Install GNO

Getting Started

Quickstart

Go from a local folder to hybrid search, browsing, and AI answers in under five minutes.

Get from a local folder to hybrid search, workspace browsing, and AI answers in under five minutes. This guide assumes you already installed GNO — if not, start with installation.

1. Initialize with your notes

Point GNO at a folder of documents. A folder can be Markdown, PDF, Office docs, plain text, or a mix.

gno init ~/notes --name notes
gno init ~/Documents --name docs --pattern "**/*.md"

Prefer a guided UI? Start gno serve, open http://localhost:3000, and use the first-run checklist to add a folder, pick a preset, and start indexing with zero CLI commands.

2. Index your documents

gno index

Runs both BM25 (keyword) and vector indexing. GNO handles Markdown, PDF, DOCX, XLSX, PPTX, and plain text automatically.

On first run, GNO may download local models (embedding ~500MB, optional rerank/gen models +700MB–1.2GB). Subsequent runs use the cache. To skip startup downloads, set GNO_NO_AUTO_DOWNLOAD=1 and run gno models pull explicitly.

gno ls

GNO exposes three search modes for different trade-offs between speed and depth.

# Full-text (BM25) — instant, ~5–20ms
gno search "project deadlines"

# Vector similarity — semantic, ~0.5s
gno vsearch "how to handle errors"

# Hybrid — both pipelines + reranking, best results
gno query "authentication best practices"

4. Get AI answers

gno ask "what is the main goal of project X" --answer

Runs the hybrid pipeline, feeds the top matches to a local LLM, and returns a cited answer. Everything runs on your machine.

Output formats

For scripting, every command supports machine-readable output:

gno search "important" --json
gno search "important" --files
gno search "important" --csv
gno search "important" --md

Next steps