🧠 NeuroLink

Enterprise AI Development Platform with built-in tools, universal provider support, and factory pattern architecture. Production-ready with TypeScript support.

NeuroLink is an Enterprise AI Development Platform that unifies 9 major AI providers with intelligent fallback and built-in tool support. Available as both a programmatic SDK and professional CLI tool. Features 6 core tools working across all providers plus SDK custom tool registration. Extracted from production use at Juspay.

🚀 Enterprise Platform Features

🏭 Factory Pattern Architecture - Unified provider management through BaseProvider inheritance
🔧 Tools-First Design - All providers include built-in tool support without additional configuration
🌐 Real-time WebSocket Infrastructure - [Coming Soon - Broken in migration, being fixed]
📊 Advanced Telemetry - [Coming Soon - Broken in migration, being fixed]
💬 Enhanced Chat Services - [Coming Soon - Broken in migration, being fixed]
🏗️ Enterprise Architecture - Production-ready with clean abstractions
🔄 Configuration Management - Flexible provider configuration
✅ Type Safety - Industry-standard TypeScript interfaces
⚡ Performance - Fast response times with streaming support
🛡️ Error Recovery - Graceful failures with provider fallback

✅ LATEST UPDATE: Factory Pattern Refactoring Complete (2025-01-20)

NeuroLink now features a unified factory pattern architecture with automatic tool support for all providers.

✅ Unified Architecture: All providers inherit from BaseProvider with built-in tool support
✅ Direct Tools: Six core tools available across all providers (getCurrentTime, readFile, listDirectory, calculateMath, writeFile, searchFiles)
✅ Simplified Providers: Removed duplicate code - providers now focus only on model-specific logic
✅ Better Testing: 78% of providers fully working with tools (7/9 providers), 22% partial support
✅ Zero Breaking Changes: All existing code continues working (backward compatibility)
✅ SDK Custom Tools: Register your own tools programmatically with the SDK

Factory Pattern: NeuroLink uses BaseProvider inheritance to provide consistent tool support across all AI providers without code duplication.

✅ Stream Function Migration Complete (2025-01-12)

NeuroLink uses stream() as the primary streaming function with future-ready multi-modal interface.

✅ New Primary Streaming: stream() with multi-modal ready interface
✅ Enhanced Generation: generate() as primary generation function
✅ Factory Enhanced: Better provider management across all methods
✅ Zero Breaking Changes: All existing code continues working (backward compatibility)

Enhanced API: NeuroLink uses stream() and generate() as primary functions with multi-modal ready interfaces and improved factory patterns.

🚀 Quick Start

Install & Run (2 minutes)

# Quick setup with Google AI Studio (free tier available)
export GOOGLE_AI_API_KEY="AIza-your-google-ai-api-key"

# CLI - No installation required
npx @juspay/neurolink generate "Hello, AI"
npx @juspay/neurolink gen "Hello, AI"        # Shortest form

# ✨ Primary Method (generate) - Recommended
npx @juspay/neurolink generate "Explain AI" --provider google-ai
npx @juspay/neurolink gen "Write code" --provider openai       # Shortest form

# 🆕 AI Enhancement Features
npx @juspay/neurolink generate "Explain AI" --enable-analytics --debug
npx @juspay/neurolink generate "Write code" --enable-evaluation --debug
npx @juspay/neurolink generate "Help me" --context '{"userId":"123"}' --debug

npx @juspay/neurolink status

# SDK Installation for using in your typescript projects
npm install @juspay/neurolink

Basic Usage

import { NeuroLink } from "@juspay/neurolink";

// NEW: Primary method (recommended)
const neurolink = new NeuroLink();
const result = await neurolink.generate({
  input: { text: "Write a haiku about programming" },
  provider: "google-ai",
  timeout: "30s", // Optional: Set custom timeout (default: 30s)
});
// Alternative: Auto-selects best available provider
import { createBestAIProvider } from "@juspay/neurolink";
const provider = createBestAIProvider();
const providerResult = await provider.generate({
  input: { text: "Write a haiku about programming" },
  timeout: "30s",
});

console.log(result.content);
console.log(`Used: ${result.provider}`);

