rawq
Semantic and lexical code search for faster context retrieval
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install rawq?▼
Run `npx skills add auyelbekov/rawq --all -g -y` in your terminal to install this skill globally.
What does rawq do?▼
rawq is a context retrieval engine that searches codebases using combined semantic and lexical matching. It returns only the relevant code chunks with file paths, line numbers, and confidence scores instead of whole files.
How does rawq save tokens for coding agents?▼
Instead of reading dozens of full files, rawq returns 5-10 ranked code chunks for a query. This sharply reduces context size and speeds up code understanding.
Does rawq work offline?▼
Yes. After the initial model download, rawq runs fully offline using local ONNX inference with optional GPU acceleration on Windows, Linux, and macOS.
Which programming languages does rawq support?▼
rawq supports 16 languages via tree-sitter, including Rust, Python, TypeScript, Go, and Java, plus a universal fallback that indexes any text file.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core