Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
The project "Claude Skills, Agents, Commands, Hooks, Plugins, Marketplaces Collection for Claude Code" is a comprehensive repository designed to enhance the Claude Code AI development environment. It provides a rich collection of specialized AI subagents and slash commands tailored for Claude Code, which is an AI coding assistant platform. The repository aims to improve development workflows by offering domain-specific expertise and powerful automation tools. The project includes over 43 specialized subagents that act as AI experts in various domains such as development, architecture, language specialization, infrastructure, operations, quality, security, data, AI, and specialized domains. These subagents can be automatically invoked based on context or explicitly called when needed, providing targeted assistance for tasks like backend architecture, frontend development, mobile app development, GraphQL schema design, Python and Go programming, DevOps troubleshooting, cloud architecture, code review, security auditing, data science, machine learning engineering, and more. Additionally, the repository offers 39+ slash commands contributed by the community to automate tasks, manage projects, and enhance workflows. It also supports over 100 Model Context Protocol (MCP) servers that enable secure connections to databases, APIs, and external tools through Docker containers or remote SSE/HTTP endpoints. A key feature is the CLI tool that facilitates easy installation, management, and configuration of subagents, commands, and MCP servers. Users can install the CLI globally, initialize user or project configurations, add subagents or commands, browse available tools, and verify MCP server installations. The project supports different installation scopes including local, user, and project scopes for flexible team collaboration. The MCP server support includes Docker MCP for containerized local tools with strong security and verified images, and Remote MCP for cloud services with custom authentication and real-time or RESTful API connections. This enables Claude Code to connect seamlessly to a wide range of external services and tools. Overall, this project significantly extends the capabilities of Claude Code by integrating a diverse set of AI subagents, commands, and MCP servers, making it a powerful toolkit for developers leveraging the Model Context Protocol ecosystem.
https://github.com/davepoon/buildwithclaude
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
Repomix is a tool that packs entire code repositories into single, AI-friendly files optimized for feeding Large Language Models and other AI tools, with features for token counting, security, and customization.
Open-source terminal coding agent in TypeScript from the Qwen team that consumes MCP servers as tool providers, alongside subagents, skills, hooks, IDE plugins and support for OpenAI, Anthropic, Gemini and Qwen APIs.
jcode is an extremely RAM-efficient and fast AI coding agent harness for the terminal, designed to optimize multi-session workflows.
kubefwd is a command-line tool that bulk port forwards Kubernetes services to a local machine, enabling seamless local development by accessing cluster services with their original names and connection strings.
Harbor is a containerized toolkit that enables effortless deployment and management of local large language model backends, frontends, and services with integrated support for the Model Context Protocol ecosystem.
Shippie is an AI-powered code review agent that integrates Large Language Models into CI/CD pipelines and functions as a Model Context Protocol client for enhanced integration with external tools.
Oterm is a versatile terminal client for Ollama that supports Model Context Protocol tools and prompts, enabling customizable and persistent AI chat sessions across multiple platforms.