Rather than trying to run Whisper locally on an underpowered NAS, I offloaded transcription to Cloudflare Workers AI and article cleanup to LiteLLM, turning the NAS into an automation hub with its own web player for listening, searching, and reading.
Databases only know what you explicitly store; ontological reasoning lets a machine derive thousands of unstated facts from a handful of concept definitions — powerful, expensive to build, and increasingly paired with LLMs to keep each other’s weaknesses in check.
After bringing photos home to Immich, files were next — Seafile replaced Dropbox for syncing, then got paired with Open WebUI, RAG, and LiteLLM to turn a plain file store into a searchable, AI-queryable knowledge base.
A site that runs AI sentiment analysis on real Hacker News developer comments, rather than benchmark scores — Claude comes out on top for engineering sense, GPT close behind, with DeepSeek a notable dark horse.
Too many English finance and tech RSS feeds to skim by hand — TrendRadar, an open-source aggregator, filters, translates, and summarizes them via AI, then pushes the results to Telegram.
Investing talk kept leaking into work notes and vice versa — the fix was splitting Hermes into a router plus dedicated stock, work, diary, and life sub-assistants, each with its own knowledge base partition and a strict no-cross-referencing prompt.
Four quick tests of the new ChatGPT Images 2.0: visualizing my current life as the AI understands it, an imagined retirement, a comic-strip take on a 2013 journal entry about orchids, and a PowerPoint-generation test.
A personal assistant on the home NAS, a home assistant tied into an investment system, and an intelligence-gathering agent on a VPS — three modules starting to work together as a real perception-cognition-action loop, not just a pile of tools.
A full writeup of the LiteLLM gateway config behind my AI stack — free NVIDIA NIM and OpenRouter models as the safety net, cheap paid models like DeepSeek V3 for daily use, and Claude Sonnet as an on-demand top-tier fallback.
After getting Hermes running on a VPS, I moved it to my Synology NAS instead so it could gradually gain access to household journal and investment data as an internal AI hub — and redesigned the model routing along the way.
OpenClaw’s buzz is fading and everyone’s talking about Hermes — its token compression alone (50%+, reportedly up to 70% in some cases) was reason enough to spin up a VPS and try it.
Blind-testing two Ollama models against real CIPLE A2 Portuguese-exam questions, the well-documented, benchmark-topping model lost badly to an obscure community fine-tune — because the benchmarks were measuring Brazilian Portuguese, not European.
