@juspay/neurolink 1.5.3 → 1.9.0

package/CHANGELOG.md

@@ -1,5 +1,242 @@
+# 1.9.0 (2025-06-20)
+
+
+* 🎉 feat: Enhanced multi-provider support with production infrastructure ([#16](https://github.com/juspay/neurolink/issues/16)) ([55eb81a](https://github.com/juspay/neurolink/commit/55eb81a4a7e88c94f6017565b14633b254a15197))
+
+
+### Bug Fixes
+
+* **cli:** prevent debug log persistence in production deployments ([#14](https://github.com/juspay/neurolink/issues/14)) ([7310a4c](https://github.com/juspay/neurolink/commit/7310a4cb405e1f35bcc5b22559f3da87a1d793f4))
+* production-ready CLI logging system and enhanced provider fallback ([#13](https://github.com/juspay/neurolink/issues/13)) ([a7e8122](https://github.com/juspay/neurolink/commit/a7e8122393f09cd85e473e5711fbfff05343025e))
+
+
+### Features
+
+* 🚀 MCP automatic tool discovery + dynamic models + AI function calling ([781b4e5](https://github.com/juspay/neurolink/commit/781b4e5c6e4886acb44a986f7b204eff346427e1))
+* add Google AI Studio integration and restructure documentation ([#11](https://github.com/juspay/neurolink/issues/11)) ([346fed2](https://github.com/juspay/neurolink/commit/346fed2ad458da07b80158f084afed8f3b804f06))
+* add Google AI Studio, fix CLI dependencies, and add LICENSE file ([#12](https://github.com/juspay/neurolink/issues/12)) ([c234bcb](https://github.com/juspay/neurolink/commit/c234bcb65ab1d07cb079ee9ffe9d61841aa945fb))
+* implement AI Development Workflow Tools and comprehensive visual documentation ([#10](https://github.com/juspay/neurolink/issues/10)) ([b0ae179](https://github.com/juspay/neurolink/commit/b0ae179d0b31936e4aa8c53c8e8a234cd467e7c3))
+* implement comprehensive CLI tool with visual documentation and … ([#4](https://github.com/juspay/neurolink/issues/4)) ([9991edb](https://github.com/juspay/neurolink/commit/9991edba7dbe7b9b33bd3b4e2b30186a81b40391))
+
+
+### BREAKING CHANGES
+
+* Enhanced provider architecture with MCP integration
+
+- ✨ MCP automatic tool discovery - detects 82+ tools from connected servers
+- 🎯 AI function calling - seamless tool execution with Vercel AI SDK
+- 🔧 Dynamic model configuration via config/models.json
+- 🤖 Agent-based generation with automatic tool selection
+- 📡 Real-time MCP server management and monitoring
+
+- Added MCPEnhancedProvider for automatic tool integration
+- Implemented function calling for Google AI, OpenAI providers
+- Created unified tool registry for MCP and built-in tools
+- Enhanced CLI with `agent-generate` and MCP management commands
+- Added comprehensive examples and documentation
+
+- Automatic .mcp-config.json discovery across platforms
+- Session-based context management for tool execution
+- Graceful fallback when MCP servers unavailable
+- Performance optimized tool discovery (<1ms per tool)
+
+- Added 5 new comprehensive guides (MCP, troubleshooting, dynamic models)
+- Created practical examples for all integration patterns
+- Updated API reference with new capabilities
+- Enhanced memory bank with implementation details
+
+Resolves: Enhanced AI capabilities with real-world tool integration
+* None - 100% backward compatibility maintained
+
+Closes: Enhanced multi-provider support milestone
+Ready for: Immediate production deployment
+Impact: Most comprehensive AI provider ecosystem (9 providers)
+
+Co-authored-by: sachin.sharma <sachin.sharma@juspay.in>
+
 # @juspay/neurolink
 
