Eldric Cluster Architecture

Complete reference for distributed AI infrastructure with database connectivity

v4.0.0

Global Cluster Layout

Enterprise Multi-Region Deployment
Eldric Distributed AI Cluster Global Controller Primary - Port 8880 EU-WEST Region Controller Secondary Router 8881 Data 8892 Worker Ollama Worker vLLM Agent 8893 Media 8894 IIoT 8896 PostgreSQL EU Analytics DB US-EAST Region Controller Secondary Router 8881 Data 8892 Worker TGI Worker Triton Agent 8893 Media 8894 IIoT 8896 MySQL US App DB APAC Region Controller Secondary Router 8881 Data 8892 Worker llama.cpp Agent 8893 Media 8894 IIoT 8896 IBM DB2 z/OS Mainframe - DRDA Edge Layer - CDN / Gateway Edge Server Europe CDN Edge Server Americas CDN Edge Server Asia CDN API Gateway Load Balancer - SSL Swarm Controller 8885-8887 OpenWebUI External External Clients (Web Apps, Mobile, CLI, API Consumers) HTTPS / REST API / WebSocket / Voice Legend: Controller (8880) Router (8881) AI Worker (8890) Data Worker (8892) Agent Worker (8893) Media Worker (8894) IIoT Worker (8896) Edge Server Swarm (8885-8887) Databases v4.0.0

Node Types

Controller

Port 8880

Cluster orchestration and management. Handles node registration, job scheduling, license validation, and provides the management dashboard.

Tiers: Primary, Secondary, Tertiary

Binary: eldric-multiapi

Router

Port 8881

Intelligent request routing with AI-powered decisions. Routes requests to appropriate workers based on content, model requirements, and load.

Features: Theme detection, model specialization, load balancing, streaming support

Binaries:

  • eldric-routerd - Dedicated router daemon (recommended)
  • eldric-multiapi --router - Router mode in controller

AI Worker

Port 8890

Handles AI inference requests via multiple backends: Ollama, vLLM, TGI, llama.cpp, Triton, TensorFlow Serving.

Tiers: Core (GPU), Standard, Edge

Binary: eldric-workerd

Data Worker

Port 8892

Unified data service for storage, database connectivity, and vector/RAG. Supports PostgreSQL, MySQL, SQLite, IBM DB2.

Features: NFS server, connection pooling, schema discovery, vector storage

Binary: eldric-datad

Agent Worker

Port 8893

Agentic RAG orchestration with multi-tenant support. Query decomposition, multi-agent execution, training data generation.

Features: ReAct pattern, distributed RAG, workflow engine

Binary: eldric-agentd

Media Worker

Port 8894

Audio/video processing with STT (Whisper.cpp, OpenAI), TTS (Piper, ElevenLabs), video transcription, and multimedia RAG.

Features: Real-time streaming, voice chat, scene detection

Binary: eldric-mediad

IIoT Worker

Port 8896

Industrial IoT integration with OPC UA, Modbus, MQTT protocols. Real-time sensor data, PLC control, OEE monitoring.

Features: Smart home, industrial automation, AI edge inference

Binary: eldric-iiotd

Science Worker

Port 8897

Scientific computing daemon for bioinformatics, pharmaceutical research, CRISPR design, and LIMS integration.

Features: 140+ REST APIs, external DB integration (NCBI, UniProt, ChEMBL)

Binary: eldric-scienced

Training Worker

Port 8898

AI model training daemon with LoRA, QLoRA, SFT, DPO, RLHF support. MLX, Unsloth, TRL, DeepSpeed backends.

Features: Training chains, latent reasoning, multi-GPU support

Binary: eldric-traind

Edge Server

Port 443

External gateway for TLS termination, API key authentication, rate limiting, and request routing to routers.

Features: Farm mode for HA, health checking, OpenWebUI compatible

Binary: eldric-edge

Swarm Orchestrator

Port 8885-8887

Multi-agent orchestration with tiered swarm hierarchy for autonomous goal execution.

