Alpha Release • v0.1.0 - Features & API subject to change

Understand context instantly

Search without
reading everything

Find relevant code and documentation instantly. Semantic search across markdown, TypeScript, Python. No more grep. No more manual browsing.

The Problem

  • Searching code takes forever. Grep doesn't understand context.
  • Reading 100 files to understand one concept wastes hours.
  • Giving Claude entire codebase = wasted tokens and slow responses.
  • Refactoring? Find ALL usages manually? No thanks.
// Traditional approach

$ grep -r "searchTerm" .

$ // 500 results...

$ // 100 false positives

$ // Still confused

// With @ngao/search

$ npx @ngao/search --setup

Indexed 1,200 files

Ready for search

// Get exactly what you need

Perfect resultsIn milliseconds

The Solution

  • Semantic search understands code meaning, not just keywords.
  • Get only relevant code. Understand context in seconds.
  • AI-ready results save 50% tokens and get better suggestions.
  • Find all usages instantly. Refactor with confidence.

Why Developers Love It

Lightning Fast

Find code in milliseconds. No waiting. No frustration. Just instant results.

🧠

Smart Understanding

Semantic indexing means fewer false positives. Find what matters, not everything.

💰

Save 50% Tokens

Give Claude only relevant code. Lower API costs. Faster responses.

Built For

→ Refactoring

Find All Usages

Locate every reference, dependency, and related code instantly. Refactor with zero risk.

→ Documentation

Search Docs & Code

Search markdown documentation alongside source files. Everything in one place.

→ AI Development

Better AI Context

Give Claude the right context. Smarter suggestions. Lower costs. Better code.

→ Onboarding

Understand Projects Fast

New to a codebase? Find patterns and structure instantly. Reduce learning time.

Getting Started

Set up ngao-search MCP in your project with a few simple steps.

1

Navigate to Your Project

Open your terminal and navigate to the project directory you want to search.

$ cd /path/to/your/project

# Run interactive setup

$ npx @ngao/search --setup

# This will:

Create .ngao-search.json config

Set up project isolation

Start MCP server automatically

2

Run Interactive Setup

Execute the setup command which will:

  • ✓ Ask about your project directories
  • ✓ Create config file (.ngao-search.json)
  • ✓ Set up database isolation with unique ID
  • ✓ Start MCP server for Claude
3

Ask Claude to Read ngao-search

Once the server is running, ask Claude to read the ngao-search instructions so it understands all available capabilities:

# Just ask Claude:

"Read the ngao-search instructions"

# Claude now has access to:

# • Index your project

# • Search semantically

# • Get AI-optimized results

# • Track search history

# • Reindex on changes

# All automatically integrated

4

Enjoy Better Search

That's it! Claude now understands your codebase and can provide:

  • ✓ Instant semantic code search
  • ✓ Smarter context-aware suggestions
  • ✓ 50% fewer tokens needed
  • ✓ Better refactoring support
  • ✓ Faster AI assistance

Supported File Types

Python (.py, .pyi)
TypeScript (.ts, .tsx)
JavaScript (.js, .jsx)
Markdown (.md, .mdx)
JSON (.json)
YAML (.yaml, .yml)

Key Features

🔍

Semantic Search

Understands code meaning, not just keywords

Lightning Fast

Results in milliseconds with smart ranking

💾

Persistent Storage

LanceDB integration persists data across restarts

🤖

AI-Optimized

Results formatted for LLMs with full context

Why Choose ngao-search?

30s

to setup

50%

token savings

100x

faster search