Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
gotalab/skillport
SkillPort is a comprehensive SkillOps toolkit designed to bring Agent Skills to any AI agent or coding agent through a Command Line Interface (CLI) or Model Context Protocol (MCP). It enables users to manage, validate, and deliver AI agent skills at scale, supporting seamless integration and efficient skill management. The project is fully compatible with the Agent Skills specification, ensuring standardized skill handling. SkillPort addresses several challenges faced by AI developers and users. It supports coding agents that lack native skill support by serving skills via MCP or CLI. It offers a MCP server, CLI tools, and a Python library for building custom AI agents. The toolkit is optimized for environments with numerous skills, employing a search-first loading pattern inspired by Anthropic's Tool Search Tool to efficiently find and load the right skill on demand, reducing context load and improving accuracy. Key features include skill validation against the Agent Skills specification to catch errors before deployment, full lifecycle skill management from various sources including GitHub and local files, and metadata management for automation and consistency. SkillPort also provides an MCP server that supports clients without native Agent Skills support, enabling search and on-demand loading of skills. The project supports two main modes for delivering skills: CLI mode for agents with shell access and MCP mode for MCP-compatible clients. CLI mode allows agents to discover and load skills via generated documentation and shell commands, while MCP mode involves running a dedicated MCP server integrated into the client's configuration. SkillPort also supports organizing skills with categories and tags, enabling filtering and exposure of different skill sets to different agents. Configuration options allow customization of skill directories, enabled categories, and core skill behaviors. The project includes guides for creating new skills and supports various skill sources, including official Anthropic skills, community collections, and specialized scientific skills. Overall, SkillPort is a powerful and flexible solution for managing and deploying AI agent skills efficiently across diverse environments and clients.
https://github.com/gotalab/skillport
Also in CLI Tools
yamadashy/repomix
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.
QwenLM/qwen-code
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.
1jehuang/jcode
jcode is an extremely RAM-efficient and fast AI coding agent harness for the terminal, designed to optimize multi-session workflows.
txn2/kubefwd
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.
davepoon/buildwithclaude
A comprehensive collection of specialized AI subagents, slash commands, and MCP server integrations designed to enhance the Claude Code AI development environment with powerful automation and domain-specific expertise.
av/harbor
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.
mattzcarey/shippie
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.