AI
AI and machine learning on Linux — deploy LLMs, GPU setup, self-hosted AI tools, and intelligent automation for sysadmins and DevOps engineers.
Generate Ansible Playbooks with Local LLMs: AI-Assisted Infrastructure as Code
Build a local CLI tool that generates Ansible playbooks from natural language using Ollama. No vendor lock-in, full...
AI-Powered Log Analysis on Linux: Use Ollama to Parse Syslog, Journald, and Application Logs
Use Ollama and local LLMs to analyze Linux logs from journalctl, auth.log, and nginx. Includes a Python log analyzer,...
ComfyUI on a Headless Linux Server: Stable Diffusion with API Access
Install and run ComfyUI on a headless Linux server for Stable Diffusion image generation. Covers Python venv setup,...
Private LLM for Enterprise: Linux Deployment Architecture and Security Guide
Enterprise reference architecture for self-hosted LLMs on Linux. Covers data sovereignty, hardware sizing, network...
LocalAI on Linux: Deploy an OpenAI-Compatible API Server with Local Models
Set up LocalAI on Linux as a drop-in OpenAI API replacement. Covers Docker and binary installation, GGUF models, GPU...
Running Multiple Ollama Models: Memory Management and Optimization Guide
Configure Ollama to run multiple models simultaneously on Linux with proper VRAM partitioning, memory scheduling, model...
Ollama Python API: Build Linux Administration Tools with Local LLMs
Use the Ollama Python library to build practical sysadmin tools — log analyzers, config generators, incident...
Kubernetes Ollama Deployment: Production GPU Scheduling and Scaling Guide
Deploy Ollama on Kubernetes with GPU scheduling via nvidia-device-plugin, Helm charts, PersistentVolumeClaims for model...
GPU Monitoring for AI Workloads on Linux: Tools, Dashboards, and Alerts
Deep dive into gpu monitoring linux ai tools: nvidia-smi, nvtop, gpustat, Prometheus exporters, and Grafana dashboards....
Ollama Behind Nginx: Reverse Proxy with Authentication, SSL, and Rate Limiting
Production guide to running Ollama behind Nginx with SSL termination, basic and API key authentication, per-IP rate...
AnythingLLM on Linux: Self-Hosted RAG with Ollama and Document Chat
Set up AnythingLLM on Linux with Docker or bare metal, connect Ollama for local inference, ingest documents for RAG,...
LibreChat on Linux: Complete Installation and Multi-Provider Configuration Guide
Deploy LibreChat on Linux with Docker Compose, connect Ollama, OpenAI, Anthropic, and Azure simultaneously, configure...