Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
ggozad/oterm
Oterm is a versatile terminal client designed for Ollama that supports Model Context Protocol (MCP) tools and prompts, enabling users to have customizable and persistent chat sessions with AI models across multiple platforms including Linux, MacOS, and Windows. It offers an intuitive and simple terminal user interface that requires no additional servers or frontends, allowing users to start it directly from their terminal by typing `oterm`. The client supports multiple persistent chat sessions, which are stored along with system prompt and parameter customizations in an SQLite database. Users can utilize any models they have pulled in Ollama or their own custom models, with easy customization options for the model's system prompt and parameters. Oterm also supports integration with MCP tools to provide external information to the AI models, enhancing the interaction capabilities. Recent updates include support for "thinking" mode for compatible models, streaming with tools, improved message UI styling, MCP sampling, and support for streamable HTTP and WebSocket transports for MCP servers. The project is well-documented with installation instructions and usage guides available online. It also supports multiple themes for interface customization and includes features like image selection within conversations. Oterm is distributed under the MIT License and is available for installation via Homebrew and other package managers. Overall, Oterm provides a powerful and flexible terminal-based interface for interacting with AI models using the Model Context Protocol, making it a valuable tool for developers and users who prefer terminal environments for AI chat sessions and tool integrations.
https://github.com/ggozad/oterm
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.