Hybrid Search

Keyword search misses everything you paraphrase. Vector search misses the exact error code. GNO runs both, fuses them with reciprocal rank fusion, and reranks with a cross-encoder so the best passage surfaces first, across 15,000+ documents in under a second. When you want to know why a result ranked where it did, --explain shows the stage timings and per-result score components.

Install GNO Read the docs

Use cases: Teams tired of searching across folders, tools, and browser tabs; Researchers mixing exact references with open-ended questions; AI workflows that need accurate retrieval from your own documents

What it gives you

Keyword search that handles exact terms, quoted phrases, and technical names
Semantic search that understands what you mean, not just what you typed
Automatic fusion of both approaches for the best results
Default seed-scoped graph expansion brings in one-hop linked evidence after initial fusion
Reranking that pushes the most relevant passage to the top
Query expansion that finds related terms you didn’t think to search for
Smart confidence detection — skips expansion when the match is already strong
Tag, date, category, author, and language filters apply when graph expansion is enabled
Clickable terminal links for command-line search workflows
Configurable speed: fast, balanced, or thorough modes