[](LICENSE)
[](https://nodejs.org/)
[](https://www.typescriptlang.org/)
[](CONTRIBUTING.md)
**The world's only true Vector + Graph database - unified semantic search and knowledge graphs**
---
# The Search Problem Every Developer Faces
**"I need to find similar content, explore relationships, AND filter by metadata - but that means juggling 3+ databases"**
โ **Current Reality**: Pinecone + Neo4j + Elasticsearch + Custom Sync Logic
โ **Brainy Reality**: One database. One API. All three search types.
## ๐ฅ The Power of Three-in-One Search
```javascript
// This ONE query does what used to require 3 databases:
const results = await brainy.search("AI startups in healthcare", 10, {
// ๐ Vector: Semantic similarity
includeVerbs: true,
// ๐ Graph: Relationship traversal
verbTypes: ["invests_in", "partners_with"],
// ๐ Faceted: MongoDB-style filtering
metadata: {
industry: "healthcare",
funding: { $gte: 1000000 },
stage: { $in: ["Series A", "Series B"] }
}
})
// Returns: Companies similar to your query + their relationships + matching your criteria
```
**Three search paradigms. One lightning-fast query. Zero complexity.**
## ๐ Install & Go
```bash
npm install @soulcraft/brainy
```
```javascript
import { BrainyData } from '@soulcraft/brainy'
const brainy = new BrainyData() // Auto-detects your environment
await brainy.init() // Auto-configures everything
// Add data with relationships
const openai = await brainy.add("OpenAI", { type: "company", funding: 11000000 })
const gpt4 = await brainy.add("GPT-4", { type: "product", users: 100000000 })
await brainy.relate(openai, gpt4, "develops")
// Search across all dimensions
const results = await brainy.search("AI language models", 5, {
metadata: { funding: { $gte: 10000000 } },
includeVerbs: true
})
```
**That's it. You just built a knowledge graph with semantic search and faceted filtering in 8 lines.**
## ๐ฅ MAJOR UPDATES: What's New in v0.51, v0.49 & v0.48
### ๐ฏ **v0.51: Revolutionary Developer Experience**
**Problem-focused approach that gets you productive in seconds!**
- โ **Problem-Solution Narrative** - Immediately understand why Brainy exists
- โ **8-Line Quickstart** - Three search types in one simple demo
- โ **Streamlined Documentation** - Focus on what matters most
- โ **Clear Positioning** - The only true Vector + Graph database
### ๐ฏ **v0.49: Filter Discovery & Performance Improvements**
**Discover available filters and scale to millions of items!**
```javascript
// Discover what filters are available - O(1) field lookup
const categories = await brainy.getFilterValues('category')
// Returns: ['electronics', 'books', 'clothing', ...]
const fields = await brainy.getFilterFields() // O(1) operation
// Returns: ['category', 'price', 'brand', 'rating', ...]
```
- โ **Filter Discovery API**: O(1) field discovery for instant filter UI generation
- โ **Improved Performance**: Removed deprecated methods, now uses pagination everywhere
- โ **Better Scalability**: Hybrid indexing with O(1) field access scales to millions
- โ **Smart Caching**: LRU cache for frequently accessed filters
- โ **Zero Configuration**: Everything auto-optimizes based on usage patterns
### ๐ **v0.48: MongoDB-Style Metadata Filtering**
**Powerful querying with familiar syntax - filter DURING search for maximum performance!**
```javascript
const results = await brainy.search("wireless headphones", 10, {
metadata: {
category: { $in: ["electronics", "audio"] },
price: { $lte: 200 },
rating: { $gte: 4.0 },
brand: { $ne: "Generic" }
}
})
```
- โ **15+ MongoDB Operators**: `$gt`, `$in`, `$regex`, `$and`, `$or`, `$includes`, etc.
