Eldric

Cluster Architecture

Controller Port 8880

→

Router Port 8881

→

AI Worker Port 8890

↔

Data Worker Port 8895

Scalable multi-region deployment with intelligent routing and enterprise database connectivity

Documentation

Cluster Architecture

Complete reference for distributed AI infrastructure. Multi-region deployment, node types, port assignments, and sample configurations.

Architecture Deployment Diagrams

Data Worker

Database connectivity for AI workers. Connection pooling, PostgreSQL, MySQL, SQLite, and IBM DB2 (including z/OS mainframes).

New in 3.0.4 Database DB2

Knowledge Routing

AI-powered request routing with theme detection. Route requests to specialized models based on content (medicine, legal, code, etc.).

Routing AI Specialization

MultiAPI Reference

Controller API documentation. REST endpoints, cluster management, dashboard, licensing, and configuration options.

API Controller REST

Components

eldric-multiapi

Port 8880

Controller with dashboard, API, and cluster management

eldric-workerd

Port 8890

AI inference worker (Ollama, vLLM, TGI, etc.)

eldric-datad

Port 8895

Database connectivity service

eldric-edge

Port 8080

Edge/CDN gateway server

CLI

Interactive command-line client

Quick Start

# Build all components
cd cpp/build
cmake -DBUILD_DISTRIBUTED=ON -DBUILD_DATA_WORKER=ON ..
make -j4

# Start the cluster
./eldric-multiapi -p 8880 &           # Controller
./eldric-workerd -c http://localhost:8880 &  # AI Worker
./eldric-datad -c http://localhost:8880 &   # Data Worker

# Check cluster status
curl http://localhost:8880/api/v1/cluster/status
                

Supported Databases

SQLite

Built-in, always available

PostgreSQL

via libpq

MySQL

via libmysqlclient

IBM DB2

ODBC + CLI, z/OS support