Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
News Agents is a terminal-based multi-agent news aggregation and summarization system that leverages the Model Context Protocol (MCP), Amazon Q, and tmux to fetch and summarize news articles from various sources in parallel. The system is designed to run entirely within a terminal environment, providing a unique and efficient way to monitor and digest news content. It uses Amazon Q CLI as the agent harness, MCP to parse RSS feeds as tools, and tmux for terminal splitting and monitoring, enabling multiple agents to work concurrently on different news feeds. The project architecture consists of a main agent and multiple sub-agents. The main agent reads feed URLs from a configuration file, divides them into chunks, and spawns sub-agents in separate tmux panes. Each sub-agent processes its assigned feeds by pulling down content, parsing articles, summarizing them, and saving the summaries to markdown files. The main agent oversees the progress of all sub-agents and consolidates their outputs into a comprehensive summary file. News Agents supports various news sources such as Hacker News, TechCrunch, Wall Street Journal, and Wired, with specific code modules dedicated to processing each feed type. The system demonstrates the practical application of MCP in coordinating multiple agents to perform parallel tasks efficiently. It also showcases the integration of Amazon Q and tmux to create a visually organized and interactive terminal-based workflow. Users can set up the system by installing Amazon Q CLI, configuring AWS credentials, and running the provided commands to start the main agent and sub-agents. The project includes detailed instructions and debugging tools for MCP, making it accessible for developers interested in experimenting with multi-agent systems and news aggregation. Overall, News Agents is an innovative experiment that combines modern protocols and tools to deliver a powerful terminal-based news summarization experience.
https://github.com/eugeneyan/news-agents
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
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.
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.
jcode is an extremely RAM-efficient and fast AI coding agent harness for the terminal, designed to optimize multi-session workflows.
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.
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.
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.
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.