- โ **Automatic Indexing**: Zero configuration, maximum performance
- โ **Nested Fields**: Use dot notation for complex objects
- โ **100% Backward Compatible**: Your existing code works unchanged
### โก **v0.46: Transformers.js Migration**
**Replaced TensorFlow.js for better performance and true offline operation!**
- โ **95% Smaller Package**: 643 kB vs 12.5 MB
- โ **84% Smaller Models**: 87 MB vs 525 MB models
- โ **True Offline**: Zero network calls after initial download
- โ **5x Fewer Dependencies**: Clean tree, no peer dependency issues
- โ **Same API**: Drop-in replacement, existing code works unchanged
### ๐ Why Developers Love Brainy
- **๐ง Zero-to-Smartโข** - No config files, no tuning parameters, no DevOps headaches. Brainy auto-detects your environment and optimizes itself
- **๐ True Write-Once, Run-Anywhere** - Same code runs in Angular, React, Vue, Node.js, Deno, Bun, serverless, edge workers, and web workers with automatic environment detection
- **โก Scary Fast** - Handles millions of vectors with sub-millisecond search. GPU acceleration for embeddings, optimized CPU for distance calculations
- **๐ฏ Self-Learning** - Like having a database that goes to the gym. Gets faster and smarter the more you use it
- **๐ฎ AI-First Design** - Built for the age of embeddings, RAG, and semantic search. Your LLMs will thank you
- **๐ฎ Actually Fun to Use** - Clean API, great DX, and it does the heavy lifting so you can build cool stuff
### ๐ NEW: Ultra-Fast Search Performance + Auto-Configuration
**Your searches just got 100x faster AND Brainy now configures itself!** Advanced performance with zero setup:
- **๐ค Intelligent Auto-Configuration** - Detects environment and usage patterns, optimizes automatically
- **โก Smart Result Caching** - Repeated queries return in <1ms with automatic cache invalidation
- **๐ Cursor-Based Pagination** - Navigate millions of results with constant O(k) performance
- **๐ Real-Time Data Sync** - Cache automatically updates when data changes, even in distributed scenarios
- **๐ Performance Monitoring** - Built-in hit rate and memory usage tracking with adaptive optimization
- **๐ฏ Zero Breaking Changes** - All existing code works unchanged, just faster and smarter
## ๐ Why Brainy Wins
- ๐ง **Triple Search Power** - Vector + Graph + Faceted filtering in one query
- ๐ **Runs Everywhere** - Same code: React, Node.js, serverless, edge
- โก **Zero Config** - Auto-detects environment, optimizes itself
- ๐ **Always Synced** - No data consistency nightmares between systems
- ๐ฆ **Truly Offline** - Works without internet after initial setup
- ๐ **Your Data** - Run locally, in browser, or your own cloud
## ๐ฎ Coming Soon
- **๐ค MCP Integration** - Let Claude, GPT, and other AI models query your data directly
- **โก LLM Generation** - Built-in content generation powered by your knowledge graph
- **๐ Real-time Sync** - Live updates across distributed instances
## ๐จ Build Amazing Things
**๐ค AI Chat Applications** - Build ChatGPT-like apps with long-term memory and context awareness
**๐ Semantic Search Engines** - Search by meaning, not keywords. Find "that thing that's like a cat but bigger" โ returns "tiger"
**๐ฏ Recommendation Engines** - "Users who liked this also liked..." but actually good
**๐งฌ Knowledge Graphs** - Connect everything to everything. Wikipedia meets Neo4j meets magic
**๐๏ธ Computer Vision Apps** - Store and search image embeddings. "Find all photos with dogs wearing hats"
**๐ต Music Discovery** - Find songs that "feel" similar. Spotify's Discover Weekly in your app
**๐ Smart Documentation** - Docs that answer questions. "How do I deploy to production?" โ relevant guides
**๐ก๏ธ Fraud Detection** - Find patterns humans can't see. Anomaly detection on steroids
**๐ Real-Time Collaboration** - Sync vector data across devices. Figma for AI data
**๐ฅ Medical Diagnosis Tools** - Match symptoms to conditions using embedding similarity
## ๐ Works Everywhere - Same Code
**Write once, run anywhere.** Brainy auto-detects your environment and optimizes automatically:
### ๐ Browser Frameworks (React, Angular, Vue)
```javascript
import { BrainyData } from '@soulcraft/brainy'
// SAME CODE in React, Angular, Vue, Svelte, etc.
const brainy = new BrainyData()
await brainy.init() // Auto-uses OPFS in browsers
// Add entities and relationships
const john = await brainy.add("John is a software engineer", { type: "person" })
const jane = await brainy.add("Jane is a data scientist", { type: "person" })
const ai = await brainy.add("AI Project", { type: "project" })
await brainy.relate(john, ai, "works_on")
await brainy.relate(jane, ai, "leads")
// Search by meaning
const engineers = await brainy.search("software developers", 5)
// Traverse relationships
const team = await brainy.getVerbsByTarget(ai) // Who works on AI Project?
