What models are you using for your locally hosted AI? 10 Open-Source AI Models You Should Try In Your Home Lab (August 2025) https://www.virtualizationhowto.com/2025/08/10-open-source-ai-models-you-should-try-in-your-home-lab-august-2025/

i know this is breaking news, but Fable 5 has been sidelined by the US Gov't as of today. Has this had impacts in your homelab on projects you are working on? For my purposes i've had to switch back to opus 4.8 to continue development on a new ai platform i'm building..

Has anyone managed to achieve this successfully for daily work? My specs: Aoostar WTR Max 8845 - CPU: AMD Ryzen 7 PRO 8845HS (8-core, 16-thread, up to 5.1 GHz) - GPU: Integrated GPU: AMD Radeon 780M (RDNA 3, up to 2700MHz) - RAM2x 64Gb DDR5-5600 SODIMM slots (128GB) There are many opinions on the Internet about recommended hardware like a dedicated GPU but I just want to start with the iGPU first then scale up once I find the quality acceptable.

What am I self-hosting? - OpenWebUI - Ollama - llama3, codellama, gemini, phi3, etc - Kubectl-AI (***New!***) just dropped from Google Paid tools that I think are good? - Windsurf (paid product with free tier) - WarpAI (paid product with free tier) Tell me what I am missing from my list. Let me know what you are using.

Here is a good video on hardening security for OpenClaw. Also it appears that ClawHub has new tool for checking skills for possible malicious code as well you can have Openclaw scan the skills for anything unusual in the skill. https://www.youtube.com/watch?v=YCD2FSvj35I