ChatGPTNextWeb/NextChat
NextChat is a lightweight, privacy-focused AI assistant platform supporting multiple AI models and operating systems, with Model Context Protocol (MCP) support for enhanced AI interactions.
Awesome MCP › Desktop & Mobile Clients
Witsy is a versatile desktop AI assistant designed to integrate multiple large language model (LLM) providers and support the Model Context Protocol (MCP) to deliver advanced AI functionalities. It acts as a universal MCP client, allowing users to run MCP servers with virtually any LLM, making it one of the few applications with such broad compatibility. Witsy supports a wide range of LLM providers including OpenAI, Ollama, Anthropic, MistralAI, Google, xAI, Azure, OpenRouter, DeepSeek, Groq, and Cerebras, among others. It also supports connecting other providers through an OpenAI compatibility layer. The application offers a rich set of features such as chat completion with vision model support, enabling users to describe images, text-to-image and text-to-video generation using various providers like OpenAI, Google, xAI, Replicate, fal.ai, and HuggingFace. It also supports image-to-image editing and image-to-video generation. Witsy includes LLM plugins to augment language models with capabilities like executing Python code and internet search. Additional functionalities include a scratchpad for interactive content creation, prompt anywhere feature to generate content directly in any application, AI commands to boost productivity by running commands on highlighted text, and expert prompts to specialize the AI assistant on specific topics. It supports long-term memory plugins to enhance the relevance of LLM responses, read aloud features for assistant messages and any text in other applications, and chat with local files and documents using retrieval-augmented generation (RAG). Witsy also offers transcription and dictation capabilities using OpenAI Whisper or local Whisper models, real-time voice chat mode, local conversation history with automatic titles, formatting and clipboard copy for generated code, conversation PDF export, and image copy and download. It is a BYOK (Bring Your Own Keys) application requiring users to provide API keys for the LLM providers they wish to use or run models locally via Ollama. Overall, Witsy is a comprehensive AI assistant desktop application that leverages the Model Context Protocol to provide a universal, extensible, and powerful AI experience across multiple modalities including text, vision, and voice.
https://github.com/nbonamy/witsy
NextChat is a lightweight, privacy-focused AI assistant platform supporting multiple AI models and operating systems, with Model Context Protocol (MCP) support for enhanced AI interactions.
Cherry Studio is a cross-platform desktop client supporting multiple LLM providers and featuring an MCP server, AI assistants, document processing, and practical AI tools for enhanced user experience.
Self-hosted personal AI assistant in Python with a desktop app, terminal UI and chat-channel connectors, whose driver layer works as an MCP host that routes agent tool calls to external MCP, A2A and ACP servers.
Nuclear is a free, open-source music player for desktop that allows users to search, stream, and manage music from various sources, featuring a powerful plugin system and an MCP server for AI agent...
Electerm is a versatile open-source multi-platform client for terminal, SSH, SFTP, FTP, Telnet, serial port, RDP, and VNC connections with integrated AI assistant support via the Model Context Protocol (MCP) widget.
RikkaHub is a native Android chat client app supporting multiple large language model providers with Model Context Protocol support, multimodal input, and advanced customization features.
A curated collection of production-ready and experimental Model Context Protocol (MCP) clients enabling secure AI model interactions with local and remote resources through standardized implementations.
DeepChat is an open-source AI chat platform that unifies multiple large language models with advanced search enhancement and Model Context Protocol (MCP) support for tool integration and code execution.