Features: Task decomposition, agent coordination, UAP protocol, MCP support

Binary: eldric-swarmd

Deployment Scenarios

1. Development Setup

Single machine for local development and testing

localhost Your Machine Controller :8880 Worker Ollama :8890 Data SQLite :8892 dev.db SQLite

2. Production Multi-Region

Global deployment with regional controllers

Global Primary US-WEST EU-WEST APAC Secondary Secondary Secondary vLLM Data TGI Data Triton Data PostgreSQL MySQL DB2

3. Enterprise Mainframe

IBM z/OS DB2 connectivity via DRDA

Eldric Cluster Controller :8880 Worker AI Inference Data DB2 CLI mainframe db2 DRDA :446 SSL IBM z/OS DB2 DSN1 / DSN1LOC VSAM IMS DB Pool: 5-50 conn

4. Knowledge Routing

AI-powered theme detection and model selection

Request "medical Q" AI Router Theme Detection medical legal code general Medical Worker meditron:70b Legal Worker saul:7b Code Worker codellama:34b General Worker llama3.1:70b AI selects optimal model

5. Swarm Multi-Agent Orchestration

Autonomous goal execution with tiered agent hierarchy

Eldric Swarm Architecture Global Orchestrator Goal Decomposition :8885 Research Controller :8886 Dev Controller :8886 Testing Controller :8886 Explorer Glob/Grep Searcher Web/Docs Planner Strategy Coder Edit/Write Runner Bash/Exec Database Query/Schema UAP Protocol · Gossip Messaging · Shared Memory · MCP Support AUTO

Use Cases

Enterprise AI Analytics Platform

User Query
→
Edge/CDN
→
Router
Theme Detection
→
AI Worker
SQL Generation
→
Data Worker
Query DB
→
AI Worker
Analyze Results

Multi-Database RAG Pipeline

Combine data from multiple enterprise databases for AI-powered analysis:

# AI Worker queries multiple data sources 1. Query PostgreSQL for customer data 2. Query MySQL for transaction history 3. Query DB2 z/OS for mainframe records 4. AI synthesizes all data into unified response

Real-time Business Intelligence

Dashboard Request
→
Controller API
→
Data Workers
→
DB Cluster
→
AI Summary

Voice-Enabled AI Assistant

End-to-end voice chat using Media Worker for STT/TTS:

Voice Input
Audio Stream
→
Media Worker
STT (Whisper)
→
AI Worker
LLM Response
→
Media Worker
TTS (Piper)
→
Voice Output
Audio Stream

Video Meeting Summarization

Transcribe and analyze recorded meetings:

# Video processing pipeline 1. Media Worker extracts audio from video 2. Media Worker transcribes with speaker diarization 3. Data Worker stores transcript with vector embeddings 4. Agent Worker generates meeting summary and action items 5. Comm Worker distributes summary via email/Teams

Unified Customer Communication

AI-powered multi-channel messaging with Comm Worker:

Customer
WhatsApp/Email/SMS
→
Comm Worker
Protocol Adapter
→
Data Worker
Message RAG
→
AI Worker
Draft Response
→
Comm Worker
Send Reply

Agentic Knowledge Search

Complex question answering with iterative retrieval:

# Agent Worker performs multi-hop reasoning 1. Agent Worker receives complex query 2. Decomposes into sub-questions (Query Decomposition) 3. Retrieves relevant documents from Data Worker (RAG) 4. Iteratively refines search based on findings (ReAct) 5. Synthesizes final answer with citations

Quick Reference

Start a Complete Cluster

# 1. Controller (management) ./eldric-multiapi -p 8880 # 2. Router - Option A: Dedicated daemon (recommended) ./eldric-routerd -p 8881 -c http://localhost:8880 --ai-routing # 2. Router - Option B: Controller router mode ./eldric-multiapi --router -p 8881 -c http://localhost:8880 # 3. AI Workers (inference) ./eldric-workerd -p 8890 -c http://localhost:8880 # 4. Data Worker (storage, databases, vector) ./eldric-datad -p 8892 -c http://localhost:8880 --vector --nfs # 5. Agent Worker (agentic RAG) ./eldric-agentd -p 8893 -c http://localhost:8880 --data-workers http://localhost:8892 # 6. Media Worker (STT/TTS/Video) ./eldric-mediad -p 8894 -c http://localhost:8880 --stt-backend whisper_cpp # 7. IIoT Worker (industrial IoT) ./eldric-iiotd -p 8896 -c http://localhost:8880 # 8. Science Worker (bioinformatics, pharma) ./eldric-scienced -p 8897 -c http://localhost:8880 # 9. Training Worker (model fine-tuning) ./eldric-traind -p 8898 -c http://localhost:8880 --data-workers http://localhost:8892 # 10. Edge Server (TLS gateway) ./eldric-edge -p 443 --cert /etc/ssl/cert.pem --key /etc/ssl/key.pem