🔗 CLI-SDK Consistency (NEW! ✨)

Method aliases that match CLI command names:

// All three methods are equivalent:
const result1 = await provider.generate({ input: { text: "Hello" } }); // Original
const result2 = await provider.generate({ input: { text: "Hello" } }); // Matches CLI 'generate'
const result3 = await provider.gen({ input: { text: "Hello" } }); // Matches CLI 'gen'

// Use whichever style you prefer:
const provider = createBestAIProvider();

// Detailed method name
const story = await provider.generate({
  input: { text: "Write a short story about AI" },
  maxTokens: 200,
});

// CLI-style method names
const poem = await provider.generate({ input: { text: "Write a poem" } });
const joke = await provider.gen({ input: { text: "Tell me a joke" } });

🆕 Enhanced Usage (NEW! ✨)

Enhanced CLI with Analytics & Evaluation

# Basic AI generation
npx @juspay/neurolink generate "Write a business email"

# With analytics and evaluation (NEW!)
npx @juspay/neurolink generate "Write a business email" --enable-analytics --enable-evaluation --debug

# See detailed usage data:
# 📊 Analytics: Provider usage, token costs, response times
# ⭐ Response Evaluation: AI-powered quality scores

# With custom context
npx @juspay/neurolink generate "Create a proposal" --context '{"company":"TechCorp"}' --debug

Enhanced SDK with Analytics & Evaluation

import { NeuroLink } from "@juspay/neurolink";
const neurolink = new NeuroLink();

// Basic usage
const result = await neurolink.generate({ input: { text: "Write a story" } });

// With enhancements (NEW!)
const enhancedResult = await neurolink.generate({
  input: { text: "Write a business proposal" },
  enableAnalytics: true, // Get usage & cost data
  enableEvaluation: true, // Get AI quality scores
  context: { project: "Q1-sales" }, // Custom context
});

// Access enhancement data
console.log("📊 Usage:", enhancedResult.analytics);
console.log("⭐ Quality:", enhancedResult.evaluation);
console.log("Response:", enhancedResult.content);

// Enhanced evaluation included when enableEvaluation is true
// Returns basic quality scores for the generated content

🌐 Enterprise Real-time Features (NEW! 🚀)

Real-time WebSocket Chat

import {
  createEnhancedChatService,
  NeuroLinkWebSocketServer,
} from "@juspay/neurolink";

// Enhanced chat with WebSocket support
const chatService = createEnhancedChatService({
  provider: await createBestAIProvider(),
  enableWebSocket: true,
  enableSSE: true,
  streamingConfig: {
    bufferSize: 8192,
    compressionEnabled: true,
  },
});

// WebSocket server for real-time applications
const wsServer = new NeuroLinkWebSocketServer({
  port: 8080,
  maxConnections: 1000,
  enableCompression: true,
});

// Handle real-time chat
wsServer.on("chat-message", async ({ connectionId, message }) => {
  await chatService.streamChat({
    prompt: message.data.prompt,
    onChunk: (chunk) => {
      wsServer.sendMessage(connectionId, {
        type: "ai-chunk",
        data: { chunk },
      });
    },
  });
});

Enterprise Telemetry Integration

import { initializeTelemetry, getTelemetryStatus } from "@juspay/neurolink";

// Optional enterprise monitoring (zero overhead when disabled)
const telemetry = initializeTelemetry({
  serviceName: "my-ai-app",
  endpoint: "http://localhost:4318",
  enableTracing: true,
  enableMetrics: true,
  enableLogs: true,
});

// Check telemetry status
const status = await getTelemetryStatus();
console.log("Telemetry enabled:", status.enabled);
console.log("Service:", status.service);
console.log("Version:", status.version);

// All AI operations are now automatically monitored
const provider = await createBestAIProvider();
const result = await provider.generate({
  prompt: "Generate business report",
});
// Telemetry automatically tracks: response time, token usage, cost, errors