+## 1.8.0
+
+### 🎯 Major Feature: Dynamic Model Configuration System
+
+- **⚡ Revolutionary Model Management**: Introduced dynamic model configuration system replacing static enums
+
+  - **Self-Updating Models**: New models automatically available without code updates
+  - **Cost Optimization**: Automatic selection of cheapest models for tasks
+  - **Smart Resolution**: Fuzzy matching, aliases, and capability-based search
+  - **Multi-Source Loading**: Configuration from API → GitHub → local with fallback
+
+- **💰 Cost Intelligence**: Built-in cost optimization and model selection algorithms
+
+  - **Current Leader**: Gemini 2.0 Flash at $0.000075/1K input tokens
+  - **Capability Mapping**: Find models by features (function-calling, vision, code-execution)
+  - **Real-Time Pricing**: Always current model costs and performance data
+  - **Budget Controls**: Maximum price filtering and cost-aware selection
+
+- **🔧 Production-Ready Infrastructure**: Complete system with validation and monitoring
+
+  - **Model Configuration Server**: REST API with search capabilities (`scripts/model-server.js`)
+  - **Zod Schema Validation**: Type-safe runtime configuration validation
+  - **Comprehensive Testing**: Full test suite for all dynamic model functionality
+  - **Documentation**: Complete guide with examples and best practices
+
+- **🏷️ Smart Model Features**: Advanced model resolution and aliasing
+  - **Aliases**: Use friendly names like "claude-latest", "best-coding", "fastest"
+  - **Default Models**: Provider-specific defaults when no model specified
+  - **Fuzzy Matching**: "opus" → resolves to "claude-3-opus"
+  - **Deprecation Handling**: Automatically exclude deprecated models
+
+### Technical Implementation
+
+- **New Module**: `src/lib/core/dynamic-models.ts` - Core dynamic model provider
+- **Configuration**: `config/models.json` - Structured model definitions with metadata
+- **Integration**: Updated `AIProviderFactory` to use dynamic models by default
+- **Testing**: Comprehensive test suite (`test-dynamic-models.js`, `test-complete-integration.js`)
+- **Server**: Fake hosted server for testing and development (`scripts/model-server.js`)
+
+### API Enhancements
+
+- **Environment Variables**: Added `GOOGLE_AI_API_KEY` for better compatibility
+- **New Scripts**: `npm run model-server`, `npm run test:dynamic-models`
+- **Model Search API**: RESTful endpoints for model discovery and filtering
+- **Performance**: Sub-millisecond provider creation with intelligent caching
+
+### Current Model Inventory
+
+- **10 Active Models**: Across Anthropic, OpenAI, Google, and Bedrock
+- **Cost Range**: $0.000075 - $0.075 per 1K input tokens (100x cost difference)
+- **Capabilities**: Function-calling (9 models), Vision (7 models), Code-execution (1 model)
+- **Deprecation Tracking**: 1 deprecated model (GPT-4 Turbo) automatically excluded
+
+### Breaking Changes
+
+- **MCP Default**: MCP tools now enabled by default in `AIProviderFactory.createProvider`
+- **Environment**: Added `GOOGLE_AI_API_KEY` requirement for Google AI Studio
+- **Model Resolution**: Some edge cases in model name resolution may behave differently
+
+### Migration Notes
+
+- **Backward Compatible**: Existing code continues to work with improved functionality
+- **Optional Features**: Dynamic model features are additive and optional
+- **Configuration**: No changes required to existing `.env` files
+- **Performance**: Improved provider creation speed and reliability
+
+## 1.7.1
+
+### Bug Fixes - MCP System Restoration
+
+- **🔧 Fixed Built-in Tool Loading**: Resolved critical circular dependency issues preventing default tools from loading
+
+  - **Root Cause**: Circular dependency between `config.ts` and `unified-registry.ts` preventing proper initialization
+  - **Solution**: Implemented dynamic imports and restructured initialization chain
+  - **Result**: Built-in tools restored from 0 → 3 tools (100% recovery rate)
+
+- **⏰ Fixed Time Tool Functionality**: Time tool now properly available and returns accurate real-time data
+
+  - Fixed tool registration and execution pathway
+  - Proper timezone handling and formatting
+  - Verified accuracy against system time
+
+- **🔍 Enhanced External Tool Discovery**: 58+ external MCP tools now discoverable via comprehensive auto-discovery
