You need these 6 self-hosted tools if you value your privacy
…could ever need, though some of the obscure ones can only be accepted as input files. For folks who’ve got a somewhat beefy machine with a decent GPU, you can even…
Search
Related topics:
LLMs
I built an offline research system, and cloud AI doesn't feel necessary anymore
…A local LLM handles most of what I need, Kiwix covers information gaps, and Obsidian keeps everything in one, manageable place. Online and cloud-based tools still have their place, but it…
I replaced over $1,000 in cloud subscriptions with one small home server
…If you want to use Ollama and Open WebUI for local LLM usage, you'll want a more powerful CPU and lots of RAM, because StartOS doesn't have GPU passthrough yet…
My media server started as a convenience project, but it has become one of my favorite things I’ve ever built
…My motivations for deploying a media server were pretty straightforward – I needed a centralized management interface for all the CDs, DVDs, and Blu-rays my family had collected for years. Before deploying…
Top stories
My self-hosted LLMs are a lot more than just a chat replacement – here's how they boost my productivity
3d agoAMD just dropped a compact AI workstation that makes discrete GPUs look outdated for running LLMs
1w agoI built my own Googlebook with a Raspberry Pi, local LLMs, and old hardware
1w agoI added a second GPU just for local AI workloads, and it cost less than upgrading my main one
1w agoI tried a new 8B local LLM, and its design might be the biggest shift since DeepSeek R1
…Instead of solving for a, b, c, the logs of each variable, and then plugging back in, it noticed that 5a + 2b + 3c was the only quantity it actually needed. It set…
I tested Qwen3 Coder Next against four other local AI coding models, and the gap was embarrassing
…Every other model either ignored the instruction entirely (Devstral 2), searched for the wrong thing (Qwen3.5 searched for generic "Python"), got the library IDs and then decided it didn't need…
I switched from Windows Terminal to WezTerm, and the difference is night and day
…It's GPU-accelerated, written in Rust, and runs on Windows, Linux, macOS, and BSD. Being cross-platform was a big selling point for me because I can get a familiar terminal…
I stopped being afraid to break my systems after learning what each OS actually needs to recover
…That's honestly been easier now I have a local LLM to help. It might be a little slow for some tasks, but figuring out YAML or Jinja syntax and why Home…
You can build a Steam Machine right now, but Valve's optimization is the part worth waiting for
…can run 200B+ local LLMs and play some of the latest games with good results, without even touching a discrete GPU. That's a tough sell for Valve, but it has a…
The Windows Terminal is quietly becoming the best terminal on any OS
…If you launch a terminal, you expect it to mold to your needs. For me, I need to have useful shortcuts, a granular settings app where I can set up and modify…