Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
sigoden/llm-functions
LLM Functions is a versatile platform designed to simplify the creation and integration of custom Large Language Model (LLM) tools and agents. It leverages function calling capabilities to connect LLMs directly with custom code written in popular scripting languages such as Bash, JavaScript, and Python. This approach eliminates the need for complex integrations, allowing users to execute system commands, process data, and interact with APIs seamlessly. The platform supports the Model Context Protocol (MCP), enhancing interoperability between different LLM tools and agents. The project provides a straightforward workflow for building tools and agents. Users create tool scripts and list them in a tools file, similarly defining agents with their configurations. The platform uses the argc command-line framework to build and manage these tools and agents, ensuring they are ready for use with environment variables and dependencies properly set. AIChat is currently the primary CLI tool supporting LLM Functions, enabling users to interact with the tools and agents through simple commands. LLM Functions also offers detailed guidance on writing custom tools and agents. Tools are essentially functions with JSON declarations auto-generated from comments, making it easy to develop in familiar languages. Agents combine prompts, tools, and documents to create sophisticated AI assistants, with configurations defined in YAML files. The project includes examples and showcases to help users get started quickly. Additionally, the platform includes components for MCP server and bridge implementations, allowing LLM Functions tools and agents to be used through MCP and enabling external MCP tools to integrate with LLM Functions. Comprehensive documentation and guides are provided to assist users in leveraging the full capabilities of the platform. Licensed under MIT, LLM Functions is an open-source project fostering innovation in LLM tool and agent development.
https://github.com/sigoden/llm-functions
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.