+
+  - Auto-discovery across VS Code, Claude Desktop, Cursor, Windsurf
+  - Proper placeholder system for lazy activation
+  - Unified registry integration
+
+- **🏗️ Unified Registry Architecture**: Centralized tool management system now fully operational
+  - Seamless integration of built-in and external tools
+  - Proper initialization sequence and dependency management
+  - Enhanced debugging and status reporting
+
+### Technical Changes
+
+- Fixed circular dependency between core MCP modules
+- Updated `initialize.ts` to use dynamic imports preventing startup issues
+- Enhanced `loadDefaultRegistryTools()` to ensure proper built-in server registration
+- Temporarily disabled AI core server to resolve complex dependencies (utility server fully working)
+- Improved error handling and logging throughout MCP system
+
+### Validation Results
+
+- **Built-in Tools**: 3/3 working (get-current-time, calculate-date-difference, format-number)
+- **External Discovery**: 58+ tools discovered across multiple MCP sources
+- **Tool Execution**: Real-time AI tool calling verified and working
+- **System Integration**: Full CLI and SDK integration operational
+
+### Breaking Changes
+
+- None - all changes are backward compatible improvements
+
+### Migration Notes
+
+- Existing MCP configurations continue to work
+- Built-in tools now work automatically without additional setup
+- External tools require proper MCP server configuration (as before)
+
+## 1.7.0
+
+### Patch Changes
+
+- **🔧 Version Bump**: Updated version to 1.7.0 to publish the three-provider implementation
+  - All code changes were already included in 1.6.0 but not published
+  - This version publishes the complete implementation to npm
+
+## 1.6.0
+
+### Major Changes
+
+- **🎉 Universal AI Provider Support**: Expanded from 6 to 9 AI providers with support for open source models, local AI, and European compliance
+  - **🆕 Hugging Face Provider**: Access to 100,000+ open source models with community-driven AI ecosystem
+  - **🆕 Ollama Provider**: 100% local AI execution with complete data privacy and no internet required
+  - **🆕 Mistral AI Provider**: European GDPR-compliant AI with competitive pricing and multilingual models
+
+### Features
+
+- **🛠️ Enhanced CLI with Ollama Commands**: New Ollama-specific management commands
+
+  - `neurolink ollama list-models` - List installed local models
+  - `neurolink ollama pull <model>` - Download models locally
+  - `neurolink ollama remove <model>` - Remove installed models
+  - `neurolink ollama status` - Check Ollama service health
+  - `neurolink ollama start/stop` - Manage Ollama service
+  - `neurolink ollama setup` - Interactive setup wizard
+
+- **📚 Comprehensive Documentation**: Complete documentation for all new providers
+  - **OLLAMA-SETUP.md**: Platform-specific installation guides
+  - **PROVIDER-COMPARISON.md**: Detailed provider comparison matrix
+  - Updated all documentation to reflect 9 providers
+  - Enhanced provider configuration guides
+
+### Technical Implementation
+
+- **Provider Files**: `huggingFace.ts`, `ollama.ts`, `mistralAI.ts`
+- **Dependencies**: Added `@huggingface/inference`, `@ai-sdk/mistral`, `inquirer`
+- **MCP Integration**: All 10 MCP tools support new providers
+- **Demo Updates**: Enhanced demo to showcase all 9 providers
+- **CLI Enhancement**: Ollama command structure with 7 subcommands
+- **Provider Priority**: Updated auto-selection to include new providers
+
+### Provider Comparison
+
+| Provider     | Best For      | Setup Time | Privacy | Cost    |
+| ------------ | ------------- | ---------- | ------- | ------- |
+| OpenAI       | General use   | 2 min      | Cloud   | $$$     |
+| Ollama       | Privacy       | 5 min      | Local   | Free    |
+| Hugging Face | Open source   | 2 min      | Cloud   | Free/$$ |
+| Mistral      | EU compliance | 2 min      | Cloud   | $$      |
+
+### Bug Fixes
+
+- **🔧 Local Provider Fallback**: Implemented no-fallback policy for Ollama
+  - When explicitly requesting `--provider ollama`, no cloud fallback occurs
+  - Preserves user privacy intent when using local providers
+  - Auto-selection still maintains intelligent fallback
+
+### Breaking Changes
+
+- None - 100% backward compatibility maintained
+
 ## 1.5.3
 
