Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
Davidyz/VectorCode
VectorCode is a sophisticated code repository indexing tool designed to enhance the capabilities of coding large language models (LLMs) by injecting task-relevant context from codebases. It integrates with the Model Context Protocol (MCP) to improve search and retrieval functionalities, making it easier for developers to build better prompts for their coding LLMs. The tool indexes code repositories and provides detailed information about the codebase, which helps in reducing hallucinations and improving the quality of model outputs, especially for closed-source projects, lesser-known projects, or cutting-edge developments that are not widely available. The project includes a command-line interface (CLI) tool and a Neovim plugin that offers a set of APIs to build or enhance AI plugins and integrations with popular Neovim plugins. VectorCode supports advanced features such as semantic and syntax-based chunking of code using tree-sitter, metadata addition for files, configurable chunk sizes, and smarter document selection from query results. It respects .gitignore files and supports project-root anchors like .git or a custom .vectorcode.json for automatic project root detection. VectorCode is still in beta and undergoing rapid development, with ongoing improvements such as remote Chromadb support, query rewriting, and enhanced authentication. It also supports asynchronous caching, persistent clients, and joint search capabilities through integration with codecompanion.nvim and MCP. The project follows an adapted semantic versioning system to manage breaking and non-breaking changes effectively. Overall, VectorCode is a powerful tool for developers looking to leverage LLMs more effectively by providing enriched, context-aware codebase information, thereby improving coding assistance and AI-driven development workflows.
https://github.com/Davidyz/VectorCode
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.