Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
jonigl/mcp-client-for-ollama
The project "MCP Client for Ollama" (ollmcp) is a sophisticated text-based user interface (TUI) client designed for developers to interact with Model Context Protocol (MCP) servers using Ollama, a local large language model (LLM) platform. It enables seamless connection to multiple MCP servers simultaneously, supporting various transport types such as STDIO, SSE, and Streamable HTTP. The client offers a rich, interactive terminal interface with modern styling, allowing users to manage tools, models, and server connections in real time without requiring coding skills. Key features include streaming responses for real-time model output viewing, advanced tool management with the ability to enable or disable specific tools or entire servers during chat sessions, and a Human-in-the-Loop (HIL) mode that allows users to review and approve tool executions for enhanced control and safety. The client supports advanced model configuration with over 15 parameters, including context window size, temperature, sampling, and repetition control, as well as system prompt customization to control model behavior and persona. Additional capabilities include context window control for handling longer conversations, enhanced tool display with JSON syntax highlighting, context management for conversation memory retention, and a thinking mode that provides visible thought processes for supported models. The client supports cross-language MCP servers in Python and JavaScript, auto-discovers existing MCP server configurations from Claude, and allows dynamic model switching without restarting. The client also features configuration persistence for saving and loading preferences, hot-reloading of MCP servers during development, fuzzy autocomplete for commands, dynamic prompts showing current model and enabled tools, detailed performance metrics after each query, and automatic update notifications. It is built with a modern CLI using Typer for grouped options, shell autocompletion, and improved help output. The project requires Python 3.10+, Ollama running locally, and the UV package manager. It is aimed at developers working with local LLMs who want a powerful, user-friendly tool to streamline workflows involving MCP servers and advanced LLM tool use.
https://github.com/jonigl/mcp-client-for-ollama
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.