 ### Patch Changes
@@ -38,12 +275,14 @@ neurolink generate-text "test" --debug
 ### Patch Changes
 
 - **🔧 Production-Ready CLI Logging System**: Fixed critical logging system for clean production output
+
   - **Issue**: CLI showed excessive debug output during normal operation, breaking demo presentations
   - **Root Cause**: Mixed console.log statements bypassed conditional logger system
   - **Solution**: Systematic replacement of all console.log with logger.debug across codebase
   - **Impact**: **Clean CLI output by default** with conditional debug available via `NEUROLINK_DEBUG=true`
 
 - **🔄 Enhanced Provider Fallback Logic**: Fixed incomplete provider fallback coverage
+
   - **Issue**: Provider fallback only attempted 4 of 6 providers (missing Anthropic & Azure)
   - **Root Cause**: Incomplete provider array in NeuroLink class fallback logic
   - **Solution**: Updated to include all 6 providers: `['openai', 'vertex', 'bedrock', 'anthropic', 'azure', 'google-ai']`
@@ -87,6 +326,7 @@ NEUROLINK_DEBUG=true node dist/cli/cli/index.js generate-text "test" --max-token
 ### Patch Changes
 
 - **🔧 Critical CLI Dependency Fix**: Removed peer dependencies to ensure zero-friction CLI usage
+
   - **Issue**: CLI commands failed when provider-specific SDK packages were peer dependencies
   - **Root Cause**: `npx` doesn't install peer dependencies, causing missing module errors
   - **Solution**: Moved ALL AI provider SDKs to regular dependencies
@@ -144,7 +384,7 @@ docs/
 
 ```typescript
 // New Google AI Studio usage
-import { createBestAIProvider } from '@juspay/neurolink';
+import { createBestAIProvider } from "@juspay/neurolink";
 
 const provider = createBestAIProvider(); // Auto-includes Google AI Studio
 const result = await provider.generateText("Hello, Gemini!");

package/README.md

@@ -1,12 +1,15 @@
 # 🧠 NeuroLink
 
-[![npm version](https://badge.fury.io/js/%40juspay%2Fneurolink.svg)](https://badge.fury.io/js/%40juspay%2Fneurolink)
-[![TypeScript](https://img.shields.io/badge/%3C%2F%3E-TypeScript-%230074c1.svg)](http://www.typescriptlang.org/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![NPM Version](https://img.shields.io/npm/v/@juspay/neurolink)](https://www.npmjs.com/package/@juspay/neurolink)
+[![Downloads](https://img.shields.io/npm/dm/@juspay/neurolink)](https://www.npmjs.com/package/@juspay/neurolink)
+[![GitHub Stars](https://img.shields.io/github/stars/juspay/neurolink)](https://github.com/juspay/neurolink/stargazers)
+[![License](https://img.shields.io/npm/l/@juspay/neurolink)](https://github.com/juspay/neurolink/blob/main/LICENSE)
+[![TypeScript](https://img.shields.io/badge/TypeScript-Ready-blue)](https://www.typescriptlang.org/)
+[![CI](https://github.com/juspay/neurolink/workflows/CI/badge.svg)](https://github.com/juspay/neurolink/actions)
 
-> Universal AI toolkit with 5+ provider support, automatic fallback, and both CLI + SDK interfaces. Production-ready with TypeScript support.
+> Universal AI toolkit with multiple provider support, automatic fallback, and both CLI + SDK interfaces. Production-ready with TypeScript support.
 
-**NeuroLink** unifies OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, and Azure OpenAI with intelligent fallback and streaming support. Available as both a **programmatic SDK** and **professional CLI tool**. Extracted from production use at Juspay.
+**NeuroLink** unifies OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, Azure OpenAI, Hugging Face, Ollama, and Mistral AI with intelligent fallback and streaming support. Available as both a **programmatic SDK** and **professional CLI tool**. Extracted from production use at Juspay.
 
 ## 🚀 Quick Start
 
@@ -29,12 +32,12 @@ npm install @juspay/neurolink
 ### Basic Usage
 