Health Checks

curl http://localhost:8880/health # Controller curl http://localhost:8881/health # Router curl http://localhost:8890/health # AI Worker curl http://localhost:8892/health # Data Worker curl http://localhost:8893/health # Agent Worker curl http://localhost:8894/health # Media Worker curl http://localhost:8896/health # IIoT Worker curl http://localhost:8897/health # Science Worker curl http://localhost:8898/health # Training Worker

Swarm Architecture

Multi-agent orchestration system with tiered swarm intelligence for autonomous goal execution.

Tiered Swarm Hierarchy
Eldric Swarm - Multi-Agent Orchestration Global Orchestrator Goal Decomposition · Strategy · Coordination Regional Swarm: Research Coordinator Port 8885 Local Controller Task Queue Regional Swarm: Development Coordinator Port 8885 Local Controller Task Queue Regional Swarm: Testing Coordinator Port 8885 Local Controller Task Queue Specialized Agent Pool Explorer Glob · Grep · Read Planner Strategy · Decompose Coder Read · Write · Edit Runner Bash · Execute Searcher Web · Docs · API Database Query · Schema UAP Protocol (Universal Agent Protocol) · Gossip Messaging · Shared Memory · Belief Propagation Legend: Global Regional Agent

Swarm Orchestrator

Port 8885

Global goal management, task decomposition, and cross-swarm coordination. Routes goals to appropriate regional swarms.

Swarm Controller

Port 8886

Regional swarm management, agent lifecycle, task scheduling, and emergent behavior detection.

Agent Session

Port 8887

Individual agent execution context with tool access, memory management, and inter-agent communication.

Execution Modes

Advisory

Swarm proposes actions, waits for human approval before each step. Maximum oversight.

Supervised

Runs autonomously but requires approval for critical operations (writes, executions, external calls).

Autonomous

Full autonomous operation with real-time monitoring. Best for trusted, well-defined goals.

Port Reference

Component Default Port Protocol Purpose
Controller 8880 HTTP/REST Cluster API, Dashboard, Node Registration
Router 8881 HTTP/REST Request Routing, Load Balancing
AI Worker 8890 HTTP/REST LLM Inference, Tool Execution
Data Worker 8892 HTTP/REST Storage, Database, Vector/RAG
Agent Worker 8893 HTTP/REST Agentic RAG, Multi-Agent Execution
Media Worker 8894 HTTP/REST STT, TTS, Video Processing
IIoT Worker 8896 HTTP/REST Industrial IoT, OPC UA, Modbus, MQTT
Science Worker 8897 HTTP/REST Bioinformatics, Pharma, CRISPR, LIMS
Training Worker 8898 HTTP/REST AI Model Training, Fine-tuning
Edge Server 443 HTTPS TLS Termination, API Auth, Rate Limiting
Swarm Orchestrator 8885 HTTP/REST Goal Management, Task Decomposition
Swarm Controller 8886 HTTP/REST Agent Lifecycle, Task Scheduling
Agent Session 8887 HTTP/REST Agent Execution, Tool Access
Data NFS 2049 NFS Filesystem Access via NFS-Ganesha

Reserved Ports (Inference Backends)

Backend Port Notes
Ollama11434Local LLM runtime
vLLM8000OpenAI-compatible API
TGI8080HuggingFace Text Generation
llama.cpp8081Native GGUF serving
Triton8000-8002NVIDIA multi-framework
TensorFlow Serving8501TensorFlow models