Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
JohanLi233/Viby
Viby is a terminal-based AI agent designed to provide intelligent, context-aware assistance for a wide range of tasks including coding, shell command generation, information retrieval, and creative content creation. It leverages the Model Context Protocol (MCP) to extend its capabilities by integrating with MCP servers and discovering relevant tools automatically. Viby supports natural multi-turn conversations, allowing users to interact with it in a conversational manner to solve complex problems or get quick answers. It can generate optimized shell commands based on user queries and even process piped input from other commands, such as generating commit messages from git diffs or analyzing code files. The project supports multiple AI models, enabling users to select different models for various tasks, such as using a 'think' model for complex analysis or a 'fast' model for quick responses. Viby also features enhanced history management, allowing users to search, export, and manage their interaction history. It supports semantic search through command embeddings, which helps in accurate tool selection by embedding vectors. The interface is multilingual, supporting both English and Chinese with easy language switching. Installation is straightforward via PyPI or the UV package manager, and the tool integrates well with common shells like Bash, Zsh, and Fish, including keyboard shortcuts for quick access. Configuration is flexible, with options to set API endpoints, models, MCP tools, and embedding models through a configuration wizard or config files. Overall, Viby is a versatile AI assistant that harnesses the power of the Model Context Protocol to provide a seamless and powerful terminal-based experience for developers and users needing intelligent assistance with coding, shell commands, and information retrieval tasks.
https://github.com/JohanLi233/Viby
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.