LMStudio - Download and run models on your computer - This looks very cool, my only worry is that it‘s not open source. That's not always an issue, but for something like running LLMs, I am somewhat more concerned about transparency because of how much access you have to give over. lmstudio.ai #
2025/08/09 #
-
-
Maple AI - Private AI chat that is truely secure - "End-to-end encryption means your conversations are confidential and protected at every step. Only you can access your data - not even we can read your chats". It‘s still cloud based but it‘s much more private and you can run more powerful models. I feel like I want a hybrid solution where I can run local models and private models in the cloud. trymaple.ai #
-
Continue - Build and run custom agents across your IDE, terminal, and CI - Last time I tried this it was having trouble loading, the website seemed fubared, but lots of people are still talking about it, so likely still one of the contenders. I haven‘t tried it yet. www.continue.dev #
-
Is it, like, OK to say ‘like’ now? - I actually remember when people started saying 'like' all the time. It seemed to happen over night, at least in the UK and in Europe. And yet now, it‘s strange to think there was a time when people didn‘t say it, like ever. Sort of like there was a time when there was no internet, no mobile phones. I hadn‘t really thought about it much, but it did have a profound effect on how we experience the world. www.theguardian.com #
-
Rawdogging, brat and looksmaxxing: Guardian’s breakthrough words of 2024 - I like the idea of some of these new slangs, like looksmazxxing for instance, but I think they are often better as written words rather than actually using them in spoken conversations. Vibecession is pretty funny. We are heading into alt coin season, so I am expecting the memeosphere to get a bit interesting the next few months. www.theguardian.com #
-
CodeRunner: Run AI Generated Code Locally - "CodeRunner is an MCP (Model Context Protocol) server that executes AI-generated code in a sandboxed environment on your Mac using Apple's native containers". I could definitely see this could be part of a local AI rig. github.com #
-
I Want Everything Local - Building My Offline AI Workspace - Great example of someone trying to cobble together various bits of tech into a local AI setup. It‘s still complicated but we are getting there. instavm.io #
-
Getting started with Podman AI Lab - I remembered this morning that Podman has this AI Lab extension. Re-read the blurb and I wonder if whether it might turn out to be the open source dark horse. I'll have to try this out sometime soon. It‘s been a long time since I used a Redhat product. Perhaps not the coolest kid on the block, but maybe for running AI agents dependability might be more important. developers.redhat.com #