I stopped buying smart home gadgets and started building them for a fraction of the price
…I ditched a smart home hub and got a used, spec-bumped mini PC for $150. Then I installed Proxmox on it and ran Home Assistant as my smart home platform. I…
Search
One tiny change made my local LLMs more useful than ChatGPT for real work
…Related I use local LLMs and self-hosted apps to manage my documents instead of relying on ChatGPT Not every LLM-powered task requires a ChatGPT subscription RAG makes my LLMs more…
Everytime I set up a new Jellyfin server, these are the plugins I install first
…Samarveer holds a deep appreciation of gaming, and considers the platform to be the most immersive and impactful across all media. He can be found engaging with gaming communities online, always ready…
I stopped dual-booting Linux after discovering Windows' hidden kernel
…It is lighter than standard virtualization, and most people don't even know that Windows ships with it. I leveraged this native implementation to build a Paperless-ngx server that integrates with…
Self-hosted LLM took my personal knowledge management system to the next level
…It runs entirely on your own machine, requires minimal setup, and integrates smoothly with frameworks like LangChain and LlamaIndex. Not quite — the answer is ChromaDB. While PostgreSQL (with the pgvector extension) and…
I've been running some of the biggest open-weight LLMs for free on Nvidia's cloud
…You sign up at build.nvidia.com with the free Nvidia Developer account, you generate an API key prefixed with "nvapi-", and that's about it. The base URL is "https://integrate…
I've stopped recommending Plex to newcomers, because Jellyfin is ready for families now
…Samarveer holds a deep appreciation of gaming, and considers the platform to be the most immersive and impactful across all media. He can be found engaging with gaming communities online, always ready…
Home Assistant freed me from the smart home brand wars, and now I buy whatever works
…I still care about support, stability, and how well the integration works, of course. I just don’t have to pretend one brand is going to solve every possible smart home problem…
After a year of self-hosting LLMs, I realized the real bottleneck isn’t the GPU
…The correct answer is its built-in chat interface and local API server. LM Studio is entirely offline and free to use — it doesn't connect to OpenAI or require a subscription…
I used a local LLM to turn my NAS from a storage dump into something actually organized
…Client bills, ad platform receipts, software subscriptions, warranty documents, and hosting payments are just a few of the document types I deal with on a day-to-day basis. Between irrelevant file…