A coding agent toolkit that transforms LLMs into coding assistants capable of working directly on your codebase with semantic code retrieval and editing tools, providing IDE-like capabilities without requiring API subscriptions.
Provides semantic code intelligence tools (search, structural views) and a workspace TUI interface for LLM agents to efficiently navigate codebases, manage context, and maintain architectural patterns across Python, Java, C++, and Perl projects.
A coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Provides Cursor-like code intelligence using tools like ripgrep, ctags, and tree-sitter to help LLMs explore and understand entire codebases. It implements a structured, phase-gated workflow to ensure high-confidence code modifications and eliminate hallucinations.
Enables AI agents to perform hybrid code search, get explanations, analyze relations and impacts, retrieve context packs, and generate documentation across ~45 languages via 17 MCP tools, all powered by a local vector database and LLM.