```
๐ฆ Full React Component Example
```jsx
import { BrainyData } from '@soulcraft/brainy'
import { useEffect, useState } from 'react'
function Search() {
const [brainy, setBrainy] = useState(null)
const [results, setResults] = useState([])
useEffect(() => {
const init = async () => {
const db = new BrainyData()
await db.init()
// Add your data...
setBrainy(db)
}
init()
}, [])
const search = async (query) => {
const results = await brainy?.search(query, 5) || []
setResults(results)
}
return search(e.target.value)} placeholder="Search..." />
}
```
๐ฆ Full Angular Component Example
```typescript
import { Component, signal, OnInit } from '@angular/core'
import { BrainyData } from '@soulcraft/brainy'
@Component({
selector: 'app-search',
template: ``
})
export class SearchComponent implements OnInit {
brainy = new BrainyData()
async ngOnInit() {
await this.brainy.init()
// Add your data...
}
async search(query: string) {
const results = await this.brainy.search(query, 5)
// Display results...
}
}
```
๐ฆ Full Vue Example
```vue
```
### ๐ข Node.js / Serverless / Edge
```javascript
import { BrainyData } from '@soulcraft/brainy'
// SAME CODE works in Node.js, Vercel, Netlify, Cloudflare Workers, Deno, Bun
const brainy = new BrainyData()
await brainy.init() // Auto-detects environment and optimizes
// Add entities and relationships
await brainy.add("Python is great for data science", { type: "fact" })
await brainy.add("JavaScript rules the web", { type: "fact" })
// Search by meaning
const results = await brainy.search("programming languages", 5)
// Optional: Production with S3/R2 storage (auto-detected in cloud environments)
const productionBrainy = new BrainyData({
storage: {
s3Storage: { bucketName: process.env.BUCKET_NAME }
}
})
```
**That's it! Same code, everywhere. Zero-to-Smartโข**
Brainy automatically detects and optimizes for your environment:
| Environment | Storage | Optimization |
|-------------|---------|-------------|
| ๐ Browser | OPFS | Web Workers, Memory Cache |
| ๐ข Node.js | FileSystem / S3 | Worker Threads, Clustering |
| โก Serverless | S3 / Memory | Cold Start Optimization |
| ๐ฅ Edge | Memory / KV | Minimal Footprint |
## ๐ Distributed Mode (NEW!)
**Scale horizontally with zero configuration!** Brainy now supports distributed deployments with automatic coordination:
- **๐ Multi-Instance Coordination** - Multiple readers and writers working in harmony
- **๐ท๏ธ Smart Domain Detection** - Automatically categorizes data (medical, legal, product, etc.)
- **๐ Real-Time Health Monitoring** - Track performance across all instances
- **๐ Automatic Role Optimization** - Readers optimize for cache, writers for throughput
- **๐๏ธ Intelligent Partitioning** - Hash-based partitioning for perfect load distribution
```javascript
// Writer Instance - Ingests data from multiple sources
const writer = new BrainyData({
storage: { s3Storage: { bucketName: 'my-bucket' } },
distributed: { role: 'writer' } // Explicit role for safety
})
// Reader Instance - Optimized for search queries
const reader = new BrainyData({
storage: { s3Storage: { bucketName: 'my-bucket' } },
distributed: { role: 'reader' } // 80% memory for cache
})
// Data automatically gets domain tags
await writer.add("Patient shows symptoms of...", {
diagnosis: "flu" // Auto-tagged as 'medical' domain
})
// Domain-aware search across all partitions
const results = await reader.search("medical symptoms", 10, {
filter: { domain: 'medical' } // Only search medical data
})
// Monitor health across all instances
const health = reader.getHealthStatus()
console.log(`Instance ${health.instanceId}: ${health.status}`)
```
### ๐ณ NEW: Zero-Config Docker Deployment
**Deploy to any cloud with embedded models - no runtime downloads needed!**
```dockerfile
# One line extracts models automatically during build
RUN npm run download-models
# Deploy anywhere: Google Cloud, AWS, Azure, Cloudflare, etc.
```
- **โก 7x Faster Cold Starts** - Models embedded in container, no downloads
- **๐ Universal Cloud Support** - Same Dockerfile works everywhere
- **๐ Offline Ready** - No external dependencies at runtime
- **๐ฆ Zero Configuration** - Automatic model detection and loading
```javascript
// Zero configuration - everything optimized automatically!
const brainy = new BrainyData() // Auto-detects environment & optimizes
await brainy.init()
// Caching happens automatically - no setup needed!
const results1 = await brainy.search('query', 10) // ~50ms first time
const results2 = await brainy.search('query', 10) // <1ms cached hit!
