Open-source alternatives to Nerve

A simple REST API and CLI client to interact with Model Context Protocol (MCP) servers.

An MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive interface for managing, testing, and using MCP servers with your favorite chat plugins.

A middleware to provide an openAI compatible endpoint that can call MCP tools

Magg: The MCP Aggregator

This project is a Python framework for building autonomous AI agents capable of executing independent tasks through goal-oriented instructions. It provides a library of tools for managing system operations and processing multimodal data. The framework features a sandboxed system execution environment that restricts shell commands and file access to protect the host system. It also includes an automated OCR text extraction pipeline for converting printed or handwritten text from images and documents into digital formats. Connectivity is handled through a modular tool integration system and a

A CLI inspector for the Model Context Protocol

Zed is an AI-native, high-performance code editor designed for extreme responsiveness and keyboard-centric workflows. It functions as an extensible text processing workspace that integrates autonomous agents and predictive models directly into the development environment to automate complex engineering tasks, refactoring, and code generation. The editor distinguishes itself through a GPU-accelerated rendering pipeline and an asynchronous multi-threaded architecture that ensures low-latency interaction even with large-scale projects. It features built-in support for real-time, multi-user colla

the terminal client for LLMs

JDBCX: Extended JDBC driver for dynamic multi-language queries with optional bridge server for federated datasource connectivity.

ZhihuDaily with Swift language

🦁 AI chat & search summaries in Brave Search, powered by the latest LLMs

🐤 AI chat & search summaries in DuckDuckGo, powered by the latest LLMs

This project is a cross-platform desktop application that wraps web-based interfaces into a standalone, native container. By utilizing a webview-based rendering engine, it allows users to access web services as local applications on Windows, macOS, and Linux without requiring a full browser installation. The application is built on a memory-safe backend that manages system-level tasks and facilitates secure communication between the web frontend and the native operating system. This architecture enables features such as system-tray integration for background execution and quick access, provid

🚀 Powerful Local AI Chat Application - Mcp, Secure, Efficient, Personalized 本地化部署的大模型客户端

CodeMirror extension to hook up a Model Context Provider (MCP)

This project is an AI assistant for Visual Studio Code that utilizes a large language model to generate code and answer programming queries. It functions as a code generator and assistant, enabling the insertion of AI-generated snippets directly into active source files and providing a conversational interface via a side panel chat. The extension facilitates structural refactoring, optimization, and debugging of selected code blocks through natural language prompts. It also generates natural language explanations and technical documentation for complex code segments without requiring the user

Plug and play AI agents for any domain

5ire is a conversational AI interface and client that integrates large language models with external tools and local data. It functions as an AI prompt manager, a local retrieval-augmented generation knowledge base, and a monitoring tool for tracking API usage and spending across multiple model providers. The project specifically implements the Model Context Protocol to connect AI assistants with live data and executable system tools. It supports tool installation via custom application protocol URIs and uses schema-driven input generation to create interactive configuration forms for server

MCP Server & Config Manager for 14 AI Clients — Cursor, VS Code, Claude Code, Gemini CLI, Windsurf, Zed, TRAE, Kiro, JetBrains & more. 8500+ servers, 4400+ skills.

DeepChat is a desktop application that connects to multiple cloud and local AI model providers through a single unified chat interface, while also integrating external ACP-compatible coding and task agents as selectable models. It manages local AI agent sessions with project folders, permission modes, and resumable context for long-running tasks, and connects external tools and data sources via the Model Context Protocol using StreamableHTTP, SSE, or Stdio transports. The application distinguishes itself by supporting remote desktop session control, binding messaging app channels to sessions

JokeClient-Swift 1.基于swift

PyChatGPT is a Python library for sending prompts to language model APIs and receiving generated text responses programmatically. It serves as an API client that integrates language model capabilities into Python applications. The project includes an automated authenticator to retrieve and refresh access tokens without requiring a web browser. It also features a proxy-enabled network client that routes API requests through proxy servers to bypass network restrictions and manage rate limits. To maintain continuity, the library provides conversation state management that tracks chat history an