 ```typescript
-import { createBestAIProvider } from '@juspay/neurolink';
+import { createBestAIProvider } from "@juspay/neurolink";
 
 // Auto-selects best available provider
 const provider = createBestAIProvider();
 const result = await provider.generateText({
-  prompt: "Write a haiku about programming"
+  prompt: "Write a haiku about programming",
 });
 
 console.log(result.text);
@@ -57,20 +60,96 @@ npx @juspay/neurolink status
 
 ## ✨ Key Features
 
-- 🔄 **5+ AI Providers** - OpenAI, Bedrock, Vertex AI, Google AI Studio, Anthropic, Azure
+- 🔄 **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 support for extensibility
+- ✅ **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 (v1.7.1)
+
+| Component           | Status             | Description                                         |
+| ------------------- | ------------------ | --------------------------------------------------- |
+| Built-in Tools      | ✅ **Working**     | Time tool, utilities - fully functional             |
+| External Discovery  | ✅ **Working**     | 58+ MCP servers auto-discovered from all AI tools   |
+| Tool Execution      | ✅ **Working**     | Real-time AI tool calling with built-in tools       |
+| External Activation | 🔧 **Development** | Discovery complete, activation protocol in progress |
+
+### ✅ Quick MCP Test (v1.7.1)
+
+```bash
+# Test built-in tools (works immediately)
+npx @juspay/neurolink generate-text "What time is it?" --debug
+# Returns: "The current time is Friday, December 13, 2024 at 10:30:45 AM PST"
+
+# Test tool discovery
+npx @juspay/neurolink generate-text "What tools do you have access to?" --debug
+# AI will list 5+ built-in tools and 58+ discovered external servers
+
+# Test external server discovery
+npx @juspay/neurolink mcp discover --format table
+# Shows all discovered MCP servers from Claude, VS Code, Cursor, etc.
+```
+
+## ⚡ 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
+
+```bash
+# Cost optimization - automatically use cheapest model
+npx @juspay/neurolink generate-text "Hello" --optimize-cost
+
+# Capability search - find models with specific features
+npx @juspay/neurolink generate-text "Describe this image" --capability vision
+
+# Model aliases - use friendly names
+npx @juspay/neurolink generate-text "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](./docs/DYNAMIC-MODELS.md)** - Setup, configuration, and advanced usage
 
