Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
mcp-wp/ai-command
AI Command is a WP-CLI package that adds AI interaction to WordPress installations during development by implementing the Model Context Protocol. It plays both protocol roles. On one side it exposes its own MCP server whose tools control a WordPress site, so an assistant can act against the installation rather than only describe what to do. On the other side the command works as an MCP client, connecting to any additional MCP server the developer names, local or remote, and making those servers usable from the same WP-CLI session. This combination means a WordPress developer can drive the site and outside services through one terminal command instead of wiring separate tooling. Installation is done through the WP-CLI package manager and requires WP-CLI version 2.11 or greater, updated with wp cli update; the maintainers suggest the 2.12 nightly build for better support of recent PHP versions. The latest development version is installed with wp package install mcp-wp/ai-command:dev-main. At present the package also requires the target WordPress site to have the AI Services plugin installed, which supplies the model access the command builds on. The project is written in PHP, carries code coverage reporting through Codecov, and keeps its full documentation on a separate site at mcp-wp.github.io rather than in the repository README, which instead covers installation and the contribution process. The README points contributors at the WordPress CLI handbook for bug reports and pull requests and asks that new features be discussed in an issue first. It belongs to the mcp-wp organisation, which groups several efforts to connect WordPress to the Model Context Protocol, and is aimed at WordPress developers who already live in WP-CLI.
https://github.com/mcp-wp/ai-command
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.