AI
Practical AI workflows, local models, coding agents, automation, model serving, and infrastructure notes focused on real-world use and privacy.
Secure A LAN Model Server: Ollama And LM Studio Across VLANs
Define allowed clients, authentication and resource limits before exposing Ollama or LM Studio across VLANs. Evaluate each product's controls separately and check that direct backend access cannot bypass the intended path.
Can a Local Coding Model Run an Agent? Test Tools, Patches, and Safety
Use a disposable repository to test a self-hosted coding model's API, tool calls, patch quality, refusal boundaries, and rollback before giving it real code.
Is Your Self-Hosted AI Actually Private? Audit Every Data Path
A practical audit for local AI prompts, cloud model selection, web and vision sidecars, exposed APIs, logs, and backups before sensitive data enters the system.
Local LLMs in the Codex App: OpenCodex Setup and Privacy Limits
Compare the native Codex CLI local-model path with OpenCodex's third-party proxy for the desktop app. Verify actual routing, hosted sidecars and recovery before treating a local model as a private workflow.
From Digital Twin to Change Window: A Safe Network CI/CD Workflow
A network CI/CD workflow showing how to move from intent and digital twin validation to reviewed change windows, rollback, and post-change evidence.
Coding Agents In Docker Sandboxes: Test The Boundary
Distinguish Docker Sandboxes from ordinary containers before assessing a coding agent. Review mounts, credentials, sockets and network controls with harmless boundary tests, without claiming isolation makes escape impossible.
Network Source of Truth Before AgenticOps: NetBox, Nautobot, and Intent Data
A practical source-of-truth guide for preparing NetBox, Nautobot, and intent data before AI-assisted network automation.
Why Your Local Model Server Fails On User Two
Diagnose overlapping model requests through latency, queueing, failures and memory use. Compare consistent prompt workloads and cache conditions before setting admission limits from single-user throughput or another server's benchmark.
Ollama vs llama.cpp vs LM Studio vs Lemonade: Test the Runtime, Not the Logo
A local-AI runtime comparison framework for Ollama, llama.cpp, LM Studio, and Lemonade: hardware fit, context, APIs, concurrency, privacy, and evidence.
How to Block AI Scrapers: robots.txt, Rate Limits, and Access Control
State crawler preferences with robots.txt, enforce request policies with bot controls and rate limits, and authenticate private content. Test exceptions for legitimate traffic and retain logs without assuming every unwanted scraper is blocked.