// Advanced pagination works instantly
const page1 = await brainy.searchWithCursor('query', 100)
const page2 = await brainy.searchWithCursor('query', 100, {
cursor: page1.cursor // Constant time, no matter how deep!
})
// Monitor auto-optimized performance
const stats = brainy.getCacheStats()
console.log(`Auto-tuned cache hit rate: ${(stats.search.hitRate * 100).toFixed(1)}%`)
```
## ๐ญ Key Features
### Core Capabilities
- **Vector Search** - Find semantically similar content using embeddings
- **MongoDB-Style Metadata Filtering** ๐ - Advanced filtering with `$gt`, `$in`, `$regex`, `$and`, `$or` operators
- **Graph Relationships** - Connect data with meaningful relationships
- **JSON Document Search** - Search within specific fields with prioritization
- **Distributed Mode** - Scale horizontally with automatic coordination between instances
- **Real-Time Syncing** - WebSocket and WebRTC for distributed instances
- **Streaming Pipeline** - Process data in real-time as it flows through
- **Model Control Protocol** - Let AI models access your data
### Developer Experience
- **TypeScript Support** - Fully typed API with generics
- **Extensible Augmentations** - Customize and extend functionality
- **REST API** - Web service wrapper for HTTP endpoints
- **Auto-Complete** - IntelliSense for all APIs and types
## ๐ Why Not Just Use...?
### vs. Multiple Databases
โ **Pinecone + Neo4j + Elasticsearch** - 3 databases, sync nightmares, 3x the cost
โ **Brainy** - One database, always synced, built-in intelligence
### vs. Traditional Solutions
โ **PostgreSQL + pgvector + extensions** - Complex setup, performance issues
โ **Brainy** - Zero config, purpose-built for AI, works everywhere
### vs. Cloud-Only Vector DBs
โ **Pinecone/Weaviate/Qdrant** - Vendor lock-in, expensive, cloud-only
โ **Brainy** - Run anywhere, your data stays yours, cost-effective
### vs. Graph Databases with "Vector Features"
โ **Neo4j + vector plugin** - Bolt-on solution, not native, limited
โ **Brainy** - Native vector+graph architecture from the ground up
## ๐ฆ Advanced Features
๐ง MongoDB-Style Metadata Filtering
```javascript
const results = await brainy.search("machine learning", 10, {
metadata: {
// Comparison operators
price: { $gte: 100, $lte: 1000 },
category: { $in: ["AI", "ML", "Data"] },
rating: { $gt: 4.5 },
// Logical operators
$and: [
{ status: "active" },
{ verified: true }
],
// Text operators
description: { $regex: "neural.*network", $options: "i" },
// Array operators
tags: { $includes: "tensorflow" }
}
})
```
**15+ operators supported**: `$gt`, `$gte`, `$lt`, `$lte`, `$eq`, `$ne`, `$in`, `$nin`, `$and`, `$or`, `$not`, `$regex`, `$includes`, `$exists`, `$size`
๐ Graph Relationships & Traversal
```javascript
// Create entities and relationships
const company = await brainy.add("OpenAI", { type: "company" })
const product = await brainy.add("GPT-4", { type: "product" })
const person = await brainy.add("Sam Altman", { type: "person" })
// Create meaningful relationships
await brainy.relate(company, product, "develops")
await brainy.relate(person, company, "leads")
await brainy.relate(product, person, "created_by")
// Traverse relationships
const products = await brainy.getVerbsBySource(company) // What OpenAI develops
const leaders = await brainy.getVerbsByTarget(company) // Who leads OpenAI
const connections = await brainy.findSimilar(product, {
relationType: "develops"
})
// Search with relationship context
const results = await brainy.search("AI models", 10, {
includeVerbs: true,
verbTypes: ["develops", "created_by"],
searchConnectedNouns: true
})
```
๐ Universal Storage & Deployment
```javascript
// Development: File system
const dev = new BrainyData({
storage: { fileSystem: { path: './data' } }
})
// Production: S3/R2
const prod = new BrainyData({
storage: { s3Storage: { bucketName: 'my-vectors' } }
})
// Browser: OPFS
const browser = new BrainyData() // Auto-detects OPFS
// Edge: Memory
const edge = new BrainyData({
storage: { memory: {} }
})
// Redis: High performance
const redis = new BrainyData({
storage: { redis: { connectionString: 'redis://...' } }
})
```
**Extend with any storage**: MongoDB, PostgreSQL, DynamoDB - [see storage adapters guide](docs/api-reference/storage-adapters.md)
๐ณ Docker & Cloud Deployment
```dockerfile
# Production-ready Dockerfile
FROM node:24-slim AS builder
WORKDIR /app
COPY package*.json ./
RUN npm ci
COPY . .
