Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
QwenLM/qwen-code
Qwen Code is an open-source coding agent that runs in the terminal, written in TypeScript and published by the Qwen team. It installs through a shell installer, npm or Homebrew and requires Node.js 22 or newer. MCP is a documented first-class feature, so the agent loads external MCP servers as tool providers next to its built-in capabilities, which include automatic memory, automatic skills, subagents, agent teams, hooks, plan mode, LSP integration, an auto mode, sandboxing, git worktrees and computer use for desktop automation. Built-in skills cover review, batch, loop and bugfix workflows. The project positions itself against Claude Code and documents a feature comparison table. Qwen Code is multi-protocol: it talks to OpenAI, Anthropic, Gemini and Qwen APIs as well as any third-party provider or local runtime such as Ollama or vLLM, and the provider can be switched at runtime. Several execution modes are offered: an interactive terminal UI with file references and slash commands, a headless mode for scripts and continuous integration, IDE plugins for VS Code, Zed and JetBrains, a desktop application for macOS, Windows and Linux, an experimental daemon mode that serves one shared agent session over HTTP and server-sent events using ACP so several clients attach to the same agent, SDKs for TypeScript, Python and Java, and an instant-messaging bot mode for Telegram, DingTalk, WeChat and Feishu. An agent arena feature runs several models head to head on the same task. Both the framework and the Qwen models are open source. The project suits developers who want a terminal-based coding assistant that can consume MCP servers and is not tied to one model vendor.
https://github.com/QwenLM/qwen-code
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.
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.
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.