GNO
Local search for your second brain
Your 15,000 documents of notes, journals, and reference material—finally searchable. Hybrid search combines keywords and semantics. Everything runs locally.
BM25. Vectors. HyDE. Reranking. One CLI that unlocks your second brain.
THE PROBLEM
You built a second brain. 15,000 files of accumulated knowledge. But when you ask your AI assistant about it:
- ×grep is fast but dumb—misses conceptual matches
- ×Obsidian MCP servers return irrelevant results
- ×Cloud search tools send your data to external servers
- ×AI assistants hallucinate instead of citing your actual notes
GNO gives your AI long-term memory over your local files.
COMMANDS
gno queryHybrid search (BM25 + vector + reranking)
gno askSearch + AI-generated answer
gno serveStart Web UI on localhost:3000
gno graphKnowledge graph visualization
gno linksOutgoing wiki/markdown links
gno backlinksDocuments linking TO a doc
gno similarSemantically related documents
gno mcp installAdd to Claude, Cursor, Zed, etc.
SEARCH PIPELINE
gno query worksThe hybrid search pipeline combines multiple retrieval strategies for best-in-class results:
Query Expansion
LLM generates keyword variants, semantic variants, and HyDE passage
Parallel Search
BM25 and vector searches run simultaneously on all variants
RRF Fusion
Reciprocal Rank Fusion merges results (k=60)
Reranking
Cross-encoder rescores top 20 for final ordering
SEARCH MODES
gno searchFull-text search via SQLite FTS5. Best for exact terms and code.
gno search "authentication JWT"gno vsearchEmbedding-based search via sqlite-vec. Finds conceptual matches.
gno vsearch "how to protect my app"gno queryBM25 + vector + HyDE expansion + cross-encoder reranking.
gno query "best practices for error handling"gno askRetrieval-augmented generation. Get a cited answer from your docs.
gno ask "summarize the API design" --answerKNOWLEDGE GRAPH
v0.13gno graphInteractive force-directed visualization of document connections. Wiki links, markdown links, and semantic similarity edges (golden lines) rendered as a navigable graph.
Wiki [[links]]
Markdown [links]()
Similarity edges
gno graph --collection notes --similarity/graph Web UI page/api/graph RESTgno_graph MCP toolNOTE LINKING
v0.12Link documents with [[wiki links]]. See outgoing links, backlinks, and AI-powered related notes.
gno linksOutgoing links from docgno backlinksDocs linking TO this docgno similarSemantically related docsTAG SYSTEM
v0.12Frontmatter tags with hierarchical paths like project/alpha. Filter any search by tags.
gno query "auth" --tags-any work,urgentgno query "deploy" --tags-all project/alpha,reviewed--tags-any = OR, --tags-all = AND
WEB UI & REST API
gno serveNewCreate, edit, search, and browse documents. AI answers with citations. Collections management. Everything keyboard-first.
Keyboard Shortcuts
gno serve # → localhost:3000/api/*RESTHTTP API for documents, collections, search, and AI answers. Build custom integrations or automate workflows.
/api/docs— Documents/api/query— Hybrid search/api/ask— AI answers/api/collections— Managecurl -X POST localhost:3000/api/docs
-d '{"title": "New note", ...}'Localhost only — Binds to 127.0.0.1 with CSP headers and CORS protection. Use Tailscale Serve or Cloudflare Tunnel for secure remote access.
FEATURES
Interactive force-directed visualization. Wiki links, markdown links, and similarity edges rendered as navigable constellation.
Wiki-style [[links]], backlinks panel, and AI-powered related notes. Cross-collection navigation.
Frontmatter tags with hierarchical paths. Filter searches with --tags-any/--tags-all.
Split-view markdown editor with live preview, auto-save, and keyboard shortcuts (⌘B/I/K/S).
Create, edit, search, and browse documents. Manage collections. AI Q&A with citations.
Full CRUD for documents + collections. Search, sync, AI answers. Build custom tools.
BM25 + vector + cross-encoder reranking. RRF fusion combines results for best accuracy.
One command to add GNO to Claude, Cursor, Zed, Windsurf, Codex, and 5+ more tools.
⌘N capture, ⌘K search, ⌘/ shortcuts. Full editing without touching the mouse.
AI INTEGRATION
GNO integrates with AI tools via MCP (Model Context Protocol) or CLI skills. Your assistant can search and cite your local documents.
gno mcp installgno mcp install --target cursorgno mcp install --target zedgno mcp install --target windsurfgno mcp install --target lmstudiogno mcp install --target librechatgno skill installgno skill install --target codexgno skill install --target opencodegno skill install --target ampExample prompts for your AI
"Search my notes for the project roadmap and summarize Q4 goals"
"Find what I wrote about database migrations last month"
"Have I worked on something like this before?"
INSTALLATION
bun install -g @gmickel/gnogno init ~/notes --name notesgno indexgno collection add ~/Documents/Obsidian --name vaultgno collection add ~/code --name code --exclude node_modulesThen run gno index to build index + embeddings.
MODELS — Choose preset: slim (~1GB), balanced (~2GB), or quality (~2.5GB). Run gno models use <preset> to switch.
- ›Bun — Runtime + package manager + fullstack dev server
- ›SQLite + FTS5 — BM25 full-text search
- ›sqlite-vec — Vector KNN search
- ›node-llama-cpp — Local GGUF models
- ›React — Web UI SPA
- ›Personal notes — Obsidian, Notion exports, journals
- ›Code documentation — ADRs, RFCs, specs
- ›Research — PDFs, papers, literature reviews
- ›Legal docs — Contracts, policies, compliance
- ›Team knowledge — Wikis, runbooks, shared docs