Your Local Second Brain — Index, search, and synthesize your entire digital life.

GNO is a local knowledge engine for privacy-conscious developers and AI agents. Index your notes, code, PDFs, and Office docs. Get hybrid search (BM25 + vector + reranking) and AI-powered answers—all running 100% on your machine.

• Quick Start
• Installation
• Search Modes
• Web UI
• REST API
• Agent Integration
• How It Works
• Features
• Local Models
• Architecture
• Development

gno init ~/notes --name notes    # Point at your docs
gno index                        # Build search index
gno query "auth best practices"  # Hybrid search
gno ask "summarize the API" --answer  # AI answer with citations

Requires Bun >= 1.0.0.

bun install -g @gmickel/gno

macOS: Vector search requires Homebrew SQLite:

brew install sqlite3

Verify everything works:

gno doctor

One command to add GNO to your AI assistant:

gno mcp install                      # Claude Desktop (default)
gno mcp install --target cursor      # Cursor
gno mcp install --target claude-code # Claude Code CLI
gno mcp install --target zed         # Zed
gno mcp install --target windsurf    # Windsurf
gno mcp install --target codex       # OpenAI Codex CLI
gno mcp install --target opencode    # OpenCode
gno mcp install --target amp         # Amp
gno mcp install --target lmstudio    # LM Studio
gno mcp install --target librechat   # LibreChat

Check status: gno mcp status

Skills integrate via CLI—no MCP overhead:

gno skill install --scope user       # User-wide
gno skill install --target codex     # Codex
gno skill install --target all       # Both Claude + Codex

Full setup guide: MCP Integration · CLI Reference

BM25 indexes full documents (not chunks) with Snowball stemming—"running" matches "run". Vector embeds chunks with document titles for context awareness.

gno search "handleAuth"              # Find exact matches
gno vsearch "error handling patterns" # Semantic similarity
gno query "database optimization"    # Full pipeline
gno ask "what did we decide" --answer # AI synthesis

Output formats: --json, --files, --csv, --md, --xml

Visual dashboard for search, browsing, and AI answers—right in your browser.

gno serve                    # Start on port 3000
gno serve --port 8080        # Custom port

Open http://localhost:3000 to:

• Search — BM25, vector, or hybrid modes with visual results
• Browse — Paginated document list, filter by collection
• Ask — AI-powered Q&A with citations
• Switch presets — Change models live without restart

Everything runs locally. No cloud, no accounts, no data leaving your machine.

Detailed docs: Web UI Guide

Programmatic access to all GNO features via HTTP.

# Hybrid search
curl -X POST http://localhost:3000/api/query \
  -H "Content-Type: application/json" \
  -d '{"query": "authentication patterns", "limit": 10}'

# AI answer
curl -X POST http://localhost:3000/api/ask \
  -H "Content-Type: application/json" \
  -d '{"query": "What is our deployment process?"}'

# Index status
curl http://localhost:3000/api/status

No authentication. No rate limits. Build custom tools, automate workflows, integrate with any language.

Full reference: API Documentation

GNO exposes 6 tools via Model Context Protocol:

Design: MCP tools are retrieval-only. Your AI assistant (Claude, GPT-4) synthesizes answers from retrieved context—best retrieval (GNO) + best reasoning (your LLM).

Skills add GNO search to Claude Code/Codex without MCP protocol overhead:

gno skill install --scope user

Then ask your agent: "Search my notes for the auth discussion"

Detailed docs: MCP Integration · Use Cases

graph TD
    A[User Query] --> B(Query Expansion)
    B --> C{Lexical Variants}
    B --> D{Semantic Variants}
    B --> E{HyDE Passage}

    C --> G(BM25 Search)
    D --> H(Vector Search)
    E --> H
    A --> G
    A --> H

    G --> I(Ranked Results)
    H --> J(Ranked Results)
    I --> K{RRF Fusion}
    J --> K

    K --> L(Top 20 Candidates)
    L --> M(Cross-Encoder Rerank)
    M --> N[Final Results]

0. Strong Signal Check — Skip expansion if BM25 has confident match (saves 1-3s)
1. Query Expansion — LLM generates lexical variants, semantic rephrases, and a HyDE passage
2. Parallel Retrieval — Document-level BM25 + chunk-level vector search on all variants
3. Fusion — RRF with 2× weight for original query, tiered bonus for top ranks
4. Reranking — Qwen3-Reranker scores full documents (32K context), blended with fusion

Deep dive: How Search Works

Models auto-download on first use to ~/.cache/gno/models/.

gno models use balanced
gno models pull --all

Configuration: Model Setup

┌─────────────────────────────────────────────────┐
│            GNO CLI / MCP / Web UI / API         │
├─────────────────────────────────────────────────┤
│  Ports: Converter, Store, Embedding, Rerank    │
├─────────────────────────────────────────────────┤
│  Adapters: SQLite, FTS5, sqlite-vec, llama-cpp │
├─────────────────────────────────────────────────┤
│  Core: Identity, Mirrors, Chunking, Retrieval  │
└─────────────────────────────────────────────────┘

Details: Architecture

git clone https://github.com/gmickel/gno.git && cd gno
bun install
bun test
bun run lint && bun run typecheck

Contributing: CONTRIBUTING.md

MIT

made with ❤️ by @gmickel