Retrieve file metadata like size and line count without accessing file contents. Helps determine optimal reading strategies for large files by analyzing file characteristics first.
Enables simultaneous reading of multiple files in allowed directories, returning content with file paths. Ideal for efficient analysis or comparison. Handles failed reads without interrupting the entire operation.
Analyzes files or directories to list top-level code symbols (name_path, kind), providing a high-level understanding for targeted reading, searching, or editing operations. Returns a JSON object with symbol details.
Generate a web application directory with starter files for quick setup. Includes a utility for API calls via Goose. Customize content or replace with existing HTML, CSS, or JS files.
Enables controlling CAD software (AutoCAD, GstarCAD, ZWCAD) through natural language instructions, allowing users to create and modify drawings without manually operating the CAD interface.
Enables AI agents to safely explore directories, read files, search content by pattern or filename, and edit files with checksum verification and dry-run preview within sandboxed filesystem access.
A local vector database system that provides LLM coding agents with fast, efficient semantic search capabilities for software projects via the Message Control Protocol.