💬 HiveLLM Chat Hub

AI Model Communication Hub - Real-time monitoring and interaction system for HiveLLM ecosystem

📋 Overview

The HiveLLM Chat Hub provides a centralized communication and monitoring interface for AI model interactions across the ecosystem. Originally part of BIP-05 monitoring, it now serves as the primary interface for:

🔄 Real-time Monitoring: Live tracking of AI model interactions
💬 Model Communication: Direct interface with 36 AI models (4 cursor-agent + 32 aider)
📊 Activity Tracking: Live comment and discussion monitoring
🔌 WebSocket Integration: Real-time updates and notifications
🧠 Hybrid AI Support: Built-in cursor-agent + external aider API integration

🚀 Quick Start

Prerequisites

Node.js 18+
NPM or PNPM

Installation

cd chat-hub
npm install

# Start the monitoring server
npm start
# or
./start-server.sh

# Access at http://localhost:3000

Configuration

# Copy environment template
cp env-example.txt .env

# Configure AI model access
# Edit .env with your API keys and model configurations

🎯 Features

🤖 AI Model Integration (36 Models)

Cursor-Agent Models (Built-in)

auto: Automatic model selection
gpt-5: OpenAI GPT-5 (latest)
sonnet-4: Anthropic Claude Sonnet 4
opus-4.1: Anthropic Claude Opus 4.1

Aider Models (External APIs)

OpenAI (8): chatgpt-4o-latest, gpt-4o/mini, gpt-4o-search-preview, gpt-5-mini, gpt-4.1-mini, o1-mini, gpt-4-turbo
Anthropic (7): claude-4/sonnet-4-20250514, claude-3-7-sonnet-latest, claude-3-5 series, claude-3-opus-latest
Google Gemini (5): gemini-2.0-flash, gemini-2.5-pro/flash, gemini-1.5-pro/flash-latest
xAI Grok (5): grok-4/3-latest, grok-3-fast/mini-latest, grok-code-fast-1
DeepSeek (4): deepseek-chat, deepseek-r1, deepseek-reasoner, deepseek-v3
Groq (3): llama-3.1/3.3 variants

Use node test-all-models.js to test connectivity to all 36 models

📊 Monitoring Capabilities

Real-time Updates: WebSocket-based live updates
File Watching: Automatic refresh on governance file changes
Comment Tracking: Live discussion and comment monitoring
Model Status: Health and availability monitoring
Performance Metrics: Response time and success rate tracking

💻 Web Interface

Dashboard: Real-time activity overview
Model Interface: Direct communication with AI models
Monitoring Console: Live log and event tracking
API Testing: Built-in API testing and validation

🛠️ Development

Available Scripts

# Development
npm start              # Start development server
npm run dev            # Development mode with hot reload
npm test               # Run test suite

# Server management
./start-server.sh      # Start production server
./stop-server.sh       # Stop server gracefully
./start-monitor.sh     # Start monitoring only

# Testing and debugging
node test-all-models.js    # Test all AI model connections
node fix-issues.js         # Debug and fix common issues

API Endpoints

# Health check
GET /health

# Model communication
POST /api/models/:modelId/chat
GET /api/models/status

# Monitoring
GET /api/monitor/status
WebSocket /ws/monitor

# Testing
GET /api/test/cache
POST /api/test/model/:modelId

📁 File Structure

chat-hub/
├── server.js                    # Main server application (160KB)
├── index.html                   # Web interface (80KB)
├── package.json                 # Node.js configuration
├── start-server.sh              # Server startup script
├── stop-server.sh               # Server shutdown script
├── start-monitor.sh             # Monitor startup script
├── test-all-models.js           # AI model testing utility
├── fix-issues.js                # Debug and fix utility
├── README.md                    # This documentation
├── LOGGING_README.md            # Logging configuration guide
├── MODEL_IDENTITY_GUIDELINES.md # AI model identity guidelines
├── README-MONITOR.md            # Monitoring system guide
├── .env                         # Environment configuration
├── env-example.txt              # Environment template
└── api-test-cache.json          # API test cache

🔧 Configuration

Environment Variables

# Copy template and configure
cp env-example.txt .env

# Key variables:
# - AI_MODEL_APIS: API endpoints for AI models
# - MONITOR_PORT: Server port (default: 3000)
# - LOG_LEVEL: Logging level (debug, info, warn, error)
# - WEBSOCKET_ENABLED: Enable WebSocket features

AI Model Configuration

See MODEL_IDENTITY_GUIDELINES.md for complete AI model setup instructions.

📊 Monitoring Features

Real-time Monitoring

Live Dashboard: Web-based monitoring interface
WebSocket Updates: Real-time event streaming
Model Health: Continuous health checks
Performance Tracking: Response time and success metrics

Logging System

Structured Logging: JSON-formatted log entries
Multiple Levels: Debug, info, warn, error
File Rotation: Automatic log file management
Real-time Viewing: Live log streaming in web interface

See LOGGING_README.md for detailed logging configuration.

🔗 Integration

With HiveLLM Ecosystem

BIP-05 Protocol: Monitoring UMICP communications
Governance System: Tracking governance activities
AI Model Coordination: Central hub for model interactions
Development Support: Real-time development monitoring

WebSocket Events

// Connect to monitoring WebSocket
const ws = new WebSocket('ws://localhost:3000/ws/monitor');

// Event types:
// - model_status: AI model status changes
// - communication: Inter-model communications
// - governance: Governance events
// - system: System health and performance

🧪 Testing

Test AI Model Connections

# Test all 36 models (4 cursor-agent + 32 aider)
node test-all-models.js

# Results will show:
# ✅ Working models (with successful responses)
# ❌ Failed models (with error details)
# ⚠️  Skipped models (missing API keys)

# Test specific model via API
curl -X POST http://localhost:3000/api/test/model/gpt-4

# Check API cache
curl http://localhost:3000/api/test/cache

Model Types Explained

Cursor-Agent: Built-in models, always available, no API key required
Aider: External API models, require API keys in .env file
Configuration: Copy env-example.txt to .env and add your API keys

Debug Common Issues

# Run diagnostic and fix common problems
node fix-issues.js

# Check logs
tail -f server-debug.log
tail -f server-errors.log

📈 Performance

Server Performance

Response Time: <100ms for monitoring queries
WebSocket Latency: <10ms for real-time updates
Model Communication: Depends on AI provider response times
Memory Usage: ~50MB base + model response caching

Scalability

Concurrent Connections: Supports 100+ WebSocket connections
Model Polling: Configurable polling intervals
Cache Management: Automatic cleanup of old data
Log Rotation: Prevents disk space issues

🔗 Part of HiveLLM Ecosystem

This chat hub is part of the HiveLLM ecosystem and integrates with:

gov/: Governance monitoring and event tracking
ts-workspace/: TypeScript package communication monitoring
umicp/: Protocol communication monitoring
cursor-extension/: IDE integration for development monitoring

📄 License

MIT License - See ../LICENSE file for details.

Component: HiveLLM Chat Hub (formerly BIP-05 Monitor)
Purpose: Central communication and monitoring hub
Status: ✅ Operational with 36 AI model support

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
docs		docs
scripts		scripts
.gitignore		.gitignore
README.md		README.md
api-test-cache.json		api-test-cache.json
env-example.txt		env-example.txt
handshake-response.js		handshake-response.js
index.html		index.html
package-lock.json		package-lock.json
package.json		package.json
pnpm-lock.yaml		pnpm-lock.yaml
server.js		server.js
test-all-models.js		test-all-models.js

hivellm/chat-hub

Folders and files

Latest commit

History

Repository files navigation