(Modified:
2026-10-21)
— Written by
SimeonOnSecurity— 13 min read
Understand Hermes Agent and its parts — profiles, skills, memory, bots, the gateway, and the kanban board — and learn when the persistent model beats a per-project CLI coding agent.
(Modified:
2026-10-21)
— Written by
SimeonOnSecurity— 11 min read
Compare Ollama, vLLM, llama.cpp, and Strata as the inference backend behind an OpenAI-compatible broker. Load lifecycle, health checks, multi-GPU, and a decision table for 2026.
(Modified:
2026-10-21)
— Written by
SimeonOnSecurity— 12 min read
Put one OpenAI-compatible broker in front of Ollama, vLLM, llama.cpp, and Strata. Learn lazy loading, idle unload, pools, failover, retries, and non-loading health checks.
(Modified:
2026-10-21)
— Written by
SimeonOnSecurity— 11 min read
Send one auto request and let the broker, not the agent, pick a local GPU model or a remote premium model using capability filtering, cost tiers, cascade, latency budgets, and placement pinning.
(Modified:
2026-10-21)
— Written by
SimeonOnSecurity— 12 min read
Reach your local AI broker and cloud models from every device with zero public ports, tailnet identity, deny-by-default grants, and one URL using Tailscale Aperture.