 ## 💻 Essential Examples
 
 ### CLI Commands
 
 ```bash
-# Text generation with provider selection
-npx @juspay/neurolink generate-text "Explain quantum computing" --provider openai
+# Text generation with automatic MCP tool detection (default)
+npx @juspay/neurolink generate-text "What time is it?"
+# AI automatically uses time tool for real-time data
+
+# Disable tools for training-data-only responses
+npx @juspay/neurolink generate-text "What time is it?" --disable-tools
 
 # Real-time streaming
 npx @juspay/neurolink stream "Tell me a story about robots"
@@ -108,21 +187,25 @@ export async function POST(request: NextRequest) {
 **No installation required!** Experience NeuroLink through comprehensive visual documentation:
 
 ### 📱 Interactive Web Demo
+
 ```bash
 cd neurolink-demo && node server.js
 # Visit http://localhost:9876 for live demo
 ```
 
-- **Real AI Integration**: All 5 providers functional with live generation
+- **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](./docs/visual-content/cli-videos/cli-01-cli-help.mp4)** - Complete command reference
 - **[Provider Status Check](./docs/visual-content/cli-videos/cli-02-provider-status.mp4)** - Connectivity verification
 - **[Text Generation](./docs/visual-content/cli-videos/cli-03-text-generation.mp4)** - Real AI content creation
 
 ### 🌐 Web Interface Videos
+
 - **[Business Use Cases](./neurolink-demo/videos/business-use-cases.mp4)** - Professional applications
 - **[Developer Tools](./neurolink-demo/videos/developer-tools.mp4)** - Code generation and APIs
 - **[Creative Tools](./neurolink-demo/videos/creative-tools.mp4)** - Content creation
@@ -132,43 +215,52 @@ cd neurolink-demo && node server.js
 ## 📚 Documentation
 
 ### Getting Started
+
 - **[🔧 Provider Setup](./docs/PROVIDER-CONFIGURATION.md)** - Complete environment configuration
 - **[🖥️ CLI Guide](./docs/CLI-GUIDE.md)** - All commands and options
 - **[🏗️ SDK Integration](./docs/FRAMEWORK-INTEGRATION.md)** - Next.js, SvelteKit, React
 - **[⚙️ Environment Variables](./docs/ENVIRONMENT-VARIABLES.md)** - Full configuration guide
 
 ### Advanced Features
+
 - **[🔄 MCP Foundation](./docs/MCP-FOUNDATION.md)** - Model Context Protocol architecture
+- **[⚡ Dynamic Models](./docs/DYNAMIC-MODELS.md)** - Self-updating model configurations and cost optimization
 - **[🧠 AI Analysis Tools](./docs/AI-ANALYSIS-TOOLS.md)** - Usage optimization and benchmarking
 - **[🛠️ AI Workflow Tools](./docs/AI-WORKFLOW-TOOLS.md)** - Development lifecycle assistance
 - **[🎬 Visual Demos](./docs/VISUAL-DEMOS.md)** - Screenshots and videos
 
 ### Reference
+
 - **[📚 API Reference](./docs/API-REFERENCE.md)** - Complete TypeScript API
 - **[🔗 Framework Integration](./docs/FRAMEWORK-INTEGRATION.md)** - SvelteKit, Next.js, Express.js
 
 ## 🏗️ Supported Providers & Models
 
-| Provider | Models | Auth Method | Free Tier |
-|----------|--------|-------------|-----------|
-| **OpenAI** | GPT-4o, GPT-4o-mini | API Key | ❌ |
-| **Google AI Studio** | Gemini 1.5/2.0 Flash/Pro | API Key | ✅ |
-| **Amazon Bedrock** | Claude 3.5/3.7 Sonnet | AWS Credentials | ❌ |
-| **Google Vertex AI** | Gemini 2.5 Flash | Service Account | ❌ |
-| **Anthropic** | Claude 3.5 Sonnet | API Key | ❌ |
-| **Azure OpenAI** | GPT-4, GPT-3.5 | API Key + Endpoint | ❌ |
+| Provider             | Models                       | Auth Method        | Free Tier |
+| -------------------- | ---------------------------- | ------------------ | --------- |
+| **OpenAI**           | GPT-4o, GPT-4o-mini          | API Key            | ❌        |
+| **Google AI Studio** | Gemini 1.5/2.0 Flash/Pro     | API Key            | ✅        |
+| **Amazon Bedrock**   | Claude 3.5/3.7 Sonnet        | AWS Credentials    | ❌        |
+| **Google Vertex AI** | Gemini 2.5 Flash             | Service Account    | ❌        |
+| **Anthropic**        | Claude 3.5 Sonnet            | API Key            | ❌        |
+| **Azure OpenAI**     | GPT-4, GPT-3.5               | API Key + Endpoint | ❌        |
+| **Hugging Face** 🆕  | 100,000+ models              | API Key            | ✅        |
+| **Ollama** 🆕        | Llama 2, Code Llama, Mistral | None (Local)       | ✅        |
+| **Mistral AI** 🆕    | Tiny, Small, Medium, Large   | API Key            | ✅        |
 
 **✨ 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
@@ -179,6 +271,7 @@ cd neurolink-demo && node server.js
 We welcome contributions! Please see our [Contributing Guidelines](./CONTRIBUTING.md) for details.
 
 ### Development Setup
+
 ```bash
 git clone https://github.com/juspay/neurolink
 cd neurolink