RUN npm run download-models # Embed models for offline operation
RUN npm run build
FROM node:24-slim AS production
WORKDIR /app
COPY package*.json ./
RUN npm ci --only=production
COPY --from=builder /app/dist ./dist
COPY --from=builder /app/models ./models # Offline models included
CMD ["node", "dist/server.js"]
```
Deploy to: Google Cloud Run, AWS Lambda/ECS, Azure Container Instances, Cloudflare Workers, Railway, Render, Vercel, anywhere Docker runs.
## ๐ Getting Started in 30 Seconds
**The same Brainy code works everywhere - React, Vue, Angular, Node.js, Serverless, Edge Workers.**
```javascript
// This EXACT code works in ALL environments
import { BrainyData } from '@soulcraft/brainy'
const brainy = new BrainyData()
await brainy.init()
// Add nouns (entities)
const openai = await brainy.add("OpenAI", { type: "company" })
const gpt4 = await brainy.add("GPT-4", { type: "product" })
// Add verbs (relationships)
await brainy.relate(openai, gpt4, "develops")
// Vector search + Graph traversal
const similar = await brainy.search("AI companies", 5)
const products = await brainy.getVerbsBySource(openai)
```
๐ See Framework Examples
### React
```jsx
function App() {
const [brainy] = useState(() => new BrainyData())
useEffect(() => brainy.init(), [])
const search = async (query) => {
return await brainy.search(query, 10)
}
// Same API as above
}
```
### Vue 3
```vue
```
### Angular
```typescript
@Component({})
export class AppComponent {
brainy = new BrainyData()
async ngOnInit() {
await this.brainy.init()
// Same API as above
}
}
```
### Node.js / Deno / Bun
```javascript
const brainy = new BrainyData()
await brainy.init()
// Same API as above
```
### ๐ Framework-First, Runs Everywhere
**Brainy automatically detects your environment and optimizes everything:**
| Environment | Storage | Optimization |
|-----------------|-----------------|----------------------------|
| ๐ Browser | OPFS | Web Workers, Memory Cache |
| ๐ข Node.js | FileSystem / S3 | Worker Threads, Clustering |
| โก Serverless | S3 / Memory | Cold Start Optimization |
| ๐ฅ Edge Workers | Memory / KV | Minimal Footprint |
| ๐ฆ Deno/Bun | FileSystem / S3 | Native Performance |
## ๐ Documentation & Resources
- **[๐ Quick Start Guide](docs/getting-started/)** - Get up and running in minutes
- **[๐ API Reference](docs/api-reference/)** - Complete method documentation
- **[๐ก Examples](docs/examples/)** - Real-world usage patterns
- **[โก Performance Guide](docs/optimization-guides/)** - Scale to millions of vectors
- **[๐ง Storage Adapters](docs/api-reference/storage-adapters.md)** - Universal storage compatibility
## ๐ค Contributing
We welcome contributions! Please see:
- [Contributing Guidelines](CONTRIBUTING.md)
- [Developer Documentation](docs/development/DEVELOPERS.md)
- [Code of Conduct](CODE_OF_CONDUCT.md)
## ๐ License
[MIT](LICENSE)
---
Ready to build the future of search? Get started with Brainy today!
**[Get Started โ](docs/getting-started/) | [View Examples โ](docs/examples/) | [Join Community โ](https://github.com/soulcraft-research/brainy/discussions)**
