GNO

Search finds. GNO proves.

A local knowledge engine for your notes, code, PDFs, and Office docs. Hybrid search, a browsable workspace with graph and editor, CLI, SDK, REST API, and MCP for ten AI clients — plus retrieval that can show its work.

bun install -g @gmickel/gno
gno setup ~/notes --name notes     # returns only after retrieval actually works
gno mcp install --target cursor    # or claude-code, claude-desktop, zed, ...

What you get

One local index across everything you have. Markdown, PDFs, Office documents, plain text, source code, and portable mail, calendar and transcript exports. Point it at a folder that mixes all of them and it handles the mix.

Three ways to search it. Keyword (BM25), semantic (vector), and hybrid — fused, reranked, and explainable, with structured intent controls and metadata filters. Ask for "how we handle retries" and find the paragraph about exponential backoff that never uses the word.

A workspace, not a search box. Cross-collection folder tree, per-tab browse context, a markdown editor, provenance-carrying quick capture, and a navigable knowledge graph.

Answers with citations. Ask a question in natural language and get an answer built from your own documents, with citations that resolve to the source passage.

Six interfaces on one index. A fast CLI, a web UI, a REST API, a TypeScript SDK, an MCP server, and a headless daemon — plus one-command install into ten agent clients. Nothing drifts between them.

Optional hosted publishing at gno.sh when a slice needs a URL.

No GPU required, no account required, no telemetry. Free and MIT licensed.

Why not just another local RAG tool

The above is most of what people use day to day. Beyond it, four things here are different, and each one is measurable rather than adjectival:

Everything runs on your machine. Zero telemetry. The three network boundaries are explicit: downloading a model, configuring an HTTP inference endpoint, and uploading an artifact you exported for publishing.

And the receipts ship too. Every benchmark behind these numbers is committed to the repository against a pinned corpus, with its limitations stated alongside the result, so you can replay it rather than take it on trust.

Use it when

• your knowledge is split across Markdown, code, PDFs, Office files, and exported mail or transcripts
• you want one retrieval layer for the CLI, the browser, MCP, and a Bun/TypeScript SDK
• you want your coding agent to have a real memory without shipping your docs to a cloud API
• you need to prove, later, which bytes supported a conclusion

Two minutes, end to end

# Install
bun install -g @gmickel/gno

# Activate a folder. Returns only after BM25 proves an exact corpus-derived hit;
# semantic embedding continues independently in the background.
gno setup ~/notes --name notes

# Add more sources
gno collection add ~/work/docs --name work-docs --pattern "**/*.{md,pdf,docx}"
gno collection add ~/work/gno/src --name gno-code --pattern "**/*.{ts,tsx,js,jsx}"

# Tell retrieval what each collection is for
gno context add "work-docs:" "Architecture docs, runbooks, RFCs, meeting notes"

gno update --yes   # sync
gno embed          # embed when you want semantic retrieval

# Pick the search that fits the question
gno search "DEC-0054"                            # exact identifier
gno vsearch "retry failed jobs with backoff"     # natural language
gno query "JWT refresh token rotation" --explain # hybrid, with score traces

# Compile checkable evidence for a goal, then re-check it later
gno context build "why we dropped the queue rewrite" \
  --collection work-docs --budget 12000 --json --output capsule.json
gno context verify capsule.json

# Generate only what that evidence supports
gno ask "why did we drop the queue rewrite" --verify --show-sources

# Run the workspace (pick one — not both against the same index)
gno serve            # browser/desktop Web UI
gno daemon --detach  # headless indexing + resident MCP gateway

[!TIP] gno.sh/publish is live. Turn any GNO note or collection into a reader-first URL — editorial typography, scoped search, and four visibility modes from public to encrypted-before-upload. See the reader →

ClawdHub: GNO skills bundled for Clawdbot — clawdhub.com/gmickel/gno

Contents

Start here · Quick Start · Installation · Agent Integration · Search Modes

Surfaces · Web UI · REST API · SDK · Daemon Mode · Publish to gno.sh

Under the hood · How It Works · Features · Local Models · Fine-Tuned Models · Architecture · Development

Deep dives on gno.sh · Context Capsules · Knowledge Delta · Retrieval learning · Project profiles · Egress policies · Export adapters

What's New

Current release: v1.31.0 — see CHANGELOG.md

Full release history: CHANGELOG.md

• Trustworthy local context compiler: deterministic Context Capsules replace repeated agent query → get → multi-get orchestration with one bounded, citation-complete evidence handoff. The promoted benchmark retained 100% completion accuracy while reducing retrieval calls by 48.94% and model-visible context by 44.12%, with 100% exact claim-span linkage.
• Verified answers and private quality learning: opt-in verified Ask checks every substantive claim against one closed Capsule and abstains below complete support. Local traces, explicit judgments, content-free qrels export, and read-only replay turn real misses into regression evidence without automatic personalization.
• Project-aware retrieval affinity: trusted local CLI searches can use the current workspace or explicit --project-root values as a transparent, explainable +0.03 soft ranking signal. Filters remain hard, and untrusted SDK, REST, MCP, and Web hints never probe paths or affect ranking.
• Retrieval-proven activation: gno status, gno doctor, REST, and the Web/Desktop dashboard now share a per-folder lexical retrieval proof. Local semantic readiness remains independent, and installed MCP targets can run an explicit read-only retrieval smoke from Connectors.
• One resident gateway: gno serve and gno daemon now host stateful Streamable HTTP MCP at /mcp from the same long-lived runtime as their watcher, jobs, stores, and models. T