https://shadowfish.night-tower.net/tags/self-hosted/Recent content in Self-Hosted on ShadowfishHugo -- gohugo.ioen-us© 2026 Creeping depths of the deepTue, 04 Aug 2026 18:30:00 +0200https://shadowfish.night-tower.net/post/job-hunting-in-the-year-3456/Tue, 04 Aug 2026 18:19:00 +0200https://shadowfish.night-tower.net/post/job-hunting-in-the-year-3456/When recruiters demand a single Junior DevOps engineer who knows 70 tech stacks and 14 cloud providers, the only logical response is to build your own autonomous AI agent team with blackjack and local LLMs.https://shadowfish.night-tower.net/post/hermes-docker-nvidia-nemotron/Tue, 04 Aug 2026 17:38:00 +0200https://shadowfish.night-tower.net/post/hermes-docker-nvidia-nemotron/Deploying Hermes Agent containerized on Docker VM with Gemini AI pair programming and NVIDIA’s mistralai/mistral-nemotron endpoint leads to sub-second inference and 3-way Spider-Man pointing chaos.https://shadowfish.night-tower.net/post/herdr-homelab-agent-multiplexer/Tue, 28 Jul 2026 12:40:00 +0200https://shadowfish.night-tower.net/post/herdr-homelab-agent-multiplexer/Herdr is to AI coding agents what tmux is to terminals. Learn how to manage a fleet of local and remote AI agents across your homelab without bloaty desktop apps.https://shadowfish.night-tower.net/post/llm-token-benchmark-showdown/Tue, 28 Jul 2026 10:45:00 +0200https://shadowfish.night-tower.net/post/llm-token-benchmark-showdown/We benchmarked Qwen 2.5, Gemma 2, and Ministral 3 across two homelab machines. Spoiler: Gemma 2 took 140 seconds to load on CPU, giving us time to rethink life choices.https://shadowfish.night-tower.net/post/n8n-multi-llm-orchestration/Wed, 22 Jul 2026 12:00:00 +0200https://shadowfish.night-tower.net/post/n8n-multi-llm-orchestration/Discover how to orchestrate multi-LLM workflows using self-hosted n8n, Python scripts, and Docker to automate complex AI content pipelines.