Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
langwatch/better-agents
Better Agents is a comprehensive CLI tool and a set of standards designed to enhance the development of AI agents. It aims to supercharge coding assistants such as Kilocode, Claude Code, and Cursor by making them experts in various agent frameworks like Agno, Mastra, and LangGraph, incorporating industry best practices for agent building. The project provides a structured approach to agent development, ensuring readiness for production through a well-defined project structure and guidelines documented in AGENTS.md. This structure includes directories for the agent code, end-to-end scenario tests, evaluation notebooks, versioned prompt files for team collaboration, and configuration files for Model Context Protocol (MCP) server setup. The tool emphasizes rigorous testing and evaluation, using Scenario agent tests to verify agent behavior and evaluation notebooks to measure prompt performance. It supports versioning of prompts to facilitate collaboration among teams and is instrumented for full observability, enhancing maintainability and reliability. The inclusion of a .mcp.json configuration file integrates MCP standards, enabling the coding assistant to become proficient in the chosen framework and in writing Scenario tests. Better Agents also provides a guided CLI experience for initializing new projects, selecting programming languages, agent frameworks, coding assistants, LLM providers, and managing API keys. It supports Node.js environments and requires API keys for LangWatch and the chosen LLM provider. The project is well-documented with guides on getting started, project structure, features, usage, and contribution, making it accessible for developers aiming to build robust AI agents. Overall, Better Agents is a valuable resource for developers looking to implement best practices in AI agent development, leveraging MCP standards to ensure quality, collaboration, and maintainability in their projects.
https://github.com/langwatch/better-agents
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.