rawq — Agent Usage Guide

What problem does it solve?

This guide teaches agents to avoid reading entire codebases by letting rawq surface the most relevant code chunks with metadata, so they stop wasting tokens on irrelevant files.

Core Features & Use Cases

• Hybrid semantic + lexical search to fuse embeddings with BM25 and adaptively weight queries for conceptual and identifier-driven intent.
• Contextual filtering and controls for languages, exclusion globs, reranking, token budgets, and daemon-backed embedding models tailored to agent workflows.
• Operational command recipes covering rawq map, search, diff, and the daemon, plus JSON/stream outputs for integration with agent pipelines.

Quick Start

Tell the agent to run rawq search "how does authentication failure handling work" ./testdata to receive ranked code snippets with file scopes and confidence scores.