Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
av/harbor
Harbor is a comprehensive containerized toolkit designed to simplify the deployment and management of local large language model (LLM) backends, frontends, and related services. It integrates seamlessly with the Model Context Protocol (MCP) ecosystem, providing users with a powerful and flexible environment for running and interacting with LLMs locally. The project includes a command-line interface (CLI) and a companion application that together facilitate easy setup and operation of various LLM services. Harbor supports a wide range of LLM inference engines, including popular and cutting-edge options such as Ollama, llama.cpp, vLLM, and others. Users can start these backends with minimal configuration, often with a single command, making it accessible for both beginners and advanced users. The toolkit also offers extensive support for frontends like Open WebUI, ComfyUI, LibreChat, and more, enabling rich user interactions with the models. One of Harbor's standout features is its integration with the MCP ecosystem, allowing users to manage MCPs through a convenient web UI and connect them to various frontends. This enhances the extensibility and interoperability of LLM workflows. Additionally, Harbor includes services for local web retrieval-augmented generation (RAG), deep research, image generation, voice chat capabilities, and LLM-based workflow automation. The project emphasizes ease of use with features like configuration profiles for different scenarios, command history for quick access to previous commands, and the ability to export setups into standalone Docker Compose files. Harbor also provides a built-in tunneling service to expose local services to the internet securely, with caution advised. Overall, Harbor is a versatile and user-friendly platform that empowers users to deploy, manage, and extend local LLM environments efficiently, leveraging the Model Context Protocol for enhanced functionality and integration.
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.
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.
ggozad/oterm
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.