Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
kubefwd is a command-line utility designed to facilitate local development by bulk port forwarding Kubernetes services to a developer's local machine. It enables developers to access services running inside a Kubernetes cluster as if they were running locally, using the same service names and connection strings as in the cluster environment. This eliminates the need for environment-specific configuration, local service setup, or Docker Compose files, streamlining the development workflow. The tool works by discovering services within a specified Kubernetes namespace, assigning each service a unique loopback IP address (127.x.x.x), and updating the local /etc/hosts file to map service names to these IPs. It then establishes port forwards through the Kubernetes API, allowing seamless access to services by their cluster names. This approach avoids port conflicts by giving each service its own IP address and supports bulk forwarding of all services in a namespace with a single command. kubefwd features an interactive terminal user interface (TUI) that provides real-time monitoring of services, including traffic metrics and pod log streaming. It supports automatic reconnection if pods restart or connections drop, ensuring a stable development environment. Additionally, kubefwd offers a REST API for programmatic control and integrates with AI assistants through the Model Context Protocol (MCP), enhancing developer productivity. The tool is cross-platform, with installation options for macOS, Linux, Windows, and Docker. It requires kubectl configured with cluster access and root or sudo privileges to modify network settings and the hosts file. kubefwd is positioned as a superior alternative to kubectl port-forward by supporting multiple services simultaneously, unique IP allocation, automatic service name resolution, and live monitoring. Comprehensive documentation is available, covering installation, usage, configuration, advanced features, API reference, MCP integration, troubleshooting, and architectural details. kubefwd is open source under the Apache License 2.0 and actively maintained with community contributions welcomed.
https://github.com/txn2/kubefwd
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.
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.
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.