$ show monkesearch/monkeSearch
monkeSearch is a macOS-native file search tool that uses a local LLM to parse natural language queries into structured search parameters, then executes Spotlight searches via PyObjC. The system breaks queries into file type indicators (with specificity detection), temporal expressions, and residual keywords, converting them to NSPredicates using UTIs for file type matching and date comparisons for temporal filtering. It features a clean separation between LLM-based query parsing (query_gen.py) and Spotlight execution (parser.py), with the former being particularly well-engineered for reuse. The tool is designed for offline, agentic use with no cloud dependencies, targeting low-resource environments.
The LLM identified 1 files worth highlighting for reuse:
This module provides a reusable LLM client and prompt engineering framework for extracting structured data from natural language queries. It defines a JSON schema for expected output and uses few-shot prompting to guide the LLM to produce valid JSON. The component is decoupled from specific search logic and can be adapted to other domains by changing the schema and prompt. It demonstrates skill in prompt engineering and schema-guided generation, making it a valuable reusable component for LLM-based applications.