Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
yamadashy/repomix
Repomix is a tool designed to pack entire code repositories into single, AI-friendly files optimized for feeding Large Language Models (LLMs) and other AI tools. It supports token counting, security checks, and customization options to tailor the output. The tool respects .gitignore and other git exclusion files, ensuring that unwanted files are not included. It incorporates Secretlint for security to detect and prevent the inclusion of sensitive information. Repomix also offers a compression feature using Tree-sitter to extract key code elements, reducing token count while preserving the code structure. Users can run Repomix via a simple CLI command, use it online through the repomix.com website, or access it via browser extensions for Chrome and Firefox. Additionally, there is a community-maintained VSCode extension that allows running Repomix directly inside the editor. The tool is designed to facilitate feeding codebases to AI assistants like ChatGPT, Claude, DeepSeek, and others, enabling AI-assisted code review, refactoring, and generation. Repomix outputs a single file containing the entire repository in an AI-friendly format, which can be used to prompt AI models for various code-related tasks. The project has been nominated for the Powered by AI category at the JSNation Open Source Awards 2025, highlighting its innovation in AI tooling for developers. It supports multiple output formats including XML, Markdown, and plain text, and provides instant token count estimation. The tool is open source and actively maintained, with a supportive community on Discord for discussion and help. Overall, Repomix streamlines the process of preparing codebases for AI consumption, enhancing developer productivity and AI integration workflows.
https://github.com/yamadashy/repomix
Also in CLI Tools
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.
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.