents, workflows, and automation. It offers plug - and - play functionality, has built - in multiple tools, and provides intelligent responses based on Google Gemini, making it suitable for developers and beginners to quickly build AI applications.

This is a curated list of resources for the Model Context Protocol (MCP) ecosystem, covering multiple categories such as official resources, development tools, MCP servers, web integrations, databases, blockchains, AI integrations, voice, mobile applications, development environments, security testing, productivity tools, and system tools.

A tool that enables seamless integration of Claude AI with Cursor IDE desktop applications, enhancing the AI-assisted development workflow through the MCP protocol.

Solon-AI is a Java AI application development framework for all scenarios, supporting multiple AI capabilities and can be embedded in various frameworks for use.

A cross - platform desktop application developed for the omni AI MCP Server, supporting Android and iOS development

This project tests the capabilities of LLM in information retrieval, API integration (such as IGN's APICARTO and GéoPlateforme services), and code generation through ChatGPT, including functions such as geocoding and postal code query, and explores the application of AI in technical evaluation and development assistance.

AppDog is a project that can easily generate MCP servers from OpenAPI specifications, aiming to simplify the development process and help developers quickly build applications.

The E2B Cookbook is a project containing various example codes and guides for development using the E2B SDK. It covers a variety of scenarios from basic introduction to advanced applications, including integration with different LLM providers, integration of AI frameworks, and practical application cases.

The ARC MCP Server is an innovative platform that provides tools such as document assistance, API integration, project generation, and deployment support through the seamless integration of AI models and the ARC enterprise application framework, accelerating the development of enterprise-level cloud-native applications.

This is a list of multiple open - source AI projects, covering multiple fields such as automated agents, large - language models, image generation, and AI development frameworks. These projects aim to help developers make money using AI technology, including building intelligent assistants, automating workflows, and content generation applications.

An application based on TypeScript that integrates AI service functions such as OpenAI and HubSpot, including development environment configuration, API integration, and front - end and back - end development capabilities.

This project demonstrates how to integrate Claude AI into the development process through the MCP protocol, including an MCP server and a to-do application demonstration to achieve AI-assisted software development.

Wordware MCP is a server for running Wordware AI applications locally. It supports integrating Wordware's AI capabilities into local development environments via APIs, simplifying the testing and development process.

A collection of tools for adding AI capabilities to Nuxt applications, including a Nuxt module and development tools.

The MCP startup project is an AI application development framework that includes a Python server - side and a TypeScript client - side, supporting the interaction between AI models and external tools/APIs, and providing functions such as document search and conversation management.

Pro MCP is a community-driven directory of Model Context Protocol (MCP) servers, aiming to provide a comprehensive list of MCP servers for developers and AI enthusiasts and promote the development of intelligent applications.

An example project that includes various AI agents and RAG technologies, covering Gemini applications, MCP services, Flutter applications, and Vertex AI integration, providing AI development examples from basic to advanced.

This project uses the Quarkus framework and the Model Context Protocol (MCP) to implement an intelligent agent application based on multiple MCP servers. It combines LangChain4j to provide functions such as AI dialogue, restaurant recommendation, and Slack notification, and supports deployment in development and production environments.

A low-cost, no-code AI SaaS building platform based on Raspberry Pi that enables everyone to develop complete SaaS applications with a device costing $480, including browser automation testing and AI-assisted development features.

This project provides code examples for developing and running an MCP server on Oracle OCI, including Python development, AI agent integration, semantic search, SelectAI integration, and connection with AI assistants such as ChatGPT, to help build enterprise - level AI applications.

AppBuilder-SDK is an AI-native application development toolkit provided by Baidu Smart Cloud Qianfan Platform, supporting model calls, component orchestration, and monitoring deployment.

PydanticAI is a Python agent framework developed by the Pydantic team, aiming to simplify the development of production-grade applications based on generative AI. It supports multiple AI models, integrates Pydantic validation and structured output, provides a dependency injection system, streaming responses, and graph support, and seamlessly integrates with Pydantic Logfire. It is suitable for building AI applications that require type safety and efficiency.