Environment Setup

# Create .env file (automatically loaded by CLI)
echo 'OPENAI_API_KEY="sk-your-openai-key"' > .env
echo 'GOOGLE_AI_API_KEY="AIza-your-google-ai-key"' >> .env
echo 'AWS_ACCESS_KEY_ID="your-aws-access-key"' >> .env

# Test configuration
npx @juspay/neurolink status

📖 Complete Setup Guide - All providers with detailed instructions

✨ Key Features

🏭 Factory Pattern Architecture - Unified provider management with BaseProvider inheritance
🔧 Tools-First Design - All providers automatically include direct tool support (getCurrentTime, readFile, listDirectory, calculateMath, writeFile, searchFiles)
🔄 9 AI Providers - OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, Azure, Hugging Face, Ollama, Mistral AI
⚡ Dynamic Model System - Self-updating model configurations without code changes
💰 Cost Optimization - Automatic selection of cheapest models for tasks
🔍 Smart Model Resolution - Fuzzy matching, aliases, and capability-based search
⚡ Automatic Fallback - Never fail when providers are down
🖥️ CLI + SDK - Use from command line or integrate programmatically
🛡️ Production Ready - TypeScript, error handling, extracted from production
✅ MCP Integration - Model Context Protocol with working built-in tools and 58+ external servers
🔍 MCP Auto-Discovery - Zero-config discovery across VS Code, Claude, Cursor, Windsurf
⚙️ Built-in Tools - Time, date calculations, and number formatting ready to use
🤖 AI Analysis Tools - Built-in optimization and workflow assistance
🏠 Local AI Support - Run completely offline with Ollama
🌍 Open Source Models - Access 100,000+ models via Hugging Face
🇪🇺 GDPR Compliance - European data processing with Mistral AI

🛠️ MCP Integration Status ✅ BUILT-IN TOOLS WORKING

Component	Status	Description
Built-in Tools	✅ Working	6 core tools fully functional across all providers
SDK Custom Tools	✅ Working	Register custom tools programmatically
External Discovery	🔍 Discovery	58+ MCP servers discovered from AI tools ecosystem
Tool Execution	✅ Working	Real-time AI tool calling with built-in tools
External Tools	🚧 Development	Manual config needs one-line fix, activation in progress
CLI Integration	✅ READY	Production-ready with built-in tools
External Activation	🔧 Development	Discovery complete, activation protocol in progress

✅ Quick MCP Test (v1.7.1)

# Test built-in tools (works immediately)
npx @juspay/neurolink generate "What time is it?" --debug

# Disable tools for pure text generation
npx @juspay/neurolink generate "Write a poem" --disable-tools

# Discover available MCP servers
npx @juspay/neurolink mcp discover --format table

🔧 SDK Custom Tool Registration (NEW!)

Register your own tools programmatically with the SDK:

import { NeuroLink } from "@juspay/neurolink";
const neurolink = new NeuroLink();

// Register a simple tool
neurolink.registerTool("weatherLookup", {
  description: "Get current weather for a city",
  parameters: z.object({
    city: z.string().describe("City name"),
    units: z.enum(["celsius", "fahrenheit"]).optional(),
  }),
  execute: async ({ city, units = "celsius" }) => {
    // Your implementation here
    return {
      city,
      temperature: 22,
      units,
      condition: "sunny",
    };
  },
});

// Use it in generation
const result = await neurolink.generate({
  input: { text: "What's the weather in London?" },
  provider: "google-ai",
});

// Register multiple tools at once
neurolink.registerTools({
  stockPrice: {
    /* tool definition */
  },
  calculator: {
    /* tool definition */
  },
});

⚡ Dynamic Model System (v1.8.0)

NeuroLink now features a revolutionary dynamic model configuration system that eliminates hardcoded model lists and enables automatic cost optimization.

✅ Key Benefits

🔄 Self-Updating: New models automatically available without code updates
💰 Cost-Optimized: Automatic selection of cheapest models for tasks
🔍 Smart Search: Find models by capabilities (function-calling, vision, etc.)
🏷️ Alias Support: Use friendly names like "claude-latest" or "best-coding"
📊 Real-Time Pricing: Always current model costs and performance data

🚀 Quick Examples

# Cost optimization - automatically use cheapest model
npx @juspay/neurolink generate "Hello" --optimize-cost

# Capability search - find models with specific features
npx @juspay/neurolink generate "Describe this image" --capability vision

# Model aliases - use friendly names
npx @juspay/neurolink gen "Write code" --model best-coding

# Test dynamic model server
npm run model-server  # Starts config server on localhost:3001
npm run test:dynamic-models  # Comprehensive test suite

📊 Current Model Inventory (Auto-Updated)

10 active models across 4 providers
Cheapest: Gemini 2.0 Flash ($0.000075/1K tokens)
Most capable: Claude 3 Opus (function-calling + vision + analysis)
Best for coding: Claude 3 Opus, Gemini 2.0 Flash
1 deprecated model automatically excluded

📖 Complete Dynamic Models Guide - Setup, configuration, and advanced usage

💻 Essential Examples

CLI Commands

# Text generation with automatic MCP tool detection (default)
npx @juspay/neurolink generate "What time is it?"

# Alternative short form
npx @juspay/neurolink gen "What time is it?"

# Disable tools for training-data-only responses
npx @juspay/neurolink generate "What time is it?" --disable-tools

# With custom timeout for complex prompts
npx @juspay/neurolink generate "Explain quantum computing in detail" --timeout 1m

# Real-time streaming with agent support (default)
npx @juspay/neurolink stream "What time is it?"

# Streaming without tools (traditional mode)
npx @juspay/neurolink stream "Tell me a story" --disable-tools

# Streaming with extended timeout
npx @juspay/neurolink stream "Write a long story" --timeout 5m

# Provider diagnostics
npx @juspay/neurolink status --verbose

# Batch processing
echo -e "Write a haiku\nExplain gravity" > prompts.txt
npx @juspay/neurolink batch prompts.txt --output results.json

# Batch with custom timeout per request
npx @juspay/neurolink batch prompts.txt --timeout 45s --output results.json

SDK Integration

// SvelteKit API route with timeout handling
export const POST: RequestHandler = async ({ request }) => {
  const { message } = await request.json();
  const provider = createBestAIProvider();

  try {
    // NEW: Primary streaming method (recommended)
    const result = await provider.stream({
      input: { text: message },
      timeout: "2m", // 2 minutes for streaming
    });

    // Process stream
    for await (const chunk of result.stream) {
      // Handle streaming content
      console.log(chunk.content);
    }

    // LEGACY: Backward compatibility (still works)
    const legacyResult = await provider.stream({ input: { text:
      prompt: message,
      timeout: "2m", // 2 minutes for streaming
    });
    return new Response(result.toReadableStream());
  } catch (error) {
    if (error.name === "TimeoutError") {
      return new Response("Request timed out", { status: 408 });
    }
    throw error;
  }
};

// Next.js API route with timeout
export async function POST(request: NextRequest) {
  const { prompt } = await request.json();
  const provider = createBestAIProvider();

  const result = await provider.generate({
    prompt,
    timeout: process.env.AI_TIMEOUT || "30s", // Configurable timeout
  });

  return NextResponse.json({ text: result.content });
}

🎬 See It In Action

No installation required! Experience NeuroLink through comprehensive visual documentation:

📱 Interactive Web Demo

cd neurolink-demo && node server.js
# Visit http://localhost:9876 for live demo

Real AI Integration: All 9 providers functional with live generation
Complete Use Cases: Business, creative, and developer scenarios
Performance Metrics: Live provider analytics and response times
Privacy Options: Test local AI with Ollama

🖥️ CLI Demonstrations

CLI Help & Commands - Complete command reference
Provider Status Check - Connectivity verification (now with authentication and model availability checks)
Text Generation - Real AI content creation

🌐 Web Interface Videos

Business Use Cases - Professional applications
Developer Tools - Code generation and APIs
Creative Tools - Content creation

📖 Complete Visual Documentation - All screenshots and videos

📚 Documentation

Getting Started

🔧 Provider Setup - Complete environment configuration
🖥️ CLI Guide - All commands and options
🏗️ SDK Integration - Next.js, SvelteKit, React
⚙️ Environment Variables - Full configuration guide

Advanced Features

🏭 Factory Pattern Migration - Guide to the new unified provider architecture
🔄 MCP Foundation - Model Context Protocol architecture
⚡ Dynamic Models - Self-updating model configurations and cost optimization
🧠 AI Analysis Tools - Usage optimization and benchmarking
🛠️ AI Workflow Tools - Development lifecycle assistance
🎬 Visual Demos - Screenshots and videos

Reference

📚 API Reference - Complete TypeScript API
🔗 Framework Integration - SvelteKit, Next.js, Express.js

🏗️ Supported Providers & Models

Provider	Models	Auth Method	Free Tier	Tool Support
OpenAI	GPT-4o, GPT-4o-mini	API Key	❌	✅ Full
Google AI Studio	Gemini 2.5 Flash/Pro	API Key	✅	✅ Full
Amazon Bedrock	Claude 3.5/3.7 Sonnet	AWS Credentials	❌	✅ Full*
Google Vertex AI	Gemini 2.5 Flash	Service Account	❌	✅ Full
Anthropic	Claude 3.5 Sonnet	API Key	❌	✅ Full
Azure OpenAI	GPT-4, GPT-3.5	API Key + Endpoint	❌	✅ Full
Hugging Face 🆕	100,000+ models	API Key	✅	⚠️ Partial
Ollama 🆕	Llama 3.2, Gemma, Mistral	None (Local)	✅	⚠️ Partial
Mistral AI 🆕	Tiny, Small, Medium, Large	API Key	✅	✅ Full

Tool Support Legend:

✅ Full: All tools working correctly
⚠️ Partial: Tools visible but may not execute properly
❌ Limited: Issues with model or configuration
* Bedrock requires valid AWS credentials, Ollama requires specific models like gemma3n for tool support

✨ Auto-Selection: NeuroLink automatically chooses the best available provider based on speed, reliability, and configuration.

🎯 Production Features

Enterprise-Grade Reliability

Automatic Failover: Seamless provider switching on failures
Error Recovery: Comprehensive error handling and logging
Performance Monitoring: Built-in analytics and metrics
Type Safety: Full TypeScript support with IntelliSense

AI Platform Capabilities

MCP Foundation: Universal AI development platform with 10+ specialized tools
Analysis Tools: Usage optimization, performance benchmarking, parameter tuning
Workflow Tools: Test generation, code refactoring, documentation, debugging
Extensibility: Connect external tools and services via MCP protocol
🆕 Dynamic Server Management: Programmatically add MCP servers at runtime

🔧 Programmatic MCP Server Management [Coming Soon]

Note: External MCP server activation is in development. Currently available:

✅ 6 built-in tools working across all providers
✅ SDK custom tool registration
🔍 MCP server discovery (58+ servers found)
🚧 External server activation (one-line fix pending)

Manual MCP configuration (.mcp-config.json) support coming soon.

🤝 Contributing

We welcome contributions! Please see our Contributing Guidelines for details.

Development Setup

git clone https://github.com/juspay/neurolink
cd neurolink
pnpm install
pnpm setup:complete  # One-command setup with all automation
pnpm test:adaptive   # Intelligent testing
pnpm build:complete  # Full build pipeline

New Developer Experience (v2.0)

NeuroLink now features enterprise-grade automation with 72+ commands:

# Environment & Setup (2-minute initialization)
pnpm setup:complete        # Complete project setup
pnpm env:setup             # Safe .env configuration
pnpm env:backup            # Environment backup

# Testing & Quality (60-80% faster)
pnpm test:adaptive         # Intelligent test selection
pnpm test:providers        # AI provider validation
pnpm quality:check         # Full quality pipeline

# Documentation & Content
pnpm docs:sync             # Cross-file documentation sync
pnpm content:generate      # Automated content creation

# Build & Deployment
pnpm build:complete        # 7-phase enterprise pipeline
pnpm dev:health            # System health monitoring

📖 Complete Automation Guide - All 72+ commands and automation features

📄 License

🔗 Related Projects

Vercel AI SDK - Underlying provider implementations
SvelteKit - Web framework used in this project
Model Context Protocol - Tool integration standard

Built with ❤️ by Juspay Technologies

Name		Name	Last commit message	Last commit date
Latest commit History 55 Commits
.changeset		.changeset
.claude		.claude
.github		.github
config		config
docs		docs
examples		examples
memory-bank		memory-bank
neurolink-demo		neurolink-demo
scripts		scripts
src		src
test		test
tools		tools
.clinerules		.clinerules
.env.example		.env.example
.gitignore		.gitignore
.mcp-config.json		.mcp-config.json
.mcp-servers.example.json		.mcp-servers.example.json
.prettierignore		.prettierignore
.releaserc.json		.releaserc.json
.tmp-test-patterns.txt		.tmp-test-patterns.txt
CHANGELOG.md		CHANGELOG.md
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
MASTER_NEUROLINK_COMPLETE_ANALYSIS.md		MASTER_NEUROLINK_COMPLETE_ANALYSIS.md
MASTER_STATUS_DOCUMENT.md		MASTER_STATUS_DOCUMENT.md
NEUROLINK_BACKUP_MIGRATION_ANALYSIS.md		NEUROLINK_BACKUP_MIGRATION_ANALYSIS.md
README.md		README.md
eslint.config.js		eslint.config.js
package.json		package.json
pnpm-lock.yaml		pnpm-lock.yaml
svelte.config.js		svelte.config.js
tsconfig.cli.json		tsconfig.cli.json
tsconfig.json		tsconfig.json
vite.config.ts		vite.config.ts

License

juspay/neurolink

Folders and files

Latest commit

History

Repository files navigation

🧠 NeuroLink

🚀 Enterprise Platform Features

✅ LATEST UPDATE: Factory Pattern Refactoring Complete (2025-01-20)

✅ Stream Function Migration Complete (2025-01-12)

🚀 Quick Start

Install & Run (2 minutes)

Basic Usage

🔗 CLI-SDK Consistency (NEW! ✨)

🆕 Enhanced Usage (NEW! ✨)

Enhanced CLI with Analytics & Evaluation

Enhanced SDK with Analytics & Evaluation

🌐 Enterprise Real-time Features (NEW! 🚀)

Real-time WebSocket Chat

Enterprise Telemetry Integration

Environment Setup

✨ Key Features

🛠️ MCP Integration Status ✅ BUILT-IN TOOLS WORKING

✅ Quick MCP Test (v1.7.1)

🔧 SDK Custom Tool Registration (NEW!)

⚡ Dynamic Model System (v1.8.0)

✅ Key Benefits

🚀 Quick Examples

📊 Current Model Inventory (Auto-Updated)

💻 Essential Examples

CLI Commands

SDK Integration

🎬 See It In Action

📱 Interactive Web Demo

🖥️ CLI Demonstrations

🌐 Web Interface Videos

📚 Documentation

Getting Started

Advanced Features

Reference

🏗️ Supported Providers & Models

🎯 Production Features

Enterprise-Grade Reliability

AI Platform Capabilities

🔧 Programmatic MCP Server Management [Coming Soon]

🤝 Contributing

Development Setup

New Developer Experience (v2.0)

📄 License

🔗 Related Projects

About

Topics

Resources

License

Code of conduct

Uh oh!

Stars

Watchers

Forks

Releases 19

Packages 0

Uh oh!

Contributors 6

Uh oh!

Languages

Packages