MCP servers, clients and tools

Agent Zero is an autonomous AI agent framework designed to execute complex, multi-step workflows by managing its own environment, persistent memory, and external tool interactions. It functions as a Python-based automation library that enables agents to write code, execute terminal commands, and perform system-level tasks independently. The system is built to handle large-scale operations through hierarchical agent delegation, allowing for the coordination of subordinate agents to maintain focus and context. The platform distinguishes itself through a focus on secure, isolated execution and standardized integration. It utilizes a sandboxed environment for all system-level operations and incorporates a security-first approach to plugin management, automatically scanning external tools for vulnerabilities before deployment. By leveraging the Model Context Protocol, the framework provides a unified interface for connecting to external data sources and third-party tools, ensuring that agents can expand their functional capabilities while maintaining strict environment-based configuration isolation. The system supports a broad range of operational requirements, including persistent knowledge management, automated scheduling of recurring tasks, and secure credential handling. It provides tools for analyzing complex data and performing automated security assessments, ensuring that long-running tasks remain consistent and transparent. The framework is designed for developers to build and manage self-directed agents that operate within defined security boundaries.

This project is a comprehensive network traffic orchestrator and server infrastructure manager designed to provide centralized control over secure tunneling, routing, and security policies. It functions as a web-based dashboard that enables administrators to deploy and maintain network services, enforce access restrictions, and manage traffic flow through a private server environment. The platform distinguishes itself by integrating advanced traffic anonymization and routing capabilities, including support for relay networks and secure tunnels to bypass regional restrictions. It provides granular control over network security through automated certificate lifecycle management, host-based firewall rule enforcement, and the ability to configure specialized transport protocols. Administrators can further manage server operations remotely via event-driven messaging bot integration, allowing for real-time monitoring and command execution. Beyond its core routing and security functions, the software supports flexible deployment models, including containerized orchestration and automated script-based installation. It includes a suite of maintenance tools for monitoring user traffic, managing geographical routing databases, and hardening system environments against unauthorized access. The project provides multiple installation paths, ranging from automated scripts to manual binary deployment, to accommodate various server configurations.

Ant Design is an enterprise-grade component library and design system framework built for developing complex, data-heavy web applications. It provides a comprehensive collection of pre-built, state-driven interface elements that map data properties to rendered components, ensuring consistent interaction patterns and visual language across large-scale projects. The library distinguishes itself through a robust styling architecture that utilizes design tokens and hierarchical configuration providers to propagate global settings like themes, locale, and layout direction. By employing component-level semantic mapping and runtime style injection, it decouples visual structure from logic, allowing for granular theme overrides and style isolation while maintaining a unified aesthetic. The project covers a broad capability surface, including advanced navigation utilities, data entry tools, feedback mechanisms, and structured content containers. These components are designed to handle intricate user interactions, such as hierarchical data selection, real-time suggestions, and programmatic focus management, while supporting flexible layout systems and portal-based overlay rendering for transient elements.

Hiddify is a cross-platform proxy client designed to manage secure network connections and traffic routing across desktop and mobile operating systems. It functions as a unified proxy manager, providing a centralized interface to configure and control various network proxy protocols for encrypted and private internet access. The application distinguishes itself by integrating local loopback interception, which configures the operating system network stack to route traffic through a local port for granular filtering. It also serves as a self-hosted infrastructure tool, enabling users to automate the deployment of private proxy servers on remote infrastructure through simplified command-line initialization. The system maintains consistency across environments by synchronizing remote server states through declarative configuration files and utilizing an event-driven daemon to monitor proxy health and network state changes. It employs a shared bridge layer to interact with native system APIs and firewall rules, while bundling all necessary dependencies into a singular, self-contained executable package.

This project is a scientific agent framework and workflow orchestrator designed to extend large language models with specialized tools for genomic, chemical, and biological research. It provides a system for planning research hypotheses and executing automated workflows by integrating scientific databases with dynamic code execution. The framework includes a cheminformatics modeling suite for predicting molecular bioactivity and performing virtual screening, alongside a bioinformatics analysis toolkit for processing genomic sequences and single-cell data. It also features an academic document generator capable of drafting research papers and grant proposals with LaTeX export and publication-quality visualizations. The system covers a broad range of capabilities, including clinical genomics interpretation, biological pathway mapping, and scientific literature synthesis. It further supports laboratory protocol design and the extraction of structured data from scientific documents using optical character recognition.

v2rayNG is an Android proxy client designed to route device network traffic through encrypted tunnels. It functions as a network routing engine that intercepts outgoing requests and applies custom traffic rules to manage connectivity and enhance user privacy. The application distinguishes itself by integrating a high-performance network proxy core, which enables complex protocol translation and traffic management directly on mobile devices. It utilizes local loopback and Unix-socket tunneling to redirect device-wide requests, maintaining persistent connectivity through native background service binding. Users can define granular routing policies by importing geographic data and domain-specific rules, which are processed against external binary databases to enforce network access controls. The system supports modular configuration through a structured settings interface that parses text-based files to define connection parameters and routing logic. This architecture allows for the management of custom proxy protocols and consistent policy enforcement across different network environments.

Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation history to correct errors and optimize token usage. The framework provides a broad set of capabilities for grounding model responses in factual data using vector databases, graph databases, and tabular datasets. It includes a schema-driven tool execution system that binds models to Python functions and external protocol servers, as well as a comprehensive observability suite for tracing message lineage and monitoring reasoning paths. The library provides installation guidance via import errors when optional dependencies are missing.

Sing-box is a universal proxy engine and traffic router designed to manage complex network connectivity across multiple operating systems. It functions as a configuration-driven core that intercepts system-level traffic, allowing for transparent proxying through encrypted tunnels. By normalizing diverse network protocols into a unified interface, the engine enables consistent traffic forwarding and protocol translation regardless of the underlying environment. The project distinguishes itself through a declarative configuration pipeline that validates and merges modular settings into a unified internal state before execution. It employs a rule-based traffic dispatcher that evaluates incoming packets against hierarchical criteria to determine optimal routing paths dynamically. This is complemented by an asynchronous domain name resolution pipeline, which provides granular control over how network requests are mapped and filtered, ensuring that traffic handling remains both accurate and performant. Beyond its core routing capabilities, the platform includes a comprehensive security layer for managing encrypted connections, including support for advanced handshake options and certificate validation. It also provides tools for monitoring real-time traffic and connection status, alongside flexible management of routing rule sets that can be sourced from local or remote locations. The software is designed to be installed as a background service, providing a stable and scalable infrastructure